KR20220146209A - Method for image-based table border generation - Google Patents

Abstract

Provided is a method for generating an image-based table boundary line which is executed by a computing device including at least one processor according to some embodiments of the present disclosure. The method comprises the steps of: generating a training data set including a source domain and a target domain which are used to train a table boundary line generation model in a pair form by using a pre-trained training data generation model; and training the table boundary line generation model using the training data set. The source domain may include a first table in which at least one of a horizontal boundary line and a vertical boundary line does not exist. The target domain may include a second table in which the horizontal boundary line and the vertical boundary line exist. According to the present invention, the method is capable of converting a table in which a part of a boundary line does not exist into a table in which all boundary lines exist.

Description

{METHOD FOR IMAGE-BASED TABLE BORDER GENERATION}

The present disclosure relates to a method for generating an image-based table boundary, and more particularly, to a method for generating an image-based table boundary by converting a table in which some boundary lines do not exist into a table in which all boundary lines exist.

A Table Structure Recognition (TSR) model may recognize a table structure included in input data and return it in a machine readable format (eg, html, spreadsheet, etc.). This TSR model can recognize the structure of the table by approaching rule-based when all boundaries exist in the table included in the input data, and return it in a machine-readable format.

However, when some of the boundary lines of the table included in the input data do not exist, many errors are caused and the accuracy is lowered. Specifically, referring to the paper “Image-based table recognition: data, model, and evaluation. arXiv preprint arXiv:1911.10683 (2019)”, the TSR model is 96-97% of the table boundary included in the input data. It showed accuracy, and when the boundary line of the table included in the input data was incomplete, it was found to show an accuracy of 52%.

Therefore, an attempt was made to solve the problem of low accuracy when the boundary of the table included in the input data is incomplete by using deep learning.

However, due to the nature of deep learning that is dependent on data, it shows low performance when there is insufficient data, and does not show high accuracy when the learned data and other types of edge-cases are input as input data even when the training data is sufficient. have. In addition, there are various variables such as blank cells and merging between cells as well as the case where there are no horizontal or vertical lines in the table. There is a problem that hinders it.

Republic of Korea Patent Registration No. 10-0277831 (Registered on January 15, 2001)

The present disclosure has been devised in response to the above-described background art, and is intended to provide an image-based table boundary generation method for converting a table in which some boundary lines do not exist into a table in which all boundary lines exist.

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 following description.

An image-based table boundary generation method performed by a computing device including at least one processor for solving the above-described problem, a source domain used for learning the table boundary generation model using a pre-trained training data generation model generating a training data set including a source domain and a target domain in the form of a pair; and training the table boundary generation model using the training data set, wherein the source domain includes a first table in which at least one of a horizontal boundary line and a vertical boundary line does not exist, The target domain may include a second table in which a horizontal boundary line and a vertical boundary line exist.

Alternatively, the table boundary line generation model may be trained to generate the target domain corresponding to the source domain by determining a horizontal boundary line and a vertical boundary line based on the first content included in each cell of the first table. have.

Alternatively, the target domain may include the first content in each cell of the second table corresponding to the respective cell of the first table.

Alternatively, the first content may include at least one of letters, numbers, and pictures.

Alternatively, by using the table boundary generation model that has been trained, input data including a table in which at least one of a horizontal boundary line and a vertical boundary line does not exist is converted to result data including a table in which a horizontal boundary line and a vertical boundary line exist. converting and outputting; may further include.

Alternatively, the second content included in each cell of the table included in the input data may be included in each cell of the table of the result data corresponding to the respective cell of the table of the input data.

Alternatively, the second content may include at least one of letters, numbers, and pictures.

Alternatively, the training data generation model generates a training data set including a plurality of different source domains and a plurality of target domains corresponding to each of the plurality of source domains in a pair form, and the plurality of sources Each domain may include a table in which at least one of a horizontal boundary line and a vertical boundary line does not exist, and each of the plurality of target domains may include a table in which a horizontal boundary line and a vertical boundary line exist.

Alternatively, the plurality of source domains have different attributes, and the plurality of target domains have a corresponding attribute and a corresponding attribute of each of the plurality of source domains, and the attribute is located in each cell of the table. It may include at least one of a first property related to the included content and a second property related to a table.

Alternatively, the first attribute may include at least one of a size of the content, a color of the content, or a shape of the content, and the second attribute may include a background color of a table, a thickness of a horizontal boundary line, a thickness of a vertical boundary line, At least one of a color of a horizontal boundary line or a color of a vertical boundary line may be included.

Alternatively, the source domain is an image including the first table or data configured in a programming language expressing the first table, and the target domain is an image including the second table or the second table. It may be data composed of a programming language expressing

Alternatively, the training data generation model generates a second target domain using a first source domain and a first target domain corresponding to the first source domain, and the first source domain and the second target domain generate a training data set including in the form of a pair, wherein the first source domain includes a third table in which at least one of a horizontal boundary line and a vertical boundary line does not exist and third content is included in each cell, The first target domain includes a fourth table in which horizontal and vertical boundaries exist and each cell is empty, and the second target domain includes each cell of the fourth table and each cell of the third table. It may include a table in which the included third content is inserted.

A computer program stored in a computer-readable storage medium for solving the above-described problem, the computer program comprising instructions for causing a processor of a computing device to generate a boundary line of an image-based table to perform the following steps, , the steps are: Using a pre-trained training data generation model, a training data set including a source domain and a target domain used for training a table boundary generation model in a pair form creating a; and training the table boundary generation model using the training data set, wherein the source domain includes a first table in which at least one of a horizontal boundary line and a vertical boundary line does not exist, The target domain may include a second table in which a horizontal boundary line and a vertical boundary line exist.

A computing device for generating a boundary line of an image-based table in order to solve the above-described problem, the computing device comprising: a processor including at least one core; and a memory for storing a computer program executable by the processor, wherein the processor includes a source domain and a target used for training a table boundary generation model using a pre-trained training data generation model. A training data set including a target domain in a pair form is generated, and the table boundary generation model is trained using the training data set, and the source domain includes a horizontal boundary line and a vertical boundary line. A first table in which at least one does not exist may be included, and the target domain may include a second table in which a horizontal boundary line and a vertical boundary line exist.

The present disclosure may provide an image-based table boundary generation method capable of converting a table in which some boundary lines do not exist into a table in which all boundary lines exist.

The effects obtainable in the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those of ordinary skill in the art to which the present disclosure belongs from the description below. .

Various aspects are now described with reference to the drawings, wherein like reference numbers are used to refer to like elements collectively. In the following examples, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more aspects. It will be evident, however, that such aspect(s) may be practiced without these specific details.
1 is a block diagram of a computing device in accordance with some embodiments of the present disclosure.
2 is a schematic diagram illustrating a network function according to some embodiments of the present disclosure.
3 is a flowchart illustrating an example of a method of generating a boundary line of a table according to some embodiments of the present disclosure.
4 is a diagram illustrating a source domain and a target domain for generating a boundary line of a table according to some embodiments of the present disclosure.
5 is a diagram illustrating a process of generating a training data set for generating a boundary line of a table according to some embodiments of the present disclosure.
6 is a diagram illustrating a process of generating a training data set for generating a boundary line of a table according to some other embodiments of the present disclosure.
7 is a diagram illustrating a process of generating a boundary line of a table according to some embodiments of the present disclosure.
8 is a diagram illustrating a process of generating a boundary line of a table according to some other embodiments of the present disclosure.
9 depicts a simplified, 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 present disclosure. However, it is apparent that these embodiments may be practiced without these specific descriptions.

The terms “component,” “module,” “system,” and the like, as used herein, refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or execution of software. For example, a component can be, but is not limited to being, 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 may 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. In addition, these components can execute from various computer readable media having various data structures stored therein. Components may communicate via a network such as the Internet with another system, for example via a signal having one or more data packets (eg, data and/or signals from one component interacting with another component in a local system, distributed system, etc.) may communicate via local and/or remote processes depending on the data being transmitted).

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from context, "X employs A or B" is intended to mean one of the natural implicit substitutions. That is, X employs A; X employs B; or when X employs both A and B, "X employs A or B" may apply to either of these cases. It should also be understood that the term “and/or” as used herein refers to and includes all possible combinations of one or more of the listed related items.

Also, the terms "comprises" and/or "comprising" should be understood to mean that the feature and/or element in question is present. However, it should be understood that the terms "comprises" and/or "comprising" do not exclude the presence or addition of one or more other features, elements and/or groups thereof. Also, unless otherwise specified or unless it is clear from context to refer to a singular form, the singular in the specification and 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 "when including only A", "when including only B", and "when combined with the configuration of A and B".

Those skilled in the art will further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or combinations of both. It should be recognized that they can be implemented with To clearly illustrate this 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 as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Descriptions of the presented embodiments are provided to enable those 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 of the present disclosure. The generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present invention is not limited to the embodiments presented herein. The invention is to be construed in its widest scope consistent with the principles and novel features presented herein.

In the present disclosure, a network function and an artificial neural network and a neural network may be used interchangeably.

The image-based table boundary generation method according to some embodiments of the present disclosure may refer to a method of generating a training data set using a pre-trained training data generation model and training the table boundary generation model using the training data set. have.

1 is a block diagram of a computing device in accordance with some embodiments of the present disclosure.

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

The computing device 100 may include at least one processor 110 , a memory 130 , and a network unit 150 .

The processor 110 may include one or more cores, and a central processing unit (CPU) of a computing device, a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU). unit) and the like, and may include a processor for data analysis and deep learning. The processor 110 may read a computer program stored in the memory 130 to perform data processing for machine learning according to some embodiments of the present disclosure. According to some embodiments of the present disclosure, the processor 110 may perform an operation for learning the neural network. The processor 110 for learning of the neural network, such as processing input data for learning in deep learning (DL), extracting features from the input data, calculating an error, updating the weight of the neural network using backpropagation calculations can be performed. At least one of a CPU, a GPGPU, and a TPU of the processor 110 may process learning of a network function. For example, the CPU and the GPGPU can process learning of a network function and data classification using the network function. Also, in an embodiment of the present disclosure, learning of a network function and data classification using the network function may be processed by using the processors of a plurality of computing devices together. In addition, the computer program executed in the computing device according to an embodiment of the present disclosure may be a CPU, GPGPU or TPU executable program.

According to some embodiments of the present disclosure, the processor 110 may generate a boundary line of an image-based table. A detailed description thereof will be described later with reference to FIG. 3 .

The memory 130 according to some embodiments of the present disclosure may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150 .

According to some embodiments of the present disclosure, the memory 130 is a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (eg, For example, SD or XD memory), Random Access Memory (RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read (PROM) -Only Memory), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. The computing device 100 may operate in relation to a web storage that performs a storage function of the memory 130 on the Internet. The description of the above-described memory is only an example, and the present disclosure is not limited thereto.

The network unit 150 according to some embodiments of the present disclosure may include any wired/wireless communication network capable of transmitting and receiving any type of data and signals, etc., in the network represented in the present disclosure. The techniques described herein may be used in the networks mentioned above, as well as in other networks.

2 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure;

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is configured to include at least one or more nodes. Nodes (or neurons) constituting the neural networks may be interconnected by one or more links.

In the neural network, one or more nodes connected through a link may relatively form a relationship between an input node and an output node. The concepts of an input node and an output node are relative, and any node in an output node relationship with respect to one node may be in an input node relationship in a relationship with another node, and vice versa. As described above, an input node-to-output node relationship may be created around a link. One or more output nodes may be connected to one input node through a link, and vice versa.

In the relationship between the input node and the output node connected through one link, the value of the data of the output node may be determined based on data input to the input node. Here, a link interconnecting the input node and the output node may have a weight. The weight may be variable, and may be changed by the user or algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node sets values input to input nodes connected to the output node and links corresponding to the respective input nodes. An output node value may 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 an output node relationship in the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the correlation between the nodes and the links, and the value of a weight assigned to each of the links. For example, when the same number of nodes and links exist and there are two neural networks having different weight values of the links, 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 constituting the neural network may constitute a layer. Some of the nodes constituting the neural network may configure one layer based on distances from the initial input node. For example, a set of nodes having a distance n from the initial input node may constitute n layers. The distance from the initial input node may be defined by the minimum number of links that must be traversed to reach the corresponding node from the initial input node. However, the definition of such a layer is arbitrary for description, and the order of the layer in the neural network may be defined in a different way from the above. For example, a layer of nodes may be defined by a distance from the final output node.

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

The neural network according to an embodiment of the present disclosure may be 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 the input layer progresses to the hidden layer. 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 the number of nodes progresses from the input layer to the hidden layer. have. 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 the number of nodes progresses from the input layer to the hidden layer. can The neural network according to another embodiment of the present disclosure may be a neural network in a combined form of the aforementioned neural networks.

A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can be used to identify the latent structures of data. In other words, it can identify the potential structure of photos, texts, videos, voices, and music (e.g., what objects are in the photos, what the text and emotions are, what the texts and emotions are, etc.) . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, generative adversarial networks (GANs), and restricted boltzmann machines (RBMs). machine), a deep belief network (DBN), a Q network, a U network, a Siamese network, and a Generative Adversarial Network (GAN). The description of the deep neural network described above is only an example, and the present disclosure is not limited thereto.

In an embodiment of the present disclosure, the network function may include an autoencoder. The auto-encoder may be a kind of artificial neural network for outputting output data similar to input data. The auto encoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between the input/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 with reduction from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform non-linear dimensionality reduction. The number of input layers and output layers may correspond to a dimension after preprocessing the input data. In the auto-encoder structure, the number of nodes of 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 between the encoder and decoder) is too small, a sufficient amount of information may not be conveyed, so a certain number or more (e.g., more than half of the input layer, etc.) ) may be maintained.

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

A neural network can be trained in a way that minimizes output errors. In the training of a neural network, iteratively input the training data into the neural network, calculate the output of the neural network and the target error for the training data, and calculate the error of the neural network from the output layer of the neural network to the input layer in the direction to reduce the error. It is the process of updating the weight of each node of the neural network by backpropagation in the direction. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (ie, labeled learning data), and in the case of comparative learning, the correct answer may not be labeled in each learning data. That is, for example, the learning data in the case of teacher learning regarding data classification may be data in which categories are labeled for each of the learning data. Labeled training data is input to the neural network, and an 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 comparison learning about data classification, an error may be calculated by comparing the input training data with the output of the neural network. The calculated error is back propagated in the reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back propagation. A change amount of the connection weight of each node to be updated may be determined according to a learning rate. The computation of the neural network on the input data and the 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 stage of learning of a neural network, a high learning rate can be used to enable the neural network to quickly acquire a certain level of performance, thereby increasing efficiency, and using a low learning rate at the end of learning can increase accuracy.

In training of a neural network, in general, the training data may be a subset of real data (that is, data to be processed using the trained neural network), and thus the error on the training data is reduced, but the error on the real data is reduced. There may be increasing learning cycles. Overfitting is a phenomenon in which errors on actual data increase by over-learning on training data as described above. For example, a phenomenon in which a neural network that has learned a cat by seeing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting. Overfitting can act as a cause of increasing errors in machine learning algorithms. In order to prevent such overfitting, various optimization methods can be used. In order to prevent overfitting, methods such as increasing the training data, regularization, and dropout that deactivate some of the nodes of the network in the process of learning, and the use of a batch normalization layer are applied. can

A computer readable medium storing a data structure is disclosed according to some embodiments of the present disclosure.

The data structure may refer to the organization, management, and storage of data that enables efficient access and modification of data. A data structure may refer to an organization of data to solve a specific problem (eg, data retrieval, data storage, and data modification in the shortest time). A data structure may be defined as a physical or logical relationship between data elements designed to support a particular data processing function. The logical relationship between data elements may include a connection relationship between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements physically stored on a computer-readable storage medium (eg, persistent storage). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to data. Through an effectively designed data structure, a computing device can perform an operation while using the computing device's resources to a minimum. Specifically, the computing device may increase the efficiency of operations, reads, insertions, deletions, comparisons, exchanges, and retrievals through effectively designed data structures.

A data structure may be classified into a linear data structure and a non-linear data structure according to the type of the data structure. The linear data structure may be a structure in which only one piece of data is connected after one piece of data. The linear data structure may include a list, a stack, a queue, and a deck. A list may mean a set of data in which an order exists internally. The list may include a linked list. The linked list may be a data structure in which data is linked in such a way that each data is linked in a line with a pointer. In a linked list, a pointer may contain information about a link with the next or previous data. A linked list may be expressed as a single linked list, a doubly linked list, or a circularly linked list according to a shape. A stack can be a data enumeration structure with limited access to data. A stack can be a linear data structure in which data can be processed (eg, inserted or deleted) at only one end of the data structure. The data stored in the stack may be a data structure LIFO-Last in First Out. A queue is a data listing structure that allows limited access to data, and unlike a stack, it may be a data structure that comes out later (FIFO-First in First Out) as data stored later. A deck can be a data structure that can process data at either end of the data structure.

The nonlinear data structure may be a structure in which a plurality of data is connected after one data. The nonlinear data structure may include a graph data structure. A graph data structure may be defined as a vertex and an edge, and the edge may include a line connecting two different vertices. A graph data structure may include a tree data structure. The tree data structure may be a data structure in which one path connects two different vertices among a plurality of vertices included in the tree. That is, 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. Hereinafter, the neural network is unified and described. The data structure may include a neural network. And the data structure including the neural network may be stored in a computer-readable medium. Data structures, including neural networks, also include 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 obtained from the neural network, activation functions associated with each node or layer of the neural network, and the neural network. It may include a loss function for learning of . A data structure comprising a neural network may include any of the components disclosed above. That is, 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 obtained from the neural network, activation functions associated with each node or layer of the neural network, and the neural network It may be configured to include all or any combination thereof, such as a loss function for learning of . In addition to the above-described configurations, a data structure including a neural network may include any other information that determines a characteristic of the neural network. In addition, the data structure may include all types of data used or generated in the operation process of the neural network, and is not limited thereto. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is configured to include at least one or more nodes.

The data structure may include data input to the neural network. A data structure including data input to the neural network may be stored in a computer-readable medium. The data input to the neural network may include learning data input in a neural network learning process and/or input data input to the neural network in which learning is completed. Data input to the neural network may include pre-processing data and/or pre-processing target data. The preprocessing may include a data processing process for inputting data into the neural network. Accordingly, the data structure may include data to be pre-processed and data generated by pre-processing. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, a weight and a parameter may be used interchangeably.) And a data structure including a weight of a neural network may be stored in a computer-readable medium. The neural network may include a plurality of weights. The weight may be variable, and may be changed by the user or algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node sets values input to input nodes connected to the output node and links corresponding to the respective input nodes. A data value output from the output node may be determined based on the weight. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

By way of example and not limitation, the weight may include a weight variable in a neural network learning process and/or a weight in which neural network learning is completed. The variable weight in the neural network learning process may include a weight at the start of the learning cycle and/or a variable weight during the learning cycle. The weight for which neural network learning is completed may include a weight for which a learning cycle is completed. Accordingly, the data structure including the weights of the neural network may include a data structure including the weights that vary in the neural network learning process and/or the weights on which the neural network learning is completed. Therefore, it is assumed that the above-described weights and/or combinations of weights are included in the data structure including the weights of the neural network. The above-described data structure is merely 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 (eg, memory, hard disk) after being serialized. Serialization can be the process of converting a data structure into a form that can be reconstructed and used later by storing it on the same or a different computing device. The computing device may serialize the data structure to send and receive data over a network. A data structure including weights of the serialized neural network may be reconstructed in the same computing device or in another computing device through deserialization. The data structure including the weight 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 the efficiency of computation while using the resources of the computing device to a minimum (e.g., B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree). The foregoing is merely an example, and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of the neural network. In addition, the data structure including the hyperparameters of the neural network may be stored in a computer-readable medium. The hyper parameter may be a variable variable by a user. Hyperparameters are, for example, learning rate, cost function, number of iterations of the learning cycle, weight initialization (e.g., setting the range of weight values to be initialized for weights), Hidden Unit The number (eg, the number of hidden layers, the number of nodes of the hidden layer) may be included. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

On the other hand, a specific model (eg, a table structure recognition (TSR) model) may have poor accuracy when a part of a boundary line of a table included in input data does not exist. Accordingly, the processor 110 of the computing device 100 may convert a table in which some boundary lines do not exist into a table in which all boundary lines exist in order to increase the accuracy of a specific model. A detailed description thereof will be described later with reference to FIGS. 3 to 8 .

3 is a flowchart illustrating an example of a method of generating a boundary line of a table according to some embodiments of the present disclosure. 4 is a diagram illustrating a source domain and a target domain for generating a boundary line of a table according to some embodiments of the present disclosure. 5 is a diagram illustrating a process of generating a training data set for generating a boundary line of a table according to some embodiments of the present disclosure. 6 is a diagram illustrating a process of generating a training data set for generating a boundary line of a table according to some other embodiments of the present disclosure. 7 is a diagram illustrating a process of generating a boundary line of a table according to some embodiments of the present disclosure. 8 is a diagram illustrating a process of generating a boundary line of a table according to some other embodiments of the present disclosure.

Referring to FIG. 3 , the processor 110 uses the pre-trained training data generation model to form a pair of a source domain and a target domain used for training the table boundary generation model. It is possible to generate a training data set including (S110).

Referring to FIG. 4 , FIG. 4(a) may be a source domain and FIG. 4(b) may be a target domain. Referring to FIG. 4A , the source domain may include a first table in which at least one of a horizontal boundary line and a vertical boundary line does not exist. For example, as shown in FIG. 4A , the source domain may include a table in which a horizontal boundary line of each cell does not exist. In addition, the source domain may be an image including the first table or data composed of a program language expressing the first table. Here, the data configured in the program language may include a hypertext markup language (HTML) format, a data frame format, and a comma separated value (CSV) format. However, data configured in a programming language is not limited thereto.

Also, referring to FIG. 4B , the target domain may include a second table in which a horizontal boundary line and a vertical boundary line exist. For example, as shown in FIG. 4B , the target domain may include a table in which a horizontal boundary line and a vertical boundary line of each cell exist. In addition, the target domain may be an image including the second table or data composed of a program language expressing the second table.

As such, the processor 110 generates learning data using data configured in various program languages, so that the processor 110 learns a table boundary line generation model using the learning data configured in various program languages, and is configured in various programming languages. Result data may be output corresponding to input data.

Further, according to some embodiments of the present disclosure, the target domain may include the first content in each cell of the second table corresponding to each cell of the first table. Specifically, the target domain may include the first content present in each cell of the first table included in the source domain in each cell of the second table corresponding to each cell of the first table. Here, the first content may include at least one of letters, numbers, and pictures. Accordingly, the processor 110 may generate various training data sets using a target domain including content as well as horizontal and vertical boundaries. However, the target domain and the first content are not limited thereto.

Meanwhile, the processor 110 may use a training data generation model to generate a training data set. A detailed description thereof will be described later with reference to FIGS. 5 and 6 .

Referring to FIG. 5 , the processor 110 sets the first source domain 210 and the first target domain 220 corresponding to the first source domain 210 to the training data generation model 10 as a set 200 . By inputting, the training data set 300 including the first source domain 210 and the second target domain 310 in a pair form may be obtained. Specifically, the training data generation model 10 generates the second target domain 310 using the first source domain 210 and the first target domain 220 corresponding to the first source domain 210, The training data set 300 including the first source domain 210 and the second target domain 310 in the form of a pair may be generated.

Here, the first source domain 210 may include a third table 211 in which at least one of a horizontal boundary line and a vertical boundary line does not exist and the third content is included in each cell. In addition, the first target domain 220 may include a fourth table 221 in which horizontal and vertical boundaries exist and each cell is empty. Also, the second target domain 310 may include a table 311 in which third content included in each cell of the third table 211 is inserted into each cell of the fourth table 221 . .

As in some embodiments described above in FIG. 5 , the processor 110 inputs a source domain in which content exists in the table and a target domain in which content does not exist in the table into the learning data generation model 10 so that the content is in the table. An existing new target domain may be acquired, and a new training data set in which the new target domain and the source domain are paired may be acquired. Accordingly, the processor 110 may obtain various training data sets by using the training data generation model 10 .

Meanwhile, according to some embodiments of the present disclosure, the processor 110 inputs a source domain and a target domain to the learning data generation model 10 , and a plurality of different source domains and a plurality of targets corresponding to each of the plurality of source domains By acquiring a domain, a training data set including in the form of a pair may be acquired. Specifically, the training data generation model 10 may generate a plurality of different source domains and a plurality of target domains corresponding to each of the plurality of source domains to generate a training data set including a pair form. Here, each of the plurality of source domains may include a table in which at least one of a horizontal boundary line and a vertical boundary line does not exist. In addition, each of the plurality of target domains may include a table in which a horizontal boundary line and a vertical boundary line exist.

Specifically, the plurality of source domains may have different properties. In addition, the plurality of target domains may have properties corresponding to the respective properties of the plurality of source domains. Here, the attribute may include at least one of a first attribute related to content included in each cell of the table and a second attribute related to the table. Specifically, the first attribute may include at least one of a size of the content, a color of the content, and a shape of the content. In addition, the second attribute may include at least one of a background color of the table, a thickness of a horizontal boundary line, a thickness of a vertical boundary line, a color of a horizontal boundary line, or a color of a vertical boundary line.

For example, referring to FIG. 6 , the processor 110 includes a source domain 410 and a source domain 410 including a table 411 in which a horizontal boundary line does not exist in each cell in the training data generation model 10 . ) and a target domain 420 including a table 421 in which a horizontal boundary line and a vertical boundary line exist in each cell corresponding to the input. The training data generation model 10 may generate the training data set 400 including the input source domain 410 and the target domain 420 . And, the training data generation model 10 is training data including the source domain 410 and the target domain 420 and the second attribute different from the source domain 510 and the target domain 520, that is, the background color of the table is different. A set 500 may be created.

As in some embodiments described above with reference to FIG. 6 , the processor 110 inputs one source domain and a target domain corresponding to the source domain to the training data generation model 10 to provide a plurality of different source domains and a plurality of different source domains. A target domain may be acquired, and a new training data set may be acquired using a plurality of source domains and a plurality of target domains. Accordingly, the processor 110 may acquire learning data having different attributes by using the learning data generation model 10 .

As in some embodiments described above with reference to FIGS. 5 and 6 , the processor 110 may generate a training data set using the training data generation model 10 . Here, the training data generation model 10 may generate a plurality of source domains based on a combination of an arbitrary vector and a source domain, and may generate a plurality of target domains based on a combination of an arbitrary vector and a target domain. Accordingly, the processor 110 may obtain various training data sets in which the source domain and the target domain are paired by using the training data generation model 10 .

According to some other embodiments of the present disclosure, the processor 110 may obtain a source domain in which other content exists in the table by inputting a source domain in which content exists in the table to the training data generation model 10 . Accordingly, the processor 110 may obtain a table in which various contents exist in one table form using the learning data generation model 10 .

Meanwhile, referring back to FIG. 3 , the processor 110 may train a table boundary generation model using the training data set ( S120 ).

Here, the processor 110 may train the table boundary line generation model to generate a target domain corresponding to the source domain by determining the horizontal boundary line and the vertical boundary line based on the first content included in each cell of the first table. Specifically, the processor 110 generates a table boundary line generation model based on the size of the first content included in each cell of the first table to wrap around the first content, including a table in which horizontal and vertical borders exist. It can be trained to create a target domain.

Here, the table boundary generation model may be a deep learning-based neural network model such as pix2pix or cycleGAN that converts an input image into another image. However, the present invention is not limited thereto.

According to some embodiments of the present disclosure, the table boundary generation model is a pix2pix-type neural network model that is learned using a conditional GAN (GAN) consisting of two neural networks, a generative model and a discriminative model. can be

Here, the generative model may aim to generate a fake sample with a level very similar to the target domain of the training data set in order to fool the discriminant model. Specifically, the generative model may generate, as a fake sample, a table having horizontal and vertical boundaries similar to a table included in the target domain. Here, the generative model can generate spurious samples based on any combination of vectors and source domains. Here, the arbitrary vector may be a random noise vector. However, the present invention is not limited thereto.

In addition, the discriminative model may aim to discriminate between the target domain of the training data set and the fake samples generated by the generative model. Specifically, the discrimination model can distinguish by outputting 1 when the input data is a target domain and outputting 0 when the input data is a fake sample.

Accordingly, the processor 110 may use the training data set to increase the discrimination ability of the discriminative model of the table boundary generation model, and train the discriminative model and the generative model together so that the generative model deceives the discrimination model. Through this learning, ultimately, the generative model can generate a fake sample at a level where it is impossible to distinguish the real from the fake, and the discrimination model can improve the discrimination ability.

On the other hand, the processor 110 uses the table boundary line generation model for which the learning is completed, input data including a table in which at least one of a horizontal boundary line and a vertical boundary line does not exist. Results including a table in which a horizontal boundary line and a vertical boundary line exist. It can be converted to data and output.

Referring to FIG. 7 , the processor 110 inputs the input data 30 including the table 31 in which the horizontal boundary of some cells does not exist to the table boundary generation model 20 on which the learning is completed, and the input data 30 ), it is possible to obtain result data 40 including a table 41 in which horizontal and vertical boundaries of all cells corresponding to the table 31 included in the table 31 exist. Specifically, when the processor 110 inputs the input data 30 to the table boundary generation model 20 on which the learning is completed, the result data 40 may be output through the generation model of the table boundary generation model 20 . .

As in some embodiments described above in FIG. 7 , the processor 110 inputs input data including a table in which some of the boundaries do not exist into the table boundary generation model 20 in which learning is completed, and displays a table in which all boundary lines exist. It can be obtained by converting it into result data that contains it. Accordingly, the processor 110 may obtain result data including a table in which all boundary lines exist by using the learned table boundary line generation model 20 .

Meanwhile, in the table included in the input data, the second content may be included in each cell. In addition, the second content may be included in each cell of the result data table corresponding to each cell of the input data table. Here, the second content may include at least one of letters, numbers, and pictures. However, the present invention is not limited thereto.

Referring to FIG. 8 , the processor 110 generates input data 50 including a table 51 including a second content without horizontal boundaries of some cells in the table boundary generation model 20 on which training has been completed. can be input to obtain result data 60 including the second content and a table 61 in which horizontal and vertical boundaries of all cells exist.

As in some embodiments described above in FIG. 8 , the processor 110 inputs input data including a table including a table in which some of the boundaries do not exist, into the table boundary generation model 20 on which learning is completed, and all boundary lines It can be obtained by converting it into result data including a table in which content exists so as to correspond to a table of input data. Accordingly, the processor 110 may obtain result data including all boundaries and contents by using the learning-completed table boundary generation model 20 .

According to some embodiments of the present disclosure, the processor 110 may analyze the structure of a table included in the result data by inputting the obtained result data into the TSR model. Specifically, the TSR model may recognize the structure of a table included in the input result data and output it in a machine readable format (eg, html, spreadsheet, etc.). That is, the processor 110 may obtain a machine-readable format by inputting the obtained result data into the TSR model.

It will also be apparent to those skilled in the art that the steps shown in FIG. 3 are exemplary steps, and some of the steps of FIG. 3 may be omitted or additional steps may be present without departing from the scope of the present disclosure.

9 is a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

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

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will appreciate that the methods of the present disclosure can be applied to single-processor or multiprocessor computer systems, minicomputers, mainframe computers as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like. It will be appreciated that each of these may be implemented in other computer system configurations, including those capable of operating in connection with one or more associated devices.

The described embodiments of the present disclosure may 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. Any medium accessible by a computer can be a computer readable medium, and such computer readable media includes volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. including 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 includes volatile and non-volatile media, temporary and non-transitory media, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. includes media. A computer-readable storage medium may be RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device, or other magnetic storage device. device, or any other medium that can be accessed by a computer and used to store the desired information.

Computer readable transmission media typically embodies computer readable instructions, data structures, program modules or other data, etc. in a modulated data signal such as a carrier wave or other transport mechanism, and Includes any information delivery medium. The term modulated data signal means a signal in which one or more of the characteristics of the signal is set or changed so as to encode information in 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 exemplary environment 1100 implementing various aspects of the disclosure is shown including a computer 1102 , the computer 1102 including a processing unit 1104 , a system memory 1106 , and a system bus 1108 . do. A system bus 1108 couples system components, including but not limited to system memory 1106 , to the processing device 1104 . The processing device 1104 may be any of a variety of commercially available processors. Dual processor and other multiprocessor architectures may also be used as processing unit 1104 .

The system bus 1108 may be any of several types of bus structures that may be further interconnected to a memory bus, a peripheral bus, and a 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 . A basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, EEPROM, etc., which BIOS is the basic input/output system (BIOS) that helps transfer information between components within computer 1102, such as during startup. contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

The computer 1102 may also be configured with an internal hard disk drive (HDD) 1114 (eg, EIDE, SATA) - this internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes-, magnetic floppy disk drive (FDD) 1116 (eg, for reading from or writing to removable diskette 1118), and optical disk drive 1120 (eg, CD-ROM) for reading from, or writing to, disk 1122, or other high capacity optical media such as DVD. The hard disk drive 1114 , the magnetic disk drive 1116 , and the optical disk drive 1120 are connected to the system bus 1108 by the hard disk drive interface 1124 , the magnetic disk drive interface 1126 , and the 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, drives and media correspond to storing any data in a suitable digital format. Although the description of computer readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will use zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other tangible computer-readable media such as etc. may also be used in the exemplary operating environment and any such media may include computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in the drive 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 in various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1102 via one or more wired/wireless input devices, for example, a pointing device such as a keyboard 1138 and a mouse 1140 . Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. Although these and other input devices are often connected to the processing unit 1104 through an input device interface 1142 that is connected to the system bus 1108, parallel ports, IEEE 1394 serial ports, game ports, USB ports, IR interfaces, It may be connected by other interfaces, etc.

A monitor 1144 or other type of display device is also coupled to the system bus 1108 via an interface, such as a video adapter 1146 . In addition to the monitor 1144, the computer typically includes other peripheral output devices (not shown), such as speakers, printers, and the like.

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 workstations, computing device computers, routers, personal computers, portable computers, microprocessor-based entertainment devices, peer devices, or other common network nodes, and are typically connected to computer 1102 . Although it includes many or all of the components described for it, only memory storage device 1150 is shown for simplicity. The logical connections shown include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, eg, a wide area network (WAN) 1154 . Such 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, for example, the Internet.

When used in a LAN networking environment, the computer 1102 is connected to the local network 1152 through a wired and/or wireless communication network interface or adapter 1156 . Adapter 1156 may facilitate wired or wireless communication to LAN 1152 , which also includes a wireless access point installed therein for communicating with wireless adapter 1156 . When used in a WAN networking environment, the computer 1102 may include a modem 1158, be connected to a communication computing device on the WAN 1154, or establish communications over the WAN 1154, such as over the Internet. have other means. A modem 1158 , which may be internal or external and a wired or wireless device, is coupled to the system bus 1108 via a 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 other means of establishing a communication link between the computers may be used.

Computer 1102 may be associated with any wireless device or object that is deployed and operates in wireless communication, for example, printers, scanners, desktop and/or portable computers, portable data assistants (PDAs), communication satellites, wireless detectable tags. It operates to communicate with any device or place, and phone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network or may simply be an ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) makes it possible to connect to the Internet, etc. without a wire. Wi-Fi is a wireless technology such as cell phones that allows these devices, eg, computers, to transmit and receive data indoors and outdoors, ie anywhere within range of a base station. Wi-Fi networks use a radio 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, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks may operate in unlicensed 2.4 and 5 GHz radio bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band). .

One of ordinary skill in the art of this disclosure will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, instructions, information, signals, bits, symbols, and chips that may be referenced in the above description are voltages, currents, electromagnetic waves, magnetic fields or particles, optical field particles or particles, or any combination thereof.

A person of ordinary skill in the art of the present disclosure will recognize that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein include electronic hardware, (convenience For this purpose, 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 interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. A person skilled in the art of the present disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be interpreted as a departure from the scope of the present disclosure.

The various embodiments presented herein may be implemented as methods, apparatus, or articles 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 (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash drives. memory devices (eg, EEPROMs, cards, sticks, key drives, etc.). Also, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. Based on design priorities, it is to be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure. The appended method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific 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 readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited to the embodiments presented herein, but is to be construed in the widest scope consistent with the principles and novel features presented herein.

Claims (14)

An image-based table boundary generation method performed by a computing device comprising at least one processor, the method comprising:
generating a training data set including a source domain and a target domain used for training the table boundary generation model in a pair form by using the pre-trained training data generation model; and
training the table boundary line generation model by using the training data set;
including,
The source domain is
Including a first table (table) in which at least one of a horizontal boundary line and a vertical boundary line does not exist,
The target domain is
Containing a second table in which a horizontal boundary line and a vertical boundary line exist,
How to create image-based table borders.
The method of claim 1,
The table boundary line generation model is,
Learning to generate the target domain corresponding to the source domain by determining a horizontal boundary line and a vertical boundary line based on the first content included in each cell of the first table,
How to create image-based table borders.
3. The method of claim 2,
The target domain is
including the first content in each cell of the second table corresponding to the respective cell of the first table;
How to create image-based table borders.
3. The method of claim 2,
The first content is
containing at least one of letters, numbers and pictures;
How to create image-based table borders.
The method of claim 1,
By using the table boundary line generation model that has been trained, input data including a table in which at least one of a horizontal boundary line and a vertical boundary line does not exist is converted into result data including a table in which a horizontal boundary line and a vertical boundary line exist. step;
further comprising,
How to create image-based table borders.
6. The method of claim 5,
The second content included in each cell of the table included in the input data is,
included in each cell of the table of result data corresponding to each cell of the table of input data;
How to create image-based table borders.
7. The method of claim 6,
The second content is
containing at least one of letters, numbers and pictures;
How to create image-based table borders.
The method of claim 1,
The training data generation model is
A plurality of different source domains and a plurality of target domains corresponding to each of the plurality of source domains are generated to generate a training data set including in a pair form,
Each of the plurality of source domains,
Includes a table in which at least one of a horizontal boundary line and a vertical boundary line does not exist,
Each of the plurality of target domains,
Containing a table in which horizontal and vertical borders exist,
How to create image-based table borders.
9. The method of claim 8,
The plurality of source domains,
properties are different,
The plurality of target domains,
having a corresponding attribute and a corresponding attribute of each of the plurality of source domains;
The property is
at least one of a first property related to content contained in each cell of the table or a second property related to the table,
How to create image-based table borders.
10. The method of claim 9,
The first attribute is
including at least one of the size of the content, the color of the content, or the shape of the content,
The second attribute is
At least one of the background color of the table, the thickness of the horizontal boundary, the thickness of the vertical boundary, the color of the horizontal boundary, or the color of the vertical boundary,
How to create image-based table borders.
The method of claim 1,
The source domain is
It is an image including the first table or data composed of a program language expressing the first table,
The target domain is
An image including the second table or data composed of a program language expressing the second table,
How to create image-based table borders.
The method of claim 1,
The training data generation model is
A second target domain is generated using a first source domain and a first target domain corresponding to the first source domain, and a training data set including the first source domain and the second target domain in a pair form is generated. do,
The first source domain,
At least one of a horizontal boundary line and a vertical boundary line does not exist and includes a third table including third content in each cell,
The first target domain,
a fourth table in which horizontal and vertical borders exist and each cell is empty;
The second target domain,
including a table in which the third content included in each cell of the third table is inserted in each cell of the fourth table;
How to create image-based table borders.
A computer program stored on a computer-readable storage medium, comprising:
The computer program includes instructions for causing a processor of a computing device to perform the following steps for generating a boundary line of an image-based table, the steps comprising:
generating a training data set including a source domain and a target domain used for training the table boundary generation model in a pair form by using the pre-trained training data generation model; and
training the table boundary line generation model by using the training data set;
including,
The source domain is
Including a first table (table) in which at least one of a horizontal boundary line and a vertical boundary line does not exist,
The target domain is
Containing a second table in which a horizontal boundary line and a vertical boundary line exist,
A computer program stored on a computer-readable storage medium.
A computing device for generating a boundary of an image-based table, comprising:
a processor including at least one core; and
a memory storing a computer program executable by the processor;
including,
The processor is
By using the pre-trained training data generation model, a training data set including a source domain and a target domain used for training the table boundary generation model in a pair form is generated, and
using the training data set to train the table boundary generation model,
The source domain is
Including a first table (table) in which at least one of a horizontal boundary line and a vertical boundary line does not exist,
The target domain is
Containing a second table in which a horizontal boundary line and a vertical boundary line exist,
computing device.

Images