KR102598072B1 - Apparatus and method for providing service for preventing personal information exposure based on artificial intelligence algorithm - Google Patents

Abstract

A method and device for providing a service that prevents personal information exposure based on an AI algorithm are disclosed. According to an embodiment of the present disclosure, a method of providing a service for preventing personal information exposure based on an AI algorithm performed by a device is based on transmission of first content from a terminal device used by a user, 1 extracting at least one of first text data or first voice data included in content; At least one of the first text data and the second text data corresponding to the first voice data is input into a pre-trained first AI model, and one or more personal information included in the first text data or the second text data Obtaining information related to; De-identifying the one or more personal information in at least one of the first text data or the first voice data included in the first content and then uploading the first content; transmitting a first message notifying the one or more pieces of personal information de-identified in the first content to a terminal device used by the user; And based on receiving a second message requesting de-identification of the first type of personal information from the terminal device used by the user, the first type of personal information among the one or more personal information on the first content It may include the step of performing de-identification.

Description

Device and method for providing services that prevent personal information exposure based on artificial intelligence algorithms {APPARATUS AND METHOD FOR PROVIDING SERVICE FOR PREVENTING PERSONAL INFORMATION EXPOSURE BASED ON ARTIFICIAL INTELLIGENCE ALGORITHM}

This disclosure relates to the field of preventing personal information exposure, and more specifically, to a device and method for providing a service for preventing personal information exposure based on an artificial intelligence algorithm.

Personal information refers to unique information about an individual that allows the individual to be identified. For example, personal information can be divided into resident registration number, mobile phone number, credit card number, IP, ID, password, passport number, driver's license number, etc. Personal information is not only important in that it can identify individuals, but is also valuable information that is essential for corporate activities.

Recently, the severity of personal information leaks has been increasing, and cases of misuse of exposed personal information are also rapidly increasing. As the scale of services and related industries utilizing personal information grows exponentially, the need to prevent personal information leaks is gradually emerging.

Registered Patent Publication No. 10-1021305, 2011.03.03

This disclosure was created to solve the above-mentioned problems, and the purpose of this disclosure is to provide a device and method for providing a service that prevents personal information exposure based on an artificial intelligence algorithm.

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

According to an embodiment of the present disclosure, a method of providing a service for preventing personal information exposure based on an artificial intelligence (AI) algorithm performed by a device includes first content being transmitted from a terminal device used by a user. extracting at least one of first text data or first voice data included in the first content based on the transmission; At least one of the first text data and the second text data corresponding to the first voice data is input into a pre-trained first AI model, and one or more personal information included in the first text data or the second text data Obtaining information related to; De-identifying the one or more personal information in at least one of the first text data or the first voice data included in the first content and then uploading the first content; transmitting a first message notifying the one or more pieces of personal information de-identified in the first content to a terminal device used by the user; And based on receiving a second message requesting de-identification of the first type of personal information from the terminal device used by the user, the first type of personal information among the one or more personal information on the first content It may include the step of performing de-identification.

Additionally, the method may further include obtaining the second text data by applying a speech-to-text (STT) algorithm to the first voice data extracted from the first content.

And, based on the plurality of image frames constituting the first content being input to a pre-trained second AI model, the second AI model: identifies a plurality of texts displayed in each of the plurality of image frames, Among the plurality of texts, the remaining texts excluding overlapping texts may be output as the first text data.

And, the second AI model may include at least one of one or more convolutional layers, one or more long short term memory (LSTM) layers, and a softmax layer.

Additionally, the method includes extracting third text data and second voice data included in the second content based on the second content being received from the terminal device used by the user; At least one of the third text data and the fourth text data corresponding to the second voice data is input into the first AI model to relate to one or more personal information included in the third text data or the fourth text data. Obtaining information; And uploading the second content after de-identifying the remaining personal information excluding the first type of personal information from at least one of the third text data or the second voice data included in the second content. More may be included.

And, the method is based on receiving a third message that a specific word included in at least one of the first text data or the first voice data is a second type of personal information from the terminal device used by the user, De-identifying the specific word on first content; And it may further include the step of additionally learning the first AI model based on the third message.

In another embodiment of the present disclosure, an apparatus that provides a service for preventing personal information exposure based on an artificial intelligence (AI) algorithm includes at least one memory; and at least one processor, wherein the at least one processor selects at least one of first text data or first voice data included in the first content based on the first content being transmitted from the terminal device used by the user. extract; At least one of the first text data and the second text data corresponding to the first voice data is input into a pre-trained first AI model, and one or more personal information included in the first text data or the second text data Obtain information related to; De-identifying the one or more personal information in at least one of the first text data or the first voice data included in the first content and then uploading the first content; transmitting a first message informing the terminal device used by the user of the one or more pieces of de-identified personal information in the first content; And based on receiving a second message requesting de-identification of the first type of personal information from the terminal device used by the user, the first type of personal information among the one or more personal information on the first content It may include a personal information filtering module that performs de-identification.

And, the personal information filtering module may obtain the second text data by applying a speech-to-text (STT) algorithm to the first voice data extracted from the first content.

And, the personal information filtering module extracts third text data and second voice data included in the second content based on the second content being received from the terminal device used by the user; At least one of the third text data and the fourth text data corresponding to the second voice data is input into the first AI model to relate to one or more personal information included in the third text data or the fourth text data. obtain information; And the second content can be uploaded after de-identifying the remaining personal information excluding the first type of personal information from at least one of the third text data or the second voice data included in the second content. .

And, the personal information filtering module is based on receiving a third message that a specific word included in at least one of the first text data or the first voice data is a second type of personal information from the terminal device used by the user. Thus, the specific word may be de-identified on the first content, and the AI model learning module included in the at least one processor may further train the first AI model based on the third message.

In addition to this, a computer program stored in a computer-readable recording medium for execution to implement the present disclosure may be further provided.

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

According to various embodiments of the present disclosure, an apparatus and method for providing a service for preventing personal information exposure based on an artificial intelligence algorithm can be provided.

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

1 is a diagram briefly illustrating a system for preventing personal information exposure based on an artificial intelligence algorithm according to an embodiment of the present disclosure.
Figure 2 is a block diagram showing the configuration of a device for preventing personal information exposure based on an artificial intelligence algorithm, according to an embodiment of the present disclosure.
Figure 3 is a diagram illustrating the structure of a second AI model, according to an embodiment of the present disclosure.
FIG. 4 is a flowchart illustrating a method of preventing personal information exposure based on an artificial intelligence algorithm according to an embodiment of the present disclosure.

Like reference numerals refer to like elements throughout this disclosure. The present disclosure does not describe all elements of the embodiments, and general content or overlapping content between the embodiments in the technical field to which the present disclosure pertains is omitted. The term 'unit, module, member, block' used in the specification may be implemented as software or hardware, and depending on the embodiment, a plurality of 'unit, module, member, block' may be implemented as a single component, or It is also possible for one 'part, module, member, or block' to include multiple components.

Throughout the specification, when a part is said to be “connected” to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection through a wireless communication network. do.

Additionally, when a part "includes" a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary.

Throughout the specification, when a member is said to be located “on” another member, this includes not only cases where a member is in contact with another member, but also cases where another member exists between the two members.

Terms such as first and second are used to distinguish one component from another component, and the components are not limited by the above-mentioned terms.

Singular expressions include plural expressions unless the context clearly makes an exception.

The identification code for each step is used for convenience of explanation. The identification code does not explain the order of each step, and each step may be performed differently from the specified order unless a specific order is clearly stated in the context. there is.

Hereinafter, the operating principle and embodiments of the present disclosure will be described with reference to the attached drawings.

In this specification, 'device according to the present disclosure' includes all various devices that can perform computational processing and provide results to the user. For example, the device according to the present disclosure may include all of a computer, a server device, and a portable terminal, or may take the form of any one.

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

Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may consist of one or multiple processors. At this time, one or more processors may be a general-purpose processor such as a CPU, AP, or DSP (Digital Signal Processor), a graphics-specific processor such as a GPU or VPU (Vision Processing Unit), or an artificial intelligence-specific processor such as an NPU. One or more processors control input data to be processed according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, when one or more processors are dedicated artificial intelligence processors, the artificial intelligence dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

Predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is learned using a large number of learning data by a learning algorithm, thereby creating a predefined operation rule or artificial intelligence model set to perform the desired characteristics (or purpose). It means burden. This learning may be performed on the device itself that performs the artificial intelligence according to the present disclosure, or may be performed through a separate server and/or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

An artificial intelligence model may be composed of multiple neural network layers. Each of the plurality of neural network layers has a plurality of weight values, and neural network calculation is performed through calculation between the calculation result of the previous layer and the plurality of weights. Multiple weights of multiple neural network layers can be optimized by the learning results of the artificial intelligence model. For example, a plurality of weights may be updated so that loss or cost values obtained from the artificial intelligence model are reduced or minimized during the learning process. Artificial neural networks may include deep neural networks (DNN), for example, Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), or Deep Q-Networks, etc., but are not limited to the examples described above.

According to an exemplary embodiment of the present disclosure, a processor may implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that allows machines to learn by imitating human biological neurons. Methodology of artificial intelligence includes supervised learning, in which the answer (output data) to the problem (input data) is determined by providing input data and output data together as training data according to the learning method, and only input data is provided without output data. In unsupervised learning, in which the solution (output data) to the problem (input data) is not determined, and a reward is given from the external environment whenever an action is taken in the current state, , It can be divided into reinforcement learning, which conducts learning in the direction of maximizing these rewards. In addition, artificial intelligence methodologies can be divided according to the architecture, which is the structure of the learning model. The architecture of widely used deep learning technology is convolutional neural network (CNN) and recurrent neural network (RNN). , Transformer, generative adversarial networks (GAN), etc.

The devices and systems may include artificial intelligence models. An artificial intelligence model may be a single artificial intelligence model or may be implemented as multiple artificial intelligence models. Artificial intelligence models may be composed of neural networks (or artificial neural networks) and may include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network can refer to an overall model in which artificial neurons (nodes), which form a network through the combination of synapses, change the strength of the synapse connection through learning and have problem-solving capabilities. Neurons in a neural network can contain combinations of weights or biases. A neural network may include one or more layers consisting of one or more neurons or nodes. By way of example, a device may include an input layer, a hidden layer, and an output layer. The neural network that makes up the device can infer the result (output) to be predicted from arbitrary input (input) by changing the weight of neurons through learning.

The processor creates a neural network, trains or learns a neural network, performs calculations based on received input data, generates an information signal based on the results, or generates a neural network. You can retrain the network. Neural network models include CNN (Convolution Neural Network), R-CNN (Region with Convolution Neural Network), RPN (Region Proposal Network), RNN such as GoogleNet, AlexNet, VGG Network, etc. (Recurrent Neural Network), S-DNN (Stacking-based deep Neural Network), S-SDNN (State-Space Dynamic Neural Network), Deconvolution Network, DBN (Deep Belief Network), RBM (Restrcted Boltzman Machine), Fully Convolutional Network , LSTM (Long Short-Term Memory) Network, Classification Network, etc., but are not limited to various types of models. The processor may include one or more processors to perform operations according to models of the neural network. For example, a neural network may include a deep neural network.

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

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

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

1 is a diagram briefly illustrating a system for preventing personal information exposure based on an artificial intelligence algorithm according to an embodiment of the present disclosure.

As shown in FIG. 1, the system 1000 for preventing personal information exposure based on an artificial intelligence algorithm includes a device 100, terminal devices 200-1, 200-2, ... used by a plurality of users. It may include 200-N) (N is a natural number of 2 or more) and a data server 300.

In FIG. 1, the device 100 is implemented as a desktop, and the terminal devices 200-1, 200-2, ... 200-N used by multiple users are implemented as smartphones. is disclosed, but is not limited thereto.

As an example, the device 100 and the terminal devices 200-1, 200-2, ... 200-N used by a plurality of users are various types of electronic devices (e.g., laptops, desktops, laptops, tablets). It can be implemented as a PC, slate PC device, server device, etc.), and can also be implemented as a group of devices where one or more types of devices are connected.

The device 100 included in the system 1000 and the terminal devices 200-1, 200-2, ... 200-N used by a plurality of users can communicate through the network (W).

Here, the network W may include a wired network and a wireless network. For example, the network may include various networks such as a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN).

Additionally, the network W may include the known World Wide Web (WWW). However, the network (W) according to an embodiment of the present disclosure is not limited to the networks listed above, and may include at least some of a known wireless data network, a known telephone network, and a known wired and wireless television network.

The device 100 may perform an operation to prevent personal information exposure based on an artificial intelligence algorithm. Additionally, the device 100 may create/execute web-based and/or application-based software that can perform a service that prevents personal information exposure based on an artificial intelligence algorithm.

Terminal devices 200-1, 200-2, ... 200-N used by a plurality of users may execute web-based and/or application-based software created by the device 100. Therefore, in the present disclosure, a method of preventing personal information exposure based on an artificial intelligence algorithm executed by the device 100 is used by terminal devices 200-1, 200-2, ... 200-N used by a plurality of users. You can also run it.

The device 100 may identify one or more personal information included in content input from the user. For example, the device 100 may obtain text data corresponding to text data and/or voice data on a plurality of frames constituting content. The device 100 may identify personal information on the acquired text data based on an artificial intelligence algorithm, filter/de-identify the identified personal information, and then upload content.

Operations related to this will be described in detail with reference to FIGS. 2 to 4.

Figure 2 is a block diagram showing the configuration of a device for preventing personal information exposure based on an artificial intelligence algorithm, according to an embodiment of the present disclosure.

As shown in FIG. 2 , device 100 may include memory 110, communication module 120, display 130, and processor 140.

The memory 110 may store one or more instructions for the processor 140 to perform various operations. The memory 110 can store data supporting various functions of the device 100 and a program for the operation of the processor 140, and can store input/output data (e.g., content input from the user, content (text data included, etc.) can be saved.

The memory 110 is a flash memory type, hard disk type, solid state disk type, SDD type (Silicon Disk Drive type), and multimedia card micro type. ), card-type memory (e.g. SD or XD memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), EEPROM (electrically erasable programmable read) -only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk may include at least one type of storage medium.

The communication module 120 may include one or more components including circuits that enable communication with external devices (eg, data servers and/or terminal devices used by users, etc.). For example, the communication module 120 may include at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module. The communication module 120 may receive monitoring data from an external device.

The display 130 displays (outputs) information processed by the device 100 (for example, personal information on text data included in content, etc.).

For example, the display may display execution screen information of an application running on the device 100, or UI (User Interface) and GUI (Graphic User Interface) information according to the execution screen information.

The processor 140 may provide a service to prevent personal information exposure based on an artificial intelligence algorithm by executing one or more instructions stored in the memory 110. That is, the processor 140 can control overall operations and functions using each component of the device 100. At this time, the memory 110 and the processor 140 may each be implemented as separate chips. Alternatively, the memory 110 and processor 140 may be implemented as a single chip.

The processor 140 may include an AI model learning module 140-1 and a personal information filtering module 140-2. The AI model learning module 140-1 and the personal information filtering module 140-2 may be controlled and managed by the processor 140.

The AI model learning module 140-1 can train a first AI model and a second AI model.

Specifically, the AI model learning module 140-1 may train the first AI model to output information related to one or more personal information included in the input text data.

Here, the information related to one or more personal information may include the type and importance level of each one or more personal information. The importance level of personal information can be set in advance for each type of personal information. If the type of specific personal information is sensitive data such as a resident registration number, the importance level of the type of specific personal information may be set high.

As an example, the AI model learning module 140-1 may learn a first AI model based on training data consisting of corpus data and data labeling personal information included in the corpus data. You can.

The AI model learning module 140-1 may train a second AI model to extract text data included in the input content. The second AI model may be trained to identify a plurality of texts displayed in each of a plurality of image frames constituting the content and output the remaining texts excluding overlapping texts among the identified plurality of texts.

As an example, the second AI model may be configured as shown in FIG. 3. The second AI model may include at least one of one or more convolutional layers, one or more long short term memory (LSTM) layers, and a softmax layer.

Feature data may be extracted from a plurality of image frames constituting content as they are input to one or more convolutional layers. Feature data is input to one or more LSTM layers, and the text included in each of a plurality of image frames is extracted/identified, and the remaining text excluding the duplicate text among the extracted/identified texts can be output through a soft max layer.

The personal information filtering module 140-2 can filter/de-identify personal information included in content using an AI model learned through the AI model learning module 140-1.

The personal information filtering module 140-2 may input text data included in content input from the user into the first AI model to obtain information related to one or more personal information included in the text data.

Specifically, the personal information filtering module 140-2 may input content (i.e., a plurality of image frames constituting the content) into the second AI model and extract text data included in the content. Additionally, the personal information filtering module 140-2 may input the extracted text data into the first AI model to obtain information related to personal information included in the text data.

Additionally or alternatively, the personal information filtering module 140-2 extracts voice data included in the content and applies a speech-to-text (STT) algorithm to the extracted voice data to provide text corresponding to the voice data. Data can be obtained. Additionally, the personal information filtering module 140-2 may input text data corresponding to voice data into the first AI model to obtain information related to personal information included in the text data.

The personal information filtering module 140-2 may upload the content after de-identifying one or more personal information included in the content. That is, when content is input from a user, the personal information filtering module 140-2 may de-identify personal information included in the content and then upload the content.

The personal information filtering module 140-2 may transmit a message informing the user of the filtered/de-identified personal information on the content to the terminal device used by the user. In order to prevent cases where personal information (e.g., phone number, etc.) intentionally exposed by a user is de-identified, the personal information filtering module 140-2 filters/de-identifies content on the terminal device used by the user. A message may be sent containing personal information.

Based on receiving a second message requesting de-identification of a specific type of personal information from the terminal device used by the user, the personal information filtering module 140-2 determines the specific type of personal information among one or more pieces of personal information in the content. De-identification can be performed on .

When other content is later transmitted from the user, the personal information filtering module 140-2 may not de-identify specific types of personal information included in the other content.

And, based on receiving a message from the terminal device used by the user that a specific word included in the text included in the content is personal information, the personal information filtering module 140-2 may de-identify the specific word in the content. Additionally, the AI model learning module 140-1 may further train the first AI model so that the first AI model can identify a specific word as personal information.

FIG. 4 is a flowchart illustrating a method of preventing personal information exposure based on an artificial intelligence algorithm according to an embodiment of the present disclosure.

The device may extract at least one of first text data or first voice data included in the first content based on the first content being transmitted from the terminal device used by the user (S410).

Specifically, the device may obtain first text data included in the first content by inputting the first content (that is, a plurality of image frames constituting the first content) into the second AI model.

Additionally or alternatively, the device may extract first voice data from the first content and obtain second text data by applying an STT algorithm to the extracted first voice data.

The device inputs at least one of the first text data and the second text data corresponding to the first voice data into the pre-trained first AI model to relate to one or more personal information included in the first text data or the second text data. Information can be obtained (S420).

The device may upload the first content after de-identifying one or more personal information in at least one of the first text data or the first voice data included in the first content (S430).

Specifically, the device may blur and/or mosaic an area where at least one piece of personal information is displayed on a plurality of image frames on the first content. As another example, the device may transform at least one piece of personal information displayed on a plurality of image frames on the first content into predefined characters.

Additionally or alternatively, the device may insert a predefined voice at the time the voice containing personal information is output when the first content is played. Alternatively, the device may modulate the voice containing personal information at the time the voice is output when the first content is played.

The device may upload first content containing one or more de-identified personal information in the manner described above.

The device may transmit a first message notifying one or more filtered/de-identified personal information on the first content to the terminal device used by the user (S440).

That is, the device can inform the user that exposure of the user's personal information has been prevented by de-identifying all personal information and then uploading the first content. Additionally, the device may inquire whether personal information has been de-identified differently than the user intended (i.e., unnecessarily).

Based on receiving a second message requesting de-identification of the first type of personal information from the terminal device used by the user, the device de-identifies the first type of personal information among one or more pieces of personal information on the first content. Disarming can be performed (S450).

Thereafter, the device may de-identify the first type of personal information in the content received from the user.

Specifically, based on the second content being received from the terminal device used by the user, the device may extract third text data and second voice data included in the second content. The device inputs at least one of the third text data and the fourth text data corresponding to the second voice data into the first AI model to obtain information related to one or more personal information included in the third text data or the fourth text data. can do.

The device may upload the second content after de-identifying the remaining personal information excluding the first type of personal information from at least one of the third text data or the second voice data included in the second content.

As another example of the present disclosure, based on receiving a third message that a specific word included in at least one of the first text data or the first voice data is the second type of personal information from the terminal device used by the user, the device may provide the second type of personal information. 1 Specific words in content can be de-identified. And, the device can additionally learn the first AI model based on the third message.

That is, the device may further train the first AI model so that the first AI model identifies a specific word as the second type of personal information.

Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. Instructions may be stored in the form of program code, and when executed by a processor, may create program modules to perform operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

Computer-readable recording media include all types of recording media storing instructions that can be decoded by a computer. For example, there may be Read Only Memory (ROM), Random Access Memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage device, etc.

As described above, the disclosed embodiments have been described with reference to the attached drawings. A person skilled in the art to which this disclosure pertains will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical idea or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

100: device
110: memory
120: communication module
130: display
140: processor

Claims (12)

In a method of providing a service that prevents personal information exposure based on an artificial intelligence (AI) algorithm performed by a device, the method includes:
Based on the first content being transmitted from the terminal device used by the user, extracting at least one of first text data or first voice data included in the first content;
At least one of the first text data and the second text data corresponding to the first voice data is input into a pre-trained first AI model, and one or more personal information included in the first text data or the second text data Obtaining information related to;
De-identifying the one or more personal information in at least one of the first text data or the first voice data included in the first content and then uploading the first content;
transmitting a first message notifying the one or more pieces of personal information de-identified in the first content to a terminal device used by the user; and
Based on receiving a second message requesting de-identification of the first type of personal information from the terminal device used by the user, the first type of personal information among the one or more personal information on the first content Including performing de-identification,
extracting third text data and second voice data included in the second content based on the second content being received from the terminal device used by the user;
At least one of the third text data and the fourth text data corresponding to the second voice data is input into the first AI model to relate to one or more personal information included in the third text data or the fourth text data. Obtaining information; and
A step of de-identifying remaining personal information excluding the first type of personal information from at least one of the third text data or the second voice data included in the second content and then uploading the second content. Including, method.
According to paragraph 1,
The method further comprising obtaining the second text data by applying a speech-to-text (STT) algorithm to the first voice data extracted from the first content.
According to paragraph 1,
Based on the plurality of image frames constituting the first content being input to the pre-trained second AI model, the second AI model is:
Identifying a plurality of texts displayed in each of the plurality of image frames,
A method of outputting the remaining texts excluding overlapping texts among the plurality of texts as the first text data.
According to paragraph 3,
The second AI model is,
A method comprising at least one of one or more convolutional layers, one or more long short term memory (LSTM) layers, and a softmax layer.
delete According to paragraph 1,
Based on receiving a third message from the terminal device used by the user that a specific word included in at least one of the first text data or the first voice data is a second type of personal information, the specific word on the first content de-identifying words; and
The method further comprises additionally learning the first AI model based on the third message.
In a device that provides a service that prevents personal information exposure based on an artificial intelligence (AI) algorithm, the device:
at least one memory; and
Contains at least one processor,
The at least one processor,
Based on the first content being transmitted from the terminal device used by the user, extracting at least one of first text data or first voice data included in the first content;
At least one of the first text data and the second text data corresponding to the first voice data is input into a pre-trained first AI model, and one or more personal information included in the first text data or the second text data Obtain information related to;
De-identifying the one or more personal information in at least one of the first text data or the first voice data included in the first content and then uploading the first content;
transmitting a first message informing the terminal device used by the user of the one or more pieces of de-identified personal information in the first content; and
Based on receiving a second message requesting de-identification of the first type of personal information from the terminal device used by the user, the first type of personal information among the one or more personal information on the first content a personal information filtering module that performs de-identification;
The personal information filtering module is,
extracting third text data and second voice data included in the second content based on the second content being received from the terminal device used by the user;
At least one of the third text data and the fourth text data corresponding to the second voice data is input into the first AI model to relate to one or more personal information included in the third text data or the fourth text data. obtain information; and
A device that uploads the second content after de-identifying remaining personal information excluding the first type of personal information from at least one of the third text data or the second voice data included in the second content.
In clause 7,
The personal information filtering module is,
A device that obtains the second text data by applying a speech-to-text (STT) algorithm to the first voice data extracted from the first content.
In clause 7,
Based on the plurality of image frames constituting the first content being input to the pre-trained second AI model, the second AI model is:
Identifying a plurality of texts displayed in each of the plurality of image frames,
A device that outputs the remaining texts excluding overlapping texts among the plurality of texts as the first text data.
According to clause 9,
The second AI model is,
An apparatus comprising at least one of one or more convolutional layers, one or more long short term memory (LSTM) layers, and a softmax layer.
delete In clause 7,
The personal information filtering module is,
Based on receiving a third message from the terminal device used by the user that a specific word included in at least one of the first text data or the first voice data is a second type of personal information, the specific word on the first content De-identify words,
The AI model learning module included in the at least one processor,
A device for further learning the first AI model based on the third message.