Method for predicting price of cryptocurrency on basis of artificial neural network

Abstract

According to an embodiment of the present disclosure, disclosed is a method for predicting the price of cryptocurrency on the basis of an artificial neural network. The method may comprise the steps of: acquiring monitoring reference information from a user terminal; generating a chart image according to the monitoring reference information; generating a pattern prediction result corresponding to the chart image on the basis of an artificial neural network-based pattern prediction model; and transmitting, to the user terminal, notification information generated on the basis of the pattern prediction result.

Description

Artificial Neural Network-based Cryptocurrency Price Prediction Method

[0001] The present invention relates to a method for predicting cryptocurrency prices, and more specifically, to a method for predicting cryptocurrency prices using an artificial neural network model.

[0002] Cryptocurrency refers to digital assets based on blockchain technology that can be traded without a central authority, and recently, many individual investors are trading them as an investment target.

[0003] However, most individual investors have limited access to information compared to institutions or large investors, so they often fail to quickly grasp market trends. In particular, as the cryptocurrency market is highly volatile and changes in real time, a lack of information acts as a disadvantage for individual investors.

[0004] Traditionally, individual investors primarily used statistical methods such as ARIMA, but this had limitations in that it could not properly reflect real-time changes in the market.

[0005] Therefore, to solve the above problems, there has recently been an increasing demand for cryptocurrency price prediction models based on artificial neural networks.

[0006] Korean Patent Publication No. 10-2650314 discloses "a method, apparatus, and system for predicting the occurrence of arbitrage using an artificial intelligence model trained based on cryptocurrency transaction data."

[0007] The present disclosure is conceived in response to the aforementioned background technology and aims to provide a method for predicting cryptocurrency prices based on an artificial neural network.

[0008] According to one embodiment of the present disclosure for realizing the aforementioned objectives, a method for predicting cryptocurrency prices based on an artificial neural network is disclosed. The method may include the steps of: obtaining monitoring reference information from a user terminal; generating a chart image according to the monitoring reference information; generating a pattern prediction result corresponding to the chart image based on an artificial neural network-based pattern prediction model; and transmitting notification information generated based on the pattern prediction result to the user terminal.

[0009] In one embodiment, the monitoring reference information may include one or more cryptocurrency names, chart periods, or candle cycles.

[0010] In one embodiment, the chart image may be an image generated by a pre-processing method determined according to the monitoring reference information.

[0011] In one embodiment, the pattern prediction model may be a model that generates a pattern prediction result including probability values ​​for rise and fall for the chart image.

[0012] In one embodiment, the pattern prediction model may be a model that generates a pattern prediction result including probability values ​​for each of the following for the chart image: upward continuation, upward reversal, downward continuation, and downward reversal.

[0013] In one embodiment, the pattern prediction model may be trained based on a training dataset generated by an artificial neural network-based pattern labeling model.

[0014] In one embodiment, the pattern labeling model may be a model trained to receive a chart image to be labeled and output at least one specific pattern among at least one upward continuation pattern included in an upward continuation pattern group; at least one upward reversal pattern included in an upward reversal pattern group; at least one downward continuation pattern included in a downward continuation pattern group; and at least one downward reversal pattern included in a downward reversal pattern group.

[0015] In one embodiment, the pattern prediction model may be trained based on a training data set generated based on a price change decision cycle input by a user.

[0016] In one embodiment, the method may further include the steps of: obtaining the price change determination cycle from a user; generating the training data set based on the price change determination cycle; and training the pattern prediction model using the generated training data set.

[0017] In one embodiment, the pattern prediction model may be a model trained using a loss function that calculates a loss value based on a salience map for an input chart image.

[0018] In one embodiment, the loss function may be a function that calculates a loss value by considering the ratio of common areas between the major areas within the input chart image and the major areas within the salience map.

[0019] A computer program stored on a computer-readable storage medium according to an embodiment of the present disclosure for realizing the aforementioned objectives, wherein, when the computer program is executed by one or more processors, the one or more processors may be configured to perform artificial neural network-based cryptocurrency price prediction operations. The operations may include: an operation of obtaining monitoring reference information from a user terminal; an operation of generating a chart image according to the monitoring reference information; an operation of generating a pattern prediction result corresponding to the chart image based on an artificial neural network-based pattern prediction model; and an operation of transmitting notification information generated based on the pattern prediction result to the user terminal.

[0020] A computing device according to one embodiment of the present disclosure for realizing the aforementioned tasks may include at least one processor and memory. The at least one processor may acquire monitoring reference information from a user terminal, generate a chart image according to the monitoring reference information, generate a pattern prediction result corresponding to the chart image based on an artificial neural network-based pattern prediction model, and transmit notification information generated based on the pattern prediction result to the user terminal.

[0021] The present disclosure may provide a method for predicting cryptocurrency prices based on an artificial neural network.

[0022] FIG. 1 is a drawing illustrating a system including a server, a user terminal, and a communication network according to one embodiment of the present disclosure.

[0023] FIG. 2 is a block diagram of a server according to one embodiment of the present disclosure.

[0024] FIG. 3 is a block diagram of a user terminal according to one embodiment of the present disclosure.

[0025] FIG. 4 is a diagram illustrating an exemplary flowchart of an artificial neural network-based cryptocurrency price prediction method according to one embodiment of the present disclosure.

[0026] Figure 5 is a diagram conceptually illustrating an example of converting price data regarding a specific cryptocurrency asset into a chart image based on monitoring reference information.

[0027] FIG. 6 is a schematic diagram showing an artificial neural network model according to one embodiment of the present disclosure.

[0028] FIG. 7 is a diagram illustrating one or more patterns belonging to an upward continuation pattern group, an upward reversal pattern group, a downward continuation pattern group, and a downward reversal pattern group.

[0029] Figure 8 is a conceptual diagram illustrating an example in which different true values ​​are labeled for a chart image according to the length of the price change determination cycle.

[0030] Figure 9 is a conceptual diagram conceptually illustrating the input and output data of a pattern prediction model.

[0031] Figure 10 is a diagram illustrating an exemplary chart image and a salience map.

[0032] Figure 11 is a diagram exemplarily showing a common area between a major area within a chart image and a major area within a salience map.

[0033] FIG. 12 is a block diagram of a computing device according to one embodiment of the present disclosure.

[0034] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to provide an understanding of the present disclosure. However, it is evident that these embodiments can be practiced without such specific descriptions.

[0035] As used herein, terms such as “component,” “module,” “system,” etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application executed on a computing device and the computing device itself may be a component. One or more components may reside within a processor and / or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers. Additionally, these components may be executed from various computer-readable media having various data structures stored therein. Components may communicate through local and / or remote processes, for example, according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system or distributed system, and / or data transmitted through signals to other systems and networks such as the Internet).

[0036] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items.

[0037] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that such features and / or components are present. However, the terms “comprising” and / or “comprising” should be understood not to exclude the presence or addition of one or more other features, components and / or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0038] And, the term "at least one of A or B" should be interpreted to mean "a case including only A," "a case including only B," or "a combination of A and B."

[0039] Those skilled in the art should recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithmic steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or a combination of both. To clearly exemplify the interchangeability of hardware and software, the various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such functionality is implemented in hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled technicians may implement the described functionality in various ways for each specific application. However, such decisions regarding implementation should not be construed as moving out of the scope of this disclosure.

[0040] The description of the presented embodiments is 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. The general 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 present invention should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

[0041] FIG. 1 is a diagram illustrating a system including a server (100), a user terminal (200), and a communication network (300) according to an embodiment of the contents disclosed in the present specification. The server (100) and the user terminal (200) can give or receive information to each other through the communication network (300).

[0042] The server (100) may be an electronic device of a service provider according to the present disclosure. The service provider may be the operator of a service providing an artificial neural network-based cryptocurrency price prediction method disclosed in this specification. The server (100) is an electronic device that transmits information or provides services to a user terminal (200) connected via wired or wireless connection, and may be, for example, an application server, a proxy server, a cloud server, etc.

[0043] The user terminal (200) may be a terminal of a user using the service according to the present disclosure. The user terminal (200) may be, for example, at least one of a smartphone, a tablet computer, a personal computer, a mobile phone, a personal digital assistant (PDA), an audio player, and a wearable device.

[0044] When describing the configuration or operation of a device in the disclosure of this specification, the term "device" may be used to refer to the device being described, and the term "external device" may be used to refer to a device existing externally from the perspective of the device being described. For example, if the server (100) is described as the "device," the user terminal (200) may be referred to as the "external device" from the perspective of the server (100). Additionally, for example, if the user terminal (200) is described as the "device," the server (100) may be referred to as the "external device" from the perspective of the user terminal (200). That is, the server (100) and the user terminal (200) may each be referred to as the "device" and "external device," or as the "external device" and "device," respectively, depending on the perspective of the operating entity.

[0045] The communication network (300) may include both wired and wireless communication networks. The communication network (300) may operate to exchange data between the server (100) and the user terminal (200). The wired communication network may include, for example, a communication network based on a method such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), RS-232 (Recommended Standard-232), or POTS (Plain Old Telephone Service). A wireless communication network may include, for example, a communication network based on methods such as eMBB (enhanced Mobile Broadband), URLLC (Ultra Reliable Low-Latency Communications), MMTC (Massive Machine Type Communications), LTE (Long-Term Evolution), LTE-A (LTE Advance), NR (New Radio), UMTS (Universal Mobile Telecommunications System), GSM (Global System for Mobile communications), CDMA (Code Division Multiple Access), WCDMA (Wideband CDMA), WiBro (Wireless Broadband), WiFi (Wireless Fidelity), Bluetooth, NFC (Near Field Communication), GPS (Global Positioning System), or GNSS (Global Navigation Satellite System). The communication network (300) of this specification is not limited to the examples described above and may include, without limitation, various types of communication networks that enable data exchange between multiple entities or devices.

[0046] FIG. 2 is a block diagram of a server (100) according to an embodiment of the contents disclosed in this specification. The server (100) may include one or more processors (110), communication interfaces (120), or memory (130) as components. In some embodiments, at least one of these components of the server (100) may be omitted, or other components may be added to the server (100). In some embodiments, additionally or alternatively, some components may be implemented as an integrated unit or as a single or multiple entity. At least some of the components inside or outside the server (100) may be connected to each other via a bus, GPIO (General Purpose Input / Output), SPI (Serial Peripheral Interface), or MIPI (Mobile Industry Processor Interface), etc., to give or receive data or signals.

[0047] In this specification, one or more processors (110) may be referred to as processors (110). The term processor (110) may mean a set of one or more processors unless the context clearly indicates otherwise. A processor (110) may control at least one component of a server (100) connected to the processor (110) by running software (e.g., instructions, programs, etc.). Additionally, the processor (110) may perform various operations such as computation, processing, data generation, or processing. Additionally, the processor (110) may load data, etc. from memory (130) or store it in memory (130).

[0048] The communication interface (120) can perform wireless or wired communication between the server (100) and another device (e.g., user terminal (200) or another server). For example, the communication interface (120) can perform wireless communication according to methods such as eMBB, URLLC, MMTC, LTE, LTE-A, NR, UMTS, GSM, CDMA, WCDMA, WiBro, WiFi, Bluetooth, NFC, GPS, or GNSS. Additionally, for example, the communication interface (120) can perform wired communication according to methods such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), RS-232 (Recommended Standard-232), or POTS (Plain Old Telephone Service).

[0049] Memory (130) can store various data. Data stored in memory (130) may include software (e.g., instructions, programs, etc.) as data acquired, processed, or used by at least one component of the server (100). Memory (130) may include volatile or non-volatile memory. The term memory (130) may mean a set of one or more memories unless the context clearly indicates otherwise. The expressions "set of instructions stored in memory (130)" or "program stored in memory (130)" mentioned herein may be used to refer to an operating system, an application for controlling the resources of the server (100), or middleware that provides various functions to the application so that the application can utilize the resources of the server (100). In one embodiment, when the processor (110) performs a specific operation, the memory (130) can store instructions that are performed by the processor (110) and correspond to the specific operation.

[0050] In one embodiment, the server (100) may transmit data according to the operation result of the processor (110), data received by the communication interface (120), or data stored in memory (130), etc., to an external device. The external device may be a device for displaying, showing, or outputting the received data.

[0051] FIG. 3 is a block diagram of a user terminal (200) according to an embodiment of the contents disclosed in the present specification. The user terminal (200) may include one or more processors (210), communication interfaces (220), or memory (230) as components. Additionally, the user terminal (200) may further include at least one of an input unit (240) or an output unit (250).

[0052] The processor (210) can control at least one component of a user terminal (200) connected to the processor (110) by running software (e.g., instructions, programs, etc.). Additionally, the processor (210) can perform various operations such as computation, processing, data generation, or processing. Furthermore, the processor (210) can load data, etc. from memory (230) or store it in memory (230).

[0053] The communication interface (220) can perform wireless or wired communication between a user terminal (200) and another device (e.g., a server (100) or another user terminal). For example, the communication interface (220) can perform wireless communication according to methods such as eMBB, URLLC, MMTC, LTE, LTE-A, NR, UMTS, GSM, CDMA, WCDMA, WiBro, WiFi, Bluetooth, NFC, GPS, or GNSS. Additionally, for example, the communication interface (220) can perform wired communication according to methods such as USB, HDMI, RS-232, or POTS.

[0054] Memory (230) can store various data. Data stored in memory (230) may include software (e.g., instructions, programs, etc.) as data acquired, processed, or used by at least one component of the user terminal (200). Memory (230) may include volatile or non-volatile memory. Unless the context clearly indicates otherwise, the term memory (230) may mean a set of one or more memories. The expressions "set of instructions stored in memory (230)" or "program stored in memory (230)" mentioned in this specification may be used to refer to an operating system, an application for controlling the resources of the user terminal (200), or middleware that provides various functions to the application so that the application can utilize the resources of the user terminal (200). In one embodiment, when the processor (210) performs a specific operation, the memory (230) can store instructions that are performed by the processor (210) and correspond to the specific operation.

[0055] In one embodiment, the user terminal (200) may further include an input unit (240). The input unit (240) may be a component that transmits data received from an external source to at least one component included in the user terminal (200). For example, the input unit (240) may include a mouse, a keyboard, or a touch pad.

[0056] In one embodiment, the user terminal (200) may further include an output unit (250). The output unit (250) may display (output) information processed by the user terminal (200) or transmit (send) it externally. For example, the output unit (250) may visually display information processed by the user terminal (200). The output unit (250) may display UI (User Interface) information or GUI (Graphic User Interface) information, etc. In this case, the output unit (250) may include at least one of a Liquid Crystal Display (LCD), a Thin Film Transistor-Liquid Crystal Display (TFT-LCD), an Organic Light-Emitting Diode (OLED), a Flexible Display, a 3D Display, or an E-ink Display. Additionally, for example, the output unit (250) may audibly display information processed by the user terminal (200). The output unit (250) can display audio data following any audio file format (e.g., MP3, FLAC, WAV, etc.) through an audio device. In this case, the output unit (250) may include at least one of a speaker, a headset, or headphones. Additionally, for example, the output unit (250) may transmit information processed at the user terminal (200) to an external output device. The output unit (250) may transmit or send information processed at the user terminal (200) to an external output device using a communication interface (220). The output unit (250) may also transmit or send information processed at the user terminal (200) to an external output device using a separate output communication interface.

[0057] The user terminal (200) may be, for example, a mobile phone, a cellular phone, a smartphone, a personal computer, a laptop, a notebook, a netbook or tablet, a personal digital assistant (PDA), a digital camera, a game console, an MP3 player, a personal multimedia player (PMP), an e-book, a navigation system, a disc player, a set-top box, a home appliance, a communication device, or a display device.

[0058] FIG. 4 is a diagram illustrating an exemplary flowchart of an artificial neural network-based cryptocurrency price prediction method according to one embodiment of the present disclosure.

[0059] The processor (110) can obtain monitoring reference information from the user terminal (200) (S410). In the present disclosure, the monitoring reference information may include one or more cryptocurrency names, chart periods, or candle cycles. One or more cryptocurrency names may be text that can identify a specific cryptocurrency, such as "Bitcoin", "Ethereum", "Ripple", etc. The chart period is a value that specifies the length of the total period when generating a chart image, and may include values ​​such as 1 day, 1 week, 3 months, 1 year, etc. The candle cycle is a value that specifies the time length of an individual candle when generating a chart image, and may include values ​​such as 1 tick, 1 minute, 5 minutes, 1 hour, etc.

[0060] The processor (110) can generate a chart image based on monitoring reference information (S420). In the present disclosure, the chart image may be a graph image representing the price fluctuation of a specific cryptocurrency asset.

[0061] In the present disclosure, the chart image may be an image generated by a preprocessing method determined according to monitoring reference information. The processor (110) may generate a chart image by converting price data into a chart image according to a standardized method determined based on monitoring reference information.

[0062] FIG. 5 is a conceptual diagram illustrating an example of converting price data (510) regarding a specific cryptocurrency asset into a chart image (530) based on monitoring reference information. A processor (110) can process the price data of a specific cryptocurrency according to monitoring reference information and generate a chart image based on the processed price data. For example, the horizontal length of the chart image (530) may correspond to the chart period included in the monitoring reference information, and each candle included in the chart may be a candle corresponding to the candle cycle included in the monitoring reference information. Additionally, the vertical length of the chart may have a scaled value based on the maximum and minimum values ​​of the price within the entire period.

[0063] Specifically, assuming that the size of the chart image generated according to a predetermined preprocessing method is 1024 (H, number of vertical pixels) x 1024 (W, number of horizontal pixels), the processor (110) can generate the chart image (530) by corresponding the chart period included in the monitoring reference information (e.g., August 27, 2024 to September 16, 2024, a total of 21 days) to the total horizontal length of 1024 pixels and setting the horizontal width of individual candles to approximately 49 (1024 / 21) pixels according to the chart period (21 days) relative to the candle period (1 day). Additionally, assuming that the minimum value of the cryptocurrency asset price within the chart period included in the monitoring reference information is 1,800 won and the maximum value is 2,000 won, the processor (110) may correspond the minimum-maximum price range (200 won) to the total vertical length of the image, which is 1,024 pixels, and set the vertical length of the individual candle to correspond to the price change amount per candle period. The specific values ​​described above are merely examples for illustrative purposes and do not limit the present disclosure.

[0064] As described above, the present disclosure refines data by converting price data of a specific cryptocurrency asset into chart images in a standardized manner, and accordingly can increase the learning and inference performance of an artificial neural network model.

[0065] The processor (110) can generate a pattern prediction result corresponding to a chart image based on an artificial neural network-based pattern prediction model (S430).

[0066] FIG. 6 is a schematic diagram showing an artificial neural network model according to one embodiment of the present disclosure.

[0067] Throughout this specification, terms such as neural network, artificial neural network, network function, and neural network may be used interchangeably. An artificial 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 composed of at least one node. The nodes (or neurons) constituting the neural networks may be interconnected by one or more links.

[0068] In a neural network, one or more nodes connected via links can form relative input and output node relationships. The concepts of input and output nodes are relative; any node in an output node relationship with respect to one node may be in an input node relationship with respect to another node, and vice versa. As described above, the input node versus output node relationship can be generated based on links. One or more output nodes may be connected to a single input node via links, and vice versa.

[0069] In a relationship between an input node and an output node connected through a single link, the value of the output node's data can be determined based on the data input to the input node. Here, the link interconnecting the input node and the output node may have a weight. The weight can be variable and can be varied by the user or an algorithm to enable the neural network to perform the desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node's value can be determined based on the values ​​input to the input nodes connected to the output node and the weights set on the links corresponding to each input node.

[0070] As described above, a neural network consists of one or more nodes interconnected through one or more links, forming input-output node relationships within the network. The characteristics of a neural network can be determined by the number of nodes and links within the network, the relationships between the nodes and links, and the weight values ​​assigned to each link. For example, if two neural networks exist with the same number of nodes and links but different weight values ​​for the links, the two neural networks may be recognized as different from each other.

[0071] A neural network can be composed of a set of one or more nodes. A subset of nodes constituting a neural network can form a layer. Some of the nodes constituting a neural network can form a layer based on their distances from an initial input node. For example, a set of nodes with a distance of n from an initial input node can form n layers. The distance from the initial input node can be defined by the minimum number of links that must be traversed to reach that node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the degree of a layer within a neural network can be defined in a way different from that described above. For example, a layer of nodes may be defined by its distance from a final output node.

[0072] Initial input nodes may refer to one or more nodes within a neural network to which data is directly input without passing through links in their relationships with other nodes. Alternatively, in terms of link-based relationships between nodes within the neural network, they may refer to nodes that do not have other input nodes connected by links. Similarly, final output nodes may refer to one or more nodes within a neural network that do not have output nodes in their relationships with other nodes. Furthermore, hidden nodes may refer to nodes constituting the neural network that are neither initial input nodes nor final output nodes.

[0073] A neural network according to one embodiment of the present disclosure may have the number of nodes in the input layer equal to the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. Additionally, a neural network according to another embodiment of the present disclosure may have the number of nodes in the input layer less than the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases as it progresses from the input layer to the hidden layer. Additionally, a neural network according to yet another embodiment of the present disclosure may have the number of nodes in the input layer greater than the number of nodes in the output layer, and may be a neural network in which the number of nodes increases as it progresses from the input layer to the hidden layer. A neural network according to yet another embodiment of the present disclosure may be a neural network in which the above-described neural networks are combined.

[0074] A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to input and output layers. Using a deep neural network allows for the identification of latent structures in data. That is, it is possible to identify the latent structures of photos, text, videos, voice, and music (e.g., what objects are present in a photo, what the content and emotions of the text are, what the content and emotions of the voice are, etc.). Deep neural networks may include convolutional neural networks (CNN), recurrent neural networks (RNN), autoencoders, Generative Adversarial Networks (GAN), restricted Boltzmann machines (RBM), deep belief networks (DBN), Q networks, U networks, Siamese networks, Generative Adversarial Networks (GAN), etc. The description of deep neural networks described above is merely illustrative and the present disclosure is not limited thereto.

[0075] In one embodiment of the present disclosure, the network function may include a convolutional neural network (CNN). A convolutional neural network is largely composed of a convolutional layer, a pooling layer, and a fully connected layer. When image data is input, it first undergoes filter operations in the convolutional layer, passes through an activation function, and is then pooled in the pooling layer. This structure is repeated several times. Before being sent as output, the image data processed up to that point is transformed into a 1D array in the fully connected layer. Then, it passes through a softmax layer and is classified into each class.

[0076] In one embodiment of the present disclosure, the network function may include an autoencoder. The autoencoder may be a type of artificial neural network for outputting output data similar to the input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed between the input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called a bottleneck layer (encoding), and then expanded symmetrically from the bottleneck layer to the output layer (symmetrically with respect to the input layer). The autoencoder may perform non-linear dimensionality reduction. The number of input and output layers may correspond to the dimension after preprocessing of the input data. In the autoencoder structure, the number of nodes in the hidden layer included in the encoder may have a structure in which the number of nodes decreases as it moves away from the input layer. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, a sufficient amount of information may not be transmitted, so it may be maintained at a certain number or more (e.g., more than half of the input layer).

[0077] An artificial neural network model can be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Training of an artificial neural network model may be a process of applying knowledge to the artificial neural network model to perform a specific action.

[0078] Artificial neural network models can be trained to minimize the error in their output. The training process involves repeatedly inputting training data into the model, calculating the error between the model's output and the target for the training data, and updating the weights of each node in the model by backpropagating the error from the output layer to the input layer in a direction that reduces the error. In the case of supervised learning, training data is used where the correct answer is labeled for each data point (i.e., labeled training data), whereas in the case of unsupervised learning, the correct answer may not be labeled for each training data point. For instance, in the case of supervised learning for data classification, the training data may consist of data where each training point is labeled with a category. Labeled training data is input into the artificial neural network model, and the error can be calculated by comparing the model's output (category) with the labels of the training data. As another example, in the case of unsupervised learning for data classification, the error can be calculated by comparing the input training data with the output of the artificial neural network model. The calculated error is backpropagated in the artificial neural network model (i.e., from the output layer to the input layer), and through backpropagation, the connection weights of each node in each layer of the artificial neural network model can be updated. The amount of change in the connection weights of each updated node can be determined by the learning rate. The computation of the artificial neural network model on the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the artificial neural network model's learning cycle. For example, a high learning rate can be used in the early stages of training to quickly achieve a certain level of performance and increase efficiency, while a low learning rate can be used in the later stages to improve accuracy.

[0079] In the training of artificial neural network models, the training data is generally a subset of real-world data (i.e., the data intended to be processed using the trained model). Consequently, a training cycle may exist where errors decrease on the training data but increase on real-world data. Overfitting is a phenomenon where the model learns excessively on the training data, leading to increased errors on real-world data. For example, an artificial neural network model trained on yellow cats may fail to recognize cats other than yellow ones as cats; this can be considered a form of overfitting. Overfitting can act as a cause for increased errors in machine learning algorithms. Various optimization methods can be used to prevent such overfitting. To prevent overfitting, methods such as increasing the training data, regularization, dropout (which disables some nodes in the network during training), and the use of batch normalization layers can be applied.

[0080] In one embodiment of the present disclosure, a pattern prediction model may generate a pattern prediction result including probability values ​​for rise and fall for an input chart image. For example, the pattern prediction model may be trained based on a training data set in the form of a 'training chart image-label' data tuple in which label data such as {'Rise': 1, 'Down': 0} or {'Rise': 0, 'Down': 1} is matched for each training chart image included in the training data set.

[0081] In another embodiment of the present disclosure, the pattern prediction model may generate a pattern prediction result including probability values ​​for each of the following: continued upward movement, upward reversal, continued downward movement, and downward reversal, for an input chart image. That is, the pattern prediction model may be trained based on a training data set in which values ​​indicating one of the following are: continued upward movement, upward reversal, continued downward movement, or downward reversal, are labeled for the chart image. In this case, the training data may be in the form in which values ​​such as {'continued upward movement': 1, 'upward reversal': 0, 'continued downward movement': 0, 'downward reversal': 0}, {'continued upward movement': 0, 'upward reversal': 1, 'continued downward movement': 0, 'downward reversal': 0} are mapped to the image, assuming, for example, that the chart image (530) of FIG. 5 is the target chart image for training. The pattern prediction model according to the present embodiment has the effect of providing a more diverse range of prediction results to the user by learning the aspects of the rise and fall more finely, compared to a model that derives prediction results only for the two cases of rise or fall.

[0082] In one embodiment of the present disclosure, the pattern prediction model may be trained based on a training dataset generated by an artificial neural network-based pattern labeling model. The pattern labeling model may be an artificial neural network model trained separately from the pattern prediction model, and may be an artificial neural network model used to generate training data by classifying an input chart image into a specific pattern.

[0083] Specifically, the pattern labeling model can be trained to receive a chart image to be labeled as input and output at least one specific pattern among at least one upward continuation pattern included in an upward continuation pattern group, at least one upward reversal pattern included in an upward reversal pattern group, at least one downward continuation pattern included in a downward continuation pattern group, and at least one downward reversal pattern included in a downward reversal pattern group.

[0084] FIG. 7 is a diagram illustrating one or more patterns belonging to an upward continuation pattern group, an upward reversal pattern group, a downward continuation pattern group, and a downward reversal pattern group. The pattern labeling model can classify an input chart image into one of the multiple patterns included in the upward continuation pattern group, the upward reversal pattern group, the downward continuation pattern group, and the downward reversal pattern group.

[0085] In an example of the present disclosure in which a processor (110) generates a training data set using a pattern labeling model, the processor (110) can generate training data by matching label values ​​of {'Up': 1, 'Down': 0} to the chart image when the input chart image is classified by the pattern labeling model into an upward continuation pattern group or an upward reversal pattern group. Additionally, the processor (110) can generate training data by matching label values ​​of {'Up': 0, 'Down': 1} to the chart image when the input chart image is classified by the pattern labeling model into a downward continuation pattern group or a downward reversal pattern group.

[0086] In another example of a task in which a processor (110) generates a training data set using a pattern labeling model, the processor (110) can generate training data by matching label values ​​of {'Upward Continuation': 1, 'Upward Reversal': 0, 'Downward Continuation': 0, 'Downward Reversal': 0} to the chart image when the input chart image is classified by the pattern labeling model as an upward continuation pattern group, and matching label values ​​of {'Upward Continuation': 0, 'Upward Reversal': 1, 'Downward Continuation': 0, 'Downward Reversal': 0} to the chart image when it is classified by the upward reversal pattern group. In addition, the processor (110) can generate training data by matching label values ​​of {'Upward Continuation': 0, 'Upward Reversal': 0, 'Downward Continuation': 1, 'Downward Reversal': 0} to the chart image when the chart image input by the pattern labeling model is classified into a downward continuation pattern group, and matching label values ​​of {'Upward Continuation': 0, 'Upward Reversal': 0, 'Downward Continuation': 0, 'Downward Reversal': 1} to the chart image when it is classified into a downward reversal pattern group.

[0087] As described above, the processor (110) can generate a training data set by first classifying a chart image into a specific pattern through a pattern labeling model, and then labeling the chart image as rising or falling, or labeling it as continuing rising, reversing rising, continuing falling, and reversing falling, according to the result of the pattern classification. The present disclosure, which generates training data using a pattern labeling model as described above, can improve the training and inference performance of a pattern prediction model by generating a more accurately labeled training data set.

[0088] In one embodiment of the present disclosure, a pattern prediction model may be trained based on a training data set generated based on a price change determination cycle input by a user.

[0089] In the present disclosure, the term "price change determination period" may be used to refer to the time interval between the point in time when a prediction is performed to determine the price change of an asset and the point in time when the success or failure of the prediction is determined. A user may input the price change determination period through the input unit (240) of the user terminal (200) and transmit it to the server (100). The price change determination period may be set as the number of candles having a specific period (n, n is a natural number) or as a specific period (1 minute, 15 minutes, 10 days, etc.).

[0090] FIG. 8 is a conceptual diagram illustrating an example in which different true values ​​are labeled for a chart image depending on the length of the price change determination cycle. In FIG. 8, when the price change determination cycle is set as P1, the price of the asset has fallen since the period P1 compared to the last point in time of the chart image (810), so the chart image (810) may be labeled with values ​​such as {'Increase': 0, 'Down': 1}. On the other hand, when the price change determination cycle is set as P2, the price of the asset has risen since the period P2 compared to the last point in time of the chart image (810), so the chart image (810) may be labeled with values ​​such as {'Increase': 1, 'Down': 0}.

[0091] The present disclosure can generate a training data set based on a price change determination cycle input by a user and train a pattern prediction model through it. As such, even with the same price fluctuation data, the prediction results need to be derived differently depending on the price change determination cycle set by the user, and the processor (110) of the present disclosure can generate training data based on the price change determination cycle obtained from the user, train a pattern prediction model, and provide it to the user. In other words, even with the same cryptocurrency asset price fluctuation data, different training data can be generated for each price change determination cycle set by each user, and the present disclosure can provide a personalized pattern prediction model that takes into account the user's investment propensity by using a pattern prediction model trained according to each training data.

[0092] In one embodiment of the present disclosure, a pattern prediction model may be trained using a loss function that calculates a loss value based on a salience map for an input chart image.

[0093] FIG. 9 is a conceptual diagram illustrating the input and output data of a pattern prediction model. The pattern prediction model of the present disclosure can be trained to output a pattern prediction result (920) including probability values ​​for each classification category, as well as a salience map (930), through computation on an input chart image (910).

[0094] In this disclosure, the term "saliency map" may be used interchangeably with the term "saliency map" and may be generated, for example, through the Grad-CAM technique. Here, the Grad-CAM technique refers to a method that allows an artificial neural network model for image processing to determine which parts of an image were primarily viewed when predicting a specific class through computation.

[0095] In order to specifically explain the process of generating a salience map in the present disclosure, let us assume below that a pattern prediction model outputs values ​​such as {'Rising': 0.9, 'Down': 0.1} for an input chart image and predicts the input chart image as 'Rising' accordingly.

[0096] The processor (110) can calculate the gradient for each of the multiple feature maps derived from the last convolution layer for the predicted 'rising' class and calculate a weight representing the importance that each feature map has for the 'rising' class by averaging them over image space. The importance weight of each feature map can be calculated as shown in Equation 1 below.

[0097]

[0098] a on the left side k represents the weight corresponding to the k-th feature map generated in the last convolutional layer. Of the right side is the logit value z for the 'rise' of the fully connected layer. 상승 k-th feature map( It represents the value obtained by differentiation with respect to ). Here, i and j are indices representing pixel positions in the horizontal and vertical directions, respectively, and Z represents the total number of pixels.

[0099] The processor (110) calculates weights (a) for each feature map. k A Class Activation Map (CAM) can be generated using ). Mathematical Equation 2 below represents the formula for deriving the Class Activation Map.

[0100]

[0101] A on the right side of mathematical equation 2 k represents the k-th feature map and a krepresents the weight corresponding to the k-th feature map. That is, the class activation map can be generated by weighting each feature map according to importance and performing a ReLU operation on the result. As described above, the generated class activation map can ultimately be used as a salience map. In this case, if the size of the class activation map differs from the size of the input chart image, the processor (110) can adjust the class activation map to have the same size as the chart image by upsampling it.

[0102] For example, the loss function calculated based on the salience map can be expressed as Equation 3 below.

[0103]

[0104] The L1 term on the right side represents a loss term indicating how different the model's predicted result is from the actual true value (Ground Truth), and can be, for example, Cross-Entropy Loss. The L2 term represents a loss term calculated based on the salience map. λ is a parameter representing the weight of the L2 term.

[0105] In one embodiment of the present disclosure, a loss function that calculates a loss value based on a salience map may be a function that calculates a loss value by considering the ratio of common areas between a major area within an input chart image and a major area within a salience map.

[0106] FIG. 10 is a diagram illustrating an exemplary chart image and a salience map. The chart image (910) and the salience map (930) may be image data having the same size. The chart image (910) is an image generated by the processor (110) for a specific asset according to monitoring reference information transmitted from the user, and the salience map (930) may be an image generated as the output of a pattern prediction model.

[0107] The main area (913) within the chart image (910) represents an area that needs to be primarily checked within the image to determine a pattern for the chart image, and can be generated according to a method that is directly specified by the user for each chart image included in the training data set or predetermined by the processor (110). In this case, the predetermined method may be a method of specifying the main area by including candles around a main reference candle, such as, for example, "a rectangle containing a candle whose rate of increase from the open price to the close price is 10% or more and whose trading volume is 10 times or more than the 20-day moving average of trading volume, and the 10 candles to the left and 2 candles to the right of said candle."

[0108] The main area (933) within the salience map (930) can be determined by comparing the value of each pixel within the salience map (930) with a specific value. For example, if the distribution of values ​​of pixels within the salience map (930) is [0, 1], the main area (933) can be determined by extracting pixels that have a value of 0.9 or higher.

[0109] FIG. 11 is a diagram exemplarily illustrating a common area between a major area within a chart image and a major area within a salience map. As illustrated in FIG. 11, a common area (1000) composed of pixels at the same location may exist between a major area (913) within a chart image (910) and a major area (933) within a salience map (930). The ratio of the common area can be calculated as shown in Equation 4 below.

[0110]

[0111] A on the right side c represents the area of ​​the main region (913) within the chart image, and A s represents the area of ​​the main region (933) within the salience map. The ratio of the common region (1000), expressed as in Equation 4, has a value between 0 and 1.

[0112] A loss function for training a pattern prediction model according to the present disclosure can be configured to derive a lower loss value as the proportion of the common area increases and a higher loss value as the proportion of the common area decreases. For example, if the L2 term of Equation 3 is configured as the reciprocal of Equation 4, such a loss function can be generated.

[0113] As described above, the present disclosure has the effect of directly indicating to the pattern prediction model the area within a chart image that should be primarily referenced to predict patterns in the chart image by designing the loss function of the pattern prediction model using a salience map. Through this, it is possible to generate a more reliable artificial neural network-based pattern prediction model.

[0114] Referring again to FIG. 4, the processor (110) can transmit notification information generated based on the pattern prediction result to the user terminal (200) (S440). The notification information may include at least one of the cryptocurrency name, the type of the discovered pattern, the probability of a rise, the probability of a fall, and the time of pattern discovery. The processor (110) can transmit notification information to the user in real time when a rise / fall pattern according to the user's settings appears on the cryptocurrency asset of interest or the cryptocurrency asset held.

[0115] The user can proceed with the investment according to the notification information received by the user terminal (200), and this has the advantage of reducing the inconvenience of having to continuously check the chart to identify a specific pattern.

[0116] FIG. 12 is a block diagram of a computing device according to one embodiment of the present disclosure.

[0117] FIG. 12 illustrates a brief and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0118] Although the present disclosure has generally been described in relation to computer-executable instructions that can be executed on one or more computers, those skilled in the art will know that the present disclosure may be combined with other program modules and / or implemented as a combination of hardware and software.

[0119] Generally, a program module includes routines, programs, components, data structures, etc., that perform a specific task or implement a specific abstract data type. Furthermore, those skilled in the art will be well aware that the method of the present disclosure may be implemented in other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. (each of which may be connected to and operated with one or more associated devices).

[0120] The embodiments described in this disclosure may also be implemented in a distributed computing environment in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0121] Computers typically include various computer-readable media. Any medium accessible by a computer may be a computer-readable medium. Computer-readable media include volatile and non-volatile media, transitory and non-transitory media, and removable and non-removable media. By example, but not by limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media include volatile and non-volatile media, transitory and non-transitory media, and removable and non-removable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD (digital video disk) or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be accessed by a computer and used to store desired information.

[0122] Computer-readable transmission media typically include all information transmission media that implement computer-readable instructions, data structures, program modules, or other data, etc., on a modulated data signal, such as other transport mechanisms. The term modulated data signal means a signal in which one or more of the characteristics of the signal are set or modified to encode information within the signal. By example, not limiting, computer-readable transmission media include wired media such as wired networks or direct-wired connections, and wireless media such as acoustic, RF, infrared, and other wireless media. Any combination of the media described above is also considered to be included within the scope of computer-readable transmission media.

[0123] An exemplary environment (1100) for implementing various aspects of the present disclosure, including a computer (1102), is shown, wherein the computer (1102) includes a processing unit (1104), a system memory (1106), and a system bus (1108). The system bus (1108) connects system components, including the system memory (1106) (but not limited thereto), to the processing unit (1104). The processing unit (1104) may be any processor among various commercial processors. Dual processors and other multiprocessor architectures may also be used as the processing unit (1104).

[0124] The system bus (1108) may be any of several types of bus structures that can be additionally interconnected to a local bus using any of the memory bus, peripheral bus, and various commercial bus architectures. System memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). The basic input / output system (BIOS) is stored in non-volatile memory (1110), such as ROM, EPROM, EEPROM, etc., and this BIOS includes basic routines that help transfer information between components within the computer (1102) at times such as during startup. The RAM (1112) may also include high-speed RAM, such as static RAM, for caching data.

[0125] The computer (1102) also includes an internal hard disk drive (HDD) (1114) (e.g., EIDE, SATA)—this internal hard disk drive (1114) may also be configured for external use within a suitable chassis (not shown)—a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from or writing to a removable diskette (1118)), and an optical disk drive (1120) (e.g., for reading from a CD-ROM disk (1122) or reading from or writing to other high-capacity optical media such as a DVD). The hard disk drive (1114), the magnetic disk drive (1116), and the optical disk drive (1120) may each be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128). The interface (1124) for implementing an external drive includes at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

[0126] These drives and associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, etc. In the case of a computer (1102), the 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 know that other types of computer-readable media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc., may also be used in exemplary operating environments and that any of these media may contain computer-executable instructions for performing the methods of the present disclosure.

[0127] A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), may be stored in the drive and RAM (1112). All or part of the operating system, application, module and / or data may also be cached in RAM (1112). It will be well known that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

[0128] The user can input commands and information into the computer (1102) through one or more wired / wireless input devices, such as a pointing device like a keyboard (1138) and a mouse (1140). Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, etc. These and other input devices are often connected to the processing unit (1104) via an input device interface (1142) connected to the system bus (1108), but may also be connected via other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, etc.

[0129] A monitor (1144) or other type of display device is also connected to the system bus (1108) via an interface such as a video adapter (1146). In addition to the monitor (1144), the computer generally includes other peripheral output devices (not shown), such as speakers, a printer, and so on.

[0130] The computer (1102) may operate in a networked environment using a logical connection to one or more remote computers, such as remote computer(s) (1148), via wired and / or wireless communication. The remote computer(s) (1148) may be a workstation, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other conventional network node, and generally include many or all of the components described for the computer (1102), but for brevity, only the memory storage device (1150) is illustrated. The illustrated logical connection includes a wired / wireless connection to a local area network (LAN) (1152) and / or a larger network, e.g., 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 global computer network, e.g., the Internet.

[0131] When used in a LAN networking environment, the computer (1102) is connected to a local network (1152) via a wired and / or wireless communication network interface or adapter (1156). The adapter (1156) may facilitate wired or wireless communication to the LAN (1152), and the LAN (1152) may also include a wireless access point installed therein to communicate with the 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 have other means to establish communication through the WAN (1154), such as through the Internet. The modem (1158), which may be an internal or external and a wired or wireless device, is connected to the system bus (1108) via a serial port interface (1142). In a networked environment, program modules or parts thereof described for a computer (1102) may be stored in a remote memory / storage device (1150). It will be well known that the illustrated network connection is exemplary and that other means of establishing a communication link between computers may be used.

[0132] The computer (1102) operates to communicate with any wireless device or object that is deployed and operated via wireless communication, for example, a printer, scanner, desktop and / or portable computer, PDA (portable data assistant), communication satellite, any equipment or place associated with a wireless detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network, or simply ad hoc communication between at least two devices.

[0133] Wi-Fi (Wireless Fidelity) enables connectivity to the Internet and other sources without wires. Wi-Fi is a wireless technology, similar to a cell phone, that allows devices, such as computers, to transmit and receive data indoors and outdoors—that is, anywhere within the coverage area of ​​a base station. Wi-Fi networks use a wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band).

[0134] Those skilled in the art of the present disclosure will understand that information and signals may be represented using any various different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0135] Those skilled in the art to which this disclosure is made will understand that the various exemplary logic blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented by electronic hardware, various forms of programs or design code (referred to herein as “software”), or a combination of all such. To clearly illustrate this interoperability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been generally described above in relation to their functions. Whether such functions are implemented as hardware or software depends on the design constraints imposed on the specific application and the overall system. Those skilled in the art to which this disclosure is made may implement the functions described in various ways for each specific application, but such implementation decisions should not be interpreted as being outside the scope of this disclosure.

[0136] The various embodiments presented herein may be implemented as methods, devices, or articles manufactured using standard programming and / or engineering techniques. The term “article manufactured” includes a computer program or media accessible from any computer-readable device. For example, computer-readable media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical discs (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Additionally, the various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

[0137] It should be understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. It should be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of this disclosure based on design priorities. The appended method claims provide various step elements in a sample order, but do not imply being limited to the specific order or hierarchy presented.

[0138] Description of the presented embodiments is provided so that a person skilled in the art may use or practice the present disclosure. Various modifications to these embodiments will be apparent to a person skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the embodiments presented herein, but should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

Claims

1. An artificial neural network-based cryptocurrency price prediction method performed by one or more processors of a computing device, A step of obtaining monitoring reference information from a user terminal; A step of generating a chart image based on the above monitoring reference information; A step of generating a pattern prediction result corresponding to the chart image based on an artificial neural network-based pattern prediction model; and A step of transmitting notification information generated based on the above pattern prediction result to the user terminal; including, Artificial Neural Network-based Cryptocurrency Price Prediction Method 2. In Paragraph 1, The above monitoring standard information is, Including one or more cryptocurrency names, chart periods, or candle cycles, Artificial Neural Network-based Cryptocurrency Price Prediction Method 3. In Paragraph 1, The above chart image is an image generated by a pre-processing method determined according to the above monitoring reference information, Artificial Neural Network-based Cryptocurrency Price Prediction Method 4. In Paragraph 1, The above pattern prediction model is, A model that generates pattern prediction results including probability values ​​for rise and fall for the above chart image, Artificial Neural Network-based Cryptocurrency Price Prediction Method 5. In Paragraph 1, The above pattern prediction model is, A model that generates pattern prediction results including probability values ​​for upward continuation, upward reversal, downward continuation, and downward reversal, respectively, for the above chart image, Artificial Neural Network-based Cryptocurrency Price Prediction Method 6. In Paragraph 1, The above pattern prediction model is, trained based on a training dataset generated by an artificial neural network-based pattern labeling model, Artificial Neural Network-based Cryptocurrency Price Prediction Method 7. In Paragraph 6, The above pattern labeling model is, Receive a chart image to be labeled as input At least one rising continuation pattern included in the rising continuation pattern group; At least one upward reversal pattern included in the upward reversal pattern group; At least one downside continuation pattern included in the downside continuation pattern group; and At least one bearish reversal pattern included in the bearish reversal pattern group; A model trained to output at least one specific pattern, Artificial Neural Network-based Cryptocurrency Price Prediction Method 8. In Paragraph 1, The above pattern prediction model is, Learned based on a training dataset generated based on price change decision cycles input by the user, Artificial Neural Network-based Cryptocurrency Price Prediction Method 9. In Paragraph 8, A step of obtaining the above price change determination cycle from the user; A step of generating the training data set based on the above price change determination cycle; and A step of training the pattern prediction model using the generated training data set; including, Artificial Neural Network-based Cryptocurrency Price Prediction Method 10. In Paragraph 1, The above pattern prediction model is, A model trained using a loss function that calculates a loss value based on a salience map of an input chart image, Artificial Neural Network-based Cryptocurrency Price Prediction Method 11. In Paragraph 10, The above loss function is, A function that calculates a loss value by considering the ratio of common areas between the major areas within the input chart image and the major areas within the salience map, Artificial Neural Network-based Cryptocurrency Price Prediction Method 12. A computer program stored on a computer-readable storage medium, wherein, when executed by one or more processors, the computer program causes the one or more processors to perform artificial neural network-based cryptocurrency price prediction operations, and said operations are: Operation of obtaining monitoring reference information from a user terminal; The operation of generating a chart image according to the above monitoring reference information; An operation to generate a pattern prediction result corresponding to the chart image based on an artificial neural network-based pattern prediction model; and The operation of transmitting notification information generated based on the above pattern prediction result to the user terminal; including, Computer program stored on a computer-readable storage medium.

13. As a computing device, At least one processor; and memory Includes, The above-mentioned at least one processor is, Obtaining monitoring standard information from a user terminal, and Generate a chart image based on the above monitoring standard information, and Based on an artificial neural network-based pattern prediction model, a pattern prediction result corresponding to the chart image is generated, and Transmitting notification information generated based on the above pattern prediction result to the user terminal, Computing device.

Images