System, method

Abstract

Provided are an apparatus and a method for predicting SNS posting data. **Solution**: An apparatus for predicting SNS posting data, in a state where there are at least two or more users, for each user, obtains information on the user's actions on at least two or more days, requests AI to perform supervised learning based on the information, stores the learning data, and provides a function of requesting AI to predict the actions of the user corresponding to a certain task based on the specified learning data.

Description

Technical Field

[0001] The present invention relates to an apparatus, a prediction apparatus, or a prediction method.

Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] Patent Document 1 discloses a conversation support apparatus.

Prior Art Document

Patent Document

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the inventor has recognized that at least in the above-described embodiment, there is a drawback that there is no method for predicting a user's behavior regarding a certain problem.

Means for Solving the Problems

[0006] At least one aspect of the present disclosure is in a state where at least two or more users exist, for each user, acquire information regarding the behavior of the user on at least two or more days, based on the information, request an AI to perform supervised learning, store the learning data separately, based on the specified learning data, request an AI to predict the behavior of the corresponding user regarding a certain problem, an apparatus is provided.

Effects of the Invention

[0007] In this configuration, there is at least the usefulness that ideas can be generated or discussions can be activated by predicting the user's actions based on the user's characteristics.

[0008] These and other aspects, features, and advantages of the present disclosure will become apparent from the following detailed written description of the preferred embodiments and aspects taken in conjunction with the following drawings, but modifications and variations thereof can be made without departing from the spirit and scope of the novel concepts of the present disclosure. Aspects in one embodiment of the present disclosure can be combined with, or replaced by, one or more of the aspects in another embodiment of the present disclosure, as long as they do not conflict.

Mode for Carrying Out the Invention

[0009] In the following disclosure, many different embodiments and examples are provided for implementing different features of the presented subject matter. To simplify the present disclosure, specific examples of components and arrangements are disclosed below. Of course, these are merely examples and are not intended to be limiting. For example, a structure in which a first feature is covered by, or in contact with, a second feature subsequently disclosed may include embodiments in which the first feature and the second feature are formed so as to be in direct contact, as well as embodiments in which additional features are formed between the first feature and the second feature so that the first feature and the second feature are not in direct contact. Further, in the present disclosure, reference numerals and / or letters may be repeated in various examples. Such repetition is for the sake of brevity and clarity and does not necessarily require that there be a relationship between the various embodiments and / or the configurations being described. Further, when a first element is described as being "connected" or "coupled" to a second element, such description includes embodiments in which the first element and the second element are directly connected or coupled to each other, as well as embodiments in which the first element and the second element are indirectly connected or coupled to each other with one or more other elements intervening therebetween.

[0010] As used herein, the phrase "at least one of" encompasses all possible variations. For example, the phrase "comprises at least one of A, B, or C" is synonymous with "consisting of A, B, C and combinations thereof", and encompasses all possible variations of A, B, C, A+B, A+C, B+C, and A+B+C.

[0011] In the present disclosure, a disclosure using a machine, an electronic operator, or a computer can include embodiments of a method, a recording medium, an apparatus, or a program. The description "A is B" used herein can be replaced with "A includes B" as long as there is no contradiction or unless otherwise stated in this specification.

[0012] The terms in the present disclosure, including the terms described in the claims, can be interpreted in consideration of the descriptions and drawings described in the specification, and further, as long as there is no contradiction with the suggestions in the present disclosure, can be interpreted based on matters that one or more members of the public have so named, indicated, understood, or practiced, or that are possible, in the past, present, or future. Regarding the operation method used in at least one embodiment, the following embodiments can be adopted. The description of JP6456303, which well explains at least one embodiment, is cited for explanation (hereinafter, citation starts).

[0013] As used herein, the term "computer", as known in the art, generally includes a processor, a memory, such as a hard drive, disk drive, flash drive, or memory stick, or other non-transitory computer-readable medium or non-transitory storage device, at least one information storage / search device, such as a keyboard, mouse, pointing and touch device, touch screen, or microphone, at least one input device, and a display structure such as a well-known computer screen. Additionally, a computer may include one or more network connections, such as a wired or wireless connection. As known in the art, such a computer or computer system may include more or less of the items listed above and is not limited to, for example, tablet computers or smart devices, but encompasses other electronic media and electronic devices.

[0014] As used herein, the term "cloud" or "cloud computing" refers to a centralized and virtualized computing facility where all computing resources are shared. For application systems and subsystems, since they are all "in the cloud", it is no longer possible to refer to a specific machine.

[0015] As used herein, the term "Distributed Internet Service System" refers to a distributed Internet service platform that transforms Internet applications for execution in various computing environments. The DIS system delivers Internet applications, including content, data, and logic, via a Component Distribution Server / Asset Distribution Server to any number and type of device, to whatever extent appropriate, and along the network. Through DIS, Internet applications can be hosted and centrally managed as services based on each user's needs, locally cached and executed at the user's device or nearby location while maintaining their integrity. Web-enabled computing devices can be upgraded with DIS software to become DIS-compliant for enjoying and running distributed Internet services. The distributed Internet service system is fully described in any one of the patent families of U.S. Patent Nos. 7,136,857, 7,150,015, 7,181,731, 7,209,921, 7,430,610, 7,685,183, 7,685,577, 7,752,214, 8,326,883, 8,386,525, 8,443,035, 8,458,142, 8,458,222, 8,473,468, 8,527,545, and 8,650,226, and U.S. Patent Publications Nos. 2012 / 0005205 and 2013 / 0091252, all of which are jointly owned by OPIE 40, Holdings, Inc. and are hereby incorporated by reference. (End of citation)

[0016] Regarding the operation method used in at least one or more embodiments, the following embodiments can be adopted for the conventional Internet method that does not use a distributed Internet. The description of JP7113047, which well explains at least one or more embodiments, will be cited for explanation (hereinafter, citation starts).

[0017] Embodiments including the matters specifically disclosed in this specification can provide an automatic response system realized in a form that actually converses with humans based on artificial intelligence, thereby enabling a more natural conversation with users while quickly and conveniently processing inquiries, reservations, delivery orders, and the like.

[0018] The plurality of electronic devices 110, 120, 130, 140 may be fixed terminals or mobile terminals realized by a computer system. Examples of the plurality of electronic devices 110, 120, 130, 140 include AI speakers, smartphones, mobile phones, navigation devices, PCs (personal computers), notebook PCs, digital broadcast terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablets, game consoles, wearable devices, IoT (internet of things) devices, VR (virtual reality) devices, AR (augmented reality) devices, and the like. As an example, in FIG. 1, an AI speaker is shown as the electronic device 110. However, in the embodiments of the present invention, the electronic device 110 may mean one of various physical computer systems that can communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 via the network 170 by substantially using a wireless or wired communication method.

[0019] The communication method is not limited, and it includes not only a communication method using a communication network that the network 170 can include (for example, a mobile communication network, a wired Internet, a wireless Internet, a broadcast network, a satellite network, etc.), but also short-range wireless communication between devices may be included. For example, the network 170 may include any one or more of networks such as a PAN (personal area network), a LAN (local area network), a CAN (campus area network), a MAN (metropolitan area network), a WAN (wide area network), a BBN (broadband network), and the Internet. Further, the network 170 may include any one or more of network topologies including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or hierarchical network, etc., but is not limited thereto.

[0020] Servers 150 and 160 may each be implemented by one or more computer devices that communicate with a plurality of electronic devices 110, 120, 130, 140 via a network 170 to provide instructions, code, files, content, services, etc. For example, server 150 may be a system that provides a first service to a plurality of electronic devices 110, 120, 130, 140 connected via network 170, and server 160 may also be a system that provides a second service to a plurality of electronic devices 110, 120, 130, 140 connected via network 170. As a more specific example, server 150 may provide, as the first service, a service (such as an automatic response service, for example) targeted by the corresponding application to a plurality of electronic devices 110, 120, 130, 140 through an application that is a computer program installed and executed in the plurality of electronic devices 110, 120, 130, 140. As another example, server 160 may provide, as the second service, a service that distributes files for installation and execution of the above-described application to a plurality of electronic devices 110, 120, 130, 140.

[0021] FIG. 2 is a block diagram for explaining the internal configurations of an electronic device and a server in an embodiment of the present invention. In FIG. 2, the internal configuration of electronic device 110 and the internal configuration of server 150 are described as examples for the electronic device. Also, the other electronic devices 120, 130, 140 and server 160 may have the same or similar internal configurations as the above-described electronic device 110 or server 150.

[0022] The electronic device 110 and the server 150 may include memories 211 and 221, processors 212 and 222, communication modules 213 and 223, and input / output interfaces 214 and 224. The memories 211 and 221 may be non-transitory computer-readable recording media, and may include non-transitory mass storage devices such as RAM (random access memory), ROM (read only memory), disk drives, SSDs (solid state drives), flash memories, and the like. Here, non-transitory mass storage devices such as ROM, SSD, flash memory, and disk drives may be included in the electronic device 110 or the server 150 as separate non-transitory recording devices distinct from the memories 211 and 221. Also, the memories 211 and 221 may record an operating system and at least one program code (for example, code for a browser installed and executed in the electronic device 110, an application installed in the electronic device 110 for providing a specific service, etc.). Such software components may be loaded from a computer-readable recording medium different from the memories 211 and 221. Such another computer-readable recording medium may include computer-readable recording media such as floppy (registered trademark) drives, disks, tapes, DVD / CD-ROM drives, memory cards, and the like. In other embodiments, the software components may be loaded into the memories 211 and 221 through the communication modules 213 and 223 that are not computer-readable recording media. For example, at least one program may be loaded into the memories 211 and 221 based on a computer program (for example, the above-described application) installed by a file distributed by a file distribution system (for example, the above-described server 160) that distributes developer or application installation files via the network 170.

[0023] The processors 212 and 222 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. The instructions may be provided to the processors 212 and 222 by the memories 211 and 221 or the communication modules 213 and 223. For example, the processors 212 and 222 may be configured to execute instructions received according to program code recorded in a recording device such as the memories 211 and 221.

[0024] The communication modules 213 and 223 may provide a function for the electronic device 110 and the server 150 to communicate with each other via the network 170, or may provide a function for the electronic device 110 and / or the server 150 to communicate with other electronic devices (for example, the electronic device 120) or other servers (for example, the server 160). As an example, a request generated by the processor 212 of the electronic device 110 according to program code recorded in a recording device such as the memory 211 may be transmitted to the server 150 via the network 170 under the control of the communication module 213. Conversely, control signals, instructions, contents, files, etc. provided under the control of the processor 222 of the server 150 may be received by the electronic device 110 through the communication module 213 of the electronic device 110 via the communication module 223 and the network 170. For example, control signals, instructions, contents, files, etc. received through the communication module 213 may be transmitted to the processor 212 and the memory 211, and the contents and files may be recorded in a recording medium (the non-transitory recording device described above) that the electronic device 110 may further include.

[0025] The input / output interface 214 may be means for interfacing with an input / output device 215. For example, the input device may include devices such as a keyboard, a mouse, a microphone, a camera, etc., and the output device may include devices such as a display, a speaker, a tactile feedback device, etc. As another example, the input / output interface 214 may be means for interfacing with a device in which functions for input and output are integrated into one, such as a touch screen. The input / output device 215 may be composed of the electronic device 110 and one device. Also, the input / output interface 224 of the server 150 may be means for interfacing with a device (not shown) for input or output that can be connected to or included in the server 150. As a more specific example, when the processor 212 of the electronic device 110 processes the instructions of a computer program loaded in the memory 211, a service screen or content configured using data provided by the server 150 or the electronic device 120 may be displayed on the display through the input / output interface 214.

[0026] Also, in other embodiments, the electronic device 110 and the server 150 may include more components than the components shown in FIG. 2. However, it is not necessary to clearly show most of the conventional components in the figure. For example, the electronic device 110 may be implemented to include at least a part of the above-described input / output device 215, or may further include other components such as a transceiver, a camera, various sensors, a database, etc. As a more specific example, when the electronic device 110 is an AI speaker, various components such as various sensors generally included in the AI speaker, a camera module, various physical buttons, buttons using a touch panel, an input / output port, a vibrator for vibration, etc. may be implemented to be further included in the electronic device 110. (End of citation)

[0027] Disclosed is a machine. According to at least one embodiment, the user terminal comprises a control unit, a RAM, a storage unit, a graphics processing unit, a communication interface, and an interface unit, which are respectively connected by an internal bus.

[0028] According to at least one embodiment, the control unit is composed of a CPU and a ROM. The control unit executes the program stored in the storage unit to control the user terminal. The RAM is the work area of the control unit. The storage unit is a storage area for storing programs and data. The control unit reads the program and data from the RAM for processing. The control unit processes the program and data loaded into the RAM and outputs a drawing command to the graphics processing unit.

[0029] According to at least one embodiment, the graphics processing unit is connected to a display unit. The display unit has a display screen. When the control unit outputs a drawing command to the graphics processing unit, the graphics processing unit outputs a video signal for displaying an image on the display screen. Here, the display unit may be a touch panel equipped with a touch sensor. The touch panel of this display unit functions as an input unit.

[0030] According to at least one embodiment, the communication interface can be connected to a communication network wirelessly or by wire, and can transmit and receive data with a server device via the communication network. The data received via the communication interface is loaded into the RAM and processed by the control unit. An external memory (e.g., an SD card, etc.) is connected to the interface unit.

[0031] According to at least one embodiment, the user terminal is not particularly limited as long as it is a computer device having a display screen and an input unit. Examples of the user terminal include a conventional mobile phone, a tablet terminal, a smartphone, a desktop or notebook personal computer, etc. It may also be composed of a VR goggle, that is, a screen (or two display panels, one for each eye) attached to a frame (or headset) fixed or attached to the head with a strap. The user terminal has an audio output unit.

[0032] According to at least one embodiment, the user terminal can be communicatively connected to the server device via a communication network. It can communicate via the communication network to send or receive information.

[0033] According to at least one embodiment, the server device includes at least a control unit, a RAM, a storage unit, and a communication interface, which are respectively connected by an internal bus.

[0034] According to at least one embodiment, the control unit is composed of a CPU and a ROM, executes a program stored in the storage unit, and controls the server device. The control unit also includes an internal timer for timing. The RAM is a work area for the control unit. The storage unit is a storage area for storing programs and data. The control unit reads programs and data from the RAM and performs program execution processing based on information received from the user terminal, etc.

[0035] Disclose about AI. According to at least one embodiment, artificial intelligence includes machine learning, deep learning, generative AI, large language models, LLM, foundation models, generative AI. Generative AI uses transformers and employs a number of mechanisms called attention. It uses self-supervised learning, Extract Prediction. In this case, the AI can guess the next word. Given a sentence, it guesses the next word from the text up to that point. It creates a large number of supervised learning problems. As a result, an AI that can guess the next word can be created. Generative AI can predict grammar structures, topic connections, and that a person of such a style is likely to write such a sentence. Furthermore, generative AI can learn the structure, causal relationships, and knowledge behind just guessing the next sentence. Generative AI has a high speed of scaling, and the greater the number of parameters, the higher the accuracy. Ordinary statistics and machine learning will overfit if the model parameters are made too large compared to the data sample size. For LLM, the greater the number of parameters, the higher the accuracy. One generative AI has 175 billion parameters. Generative AI is trained with supervised learning to have smooth conversations. It is taught not to say strange things. It writes reviews or acts as a call center operator.

[0036] According to at least one embodiment, a large language model (LLM) is, non-exhaustively, a natural language processing model of machine learning constructed using a large amount of dataset and deep learning techniques. Generally, it is adapted to various natural language processing (NLP) tasks such as text classification / generation, sentiment analysis, text summarization, and question answering using a method called "fine-tuning" which trains on a specific task. According to at least one embodiment, self-supervised learning is close to human essential intelligence. When humans act, they always predict the next event and the next input. In that process, they can learn the structure of the external world. Predicting the next word is an essential intelligence and is close to what the cerebral cortex does. According to at least one embodiment, a large language model memorizes the input information but generalizes to the extent necessary to predict the next word. It does not generalize all the information from the beginning. A large language model requires capacity to memorize information. Also, parameters are required for that. According to at least one embodiment, a large language model is equipped with 175 billion parameters or eight models with 220 billion parameters.

[0037] According to at least one embodiment, videos and images are represented as a set of visual patches, which are small data units similar to the text tokens of an LLM. Patches can effectively represent the model of visual data and are used as a very scalable and effective representation for training generative models with various types of videos and images. First, a video is compressed into a low-dimensional latent space, and then the representation is decomposed into spatio-temporal patches to convert the video into patches.

[0038] According to at least one embodiment, a Video compression network is a network that reduces the dimension of visual data. It receives raw videos as input and outputs a temporally and spatially compressed latent representation. An AI is trained in this compressed latent space and then generates videos within this compressed latent space.

[0039] According to at least one embodiment, given a compressed input video, Spacetime Latent Patches extracts a series of spatio-temporal patches that function as transformer tokens. With the patch-based representation, Sora can be trained on videos and images of various resolutions, lengths, and aspect ratios, and at inference time, by arranging randomly initialized patches into a grid of appropriate size, it controls the size of the generated video.

[0040] According to at least one embodiment, the AI is a diffusion model and is trained to predict the original "clean" patches when noisy patches (and conditional information such as text prompts) are input. The AI is a diffusion transformer, which exhibits remarkable scaling properties in various areas such as language modeling, computer vision, and image generation. The diffusion transformer is also effective as a video generation model. As the computational cost of training increases, the quality of the samples improves significantly for the AI.

[0041] According to at least one embodiment, the AI applies caption regeneration technology to train a very explanatory caption model and then uses it to generate text captions for all videos in the training set. Training highly explanatory captions improves not only the overall quality of the generated videos but also the faithfulness of the text. Utilize GPT to convert short user prompts into long detailed captions and send them to the model. This enables the AI to generate high-quality videos that exactly follow the user's prompts.

[0042] According to at least one embodiment, in natural language processing, vectorization can be performed by AI along the following process. First, cleaning processing of the given text is performed as preprocessing. In the cleaning process, unnecessary words such as JavaScript code and HTML tags included in the text are removed. Since these codes are used for display on the Internet, they are generally not used information in natural language processing. Subsequently, the text is segmented into word level by morphological analysis. Morphological analysis is to classify into the smallest language units with meaning in a sentence of natural language written in characters. As morphological analysis tools, "MeCab", "JUMAN", and "JANOME" can be used. In normalization, words with the same meaning such as writing variations are unified into one word. Stop words are words that are excluded from processing for reasons such as not being usable in natural language processing. Examples of stop words include those that do not have meaning alone, such as particles and auxiliary verbs among words. When calculating vectors, these may be removed and only meaningful words may be targeted. Vectorization may also be performed without removing these stop words. Vectorization is a process of converting a word, which is a character string, into a vector. By vectorization, word data is converted into numerical data. When converting a word into a vector, it is performed by a method called Bag of Words or distributed representation. Bag of Words is a method of vectorizing a text by using the number of occurrences of words that appear in the given text. Since it focuses on how many words appear in the text, the order of words and text is not considered. Distributed representation is a method of vectorizing by focusing on the meaning of a word. By vectorizing the meaning of a word, it is possible to give vectors close to words with similar meanings and usage, and the relationship between words can also be expressed by vectors. By expressing in vectors, addition and subtraction of the meanings of words are possible. The application process can utilize the natural language converted into numerical data as input for machine learning. Specifically, the vectorized natural language is input into a classifier to perform text classification.Tools utilized here include "TensorFlow", "scikit-learn", "PyTorch", etc.

[0043] Disclose the state where there are at least two or more users. In at least one embodiment, users include general consumers and traders. Users use user terminals or computers.

[0044] Disclose for each user. In at least one embodiment, the device performs a predetermined operation for each user. Stores data for each user.

[0045] Disclose an embodiment of obtaining information regarding the words and deeds of users on at least two or more days. In at least one embodiment, the words and deeds of users include the language activities of users. Language activities include all intellectual activities carried out through languages such as "speaking", "listening", "writing", and "reading". It includes not only simply performing these actions, but also languages for solving problems, languages necessary for social life, activities of organizing and communicating one's own thoughts rather than simply transmitting information, languages for deeper understanding of the learning content of each subject, etc. Language activities reflect not only the acquisition of knowledge, but also important abilities such as thinking ability, judgment ability, and expression ability for surviving in the future era. Information regarding the words and deeds of users includes data of the language activities of users. As an example, it includes character data of the user's language and attached data such as the category of emotions inferred from the facial muscles when the user speaks. It includes data obtained by converting the user's language activities into a form that can be processed by the device. The method of data conversion includes obtaining the user's voice and performing speech-to-text conversion if it is the user's language. In addition, when the user's language is already posted on the user's SNS, it includes obtaining that data. In addition, it includes a method of obtaining the user's expression with a video acquisition device and asking an AI that has performed supervised learning on human expressions to determine what emotion the user's expression reflects and assign a category (including categories such as joy, anger, sorrow, and happiness).

[0046] An embodiment is disclosed in which, based on the information, the AI is required to perform supervised learning. In at least one embodiment, the information includes information regarding the user's speech and actions. The device requests the AI to perform supervised learning with information regarding the user's speech and actions. The AI includes a natural language processing model. The AI is further fine-tuned with information regarding the user's speech and actions. By this method, the AI can perform text classification, generation, sentiment analysis, text summarization, and question answering that reflect the user's features and characteristics. As an example, the AI learns words and sentence flows specific to the user from information regarding the user's language. As already described, when given a sentence, the AI guesses the next word from the sentence up to that point, creating a large number of supervised learning problems. As a result, an AI that can guess the next word based on the user's features can be created. The generative AI can predict the grammatical structure, the connection of topics, and that a person with such a writing style would write such a sentence. In at least one embodiment, the device performs supervised learning for each user. That is, the device changes the information regarding the speech and actions of the user for whom supervised learning should be performed for each user. The AI can predict that if it is user A, they would write such a sentence, and if it is user B, they would write such a sentence.

[0047] An embodiment is disclosed in which the learning data is stored separately. In at least one embodiment, the device stores the learning data of the AI separately. For example, the learning data regarding user A and the learning data regarding user B are stored separately. According to this embodiment, there is the convenience and industrial applicability that at least the personality of the AI can be preserved for each user, and the learning results of that personality can be accumulated.

[0048] Disclosed is an embodiment that requires AI to predict the behavior of a user corresponding to a certain task based on specified learning data. In at least one embodiment, the device obtains information about the task. The task includes tasks that can be responded to as language activities. As an example, a question can be mentioned. For example, it includes an abstract question such as "What do you think about the global warming problem?" In addition, it also includes a specific question such as "The sales of Company A are X billion yen, and it has products such as X1 and X2... Should it sell product X3?", accompanied by specific data that is a prerequisite for the question. Regarding these tasks, the user can create the task in the information regarding the user's behavior. In addition, a person other than the user can also create the task. The content of the task can be any content. It can be a task that only the user knows, or it can be a general task. The device requires AI to predict the behavior of a user corresponding to a certain task based on the specified learning data. The AI predicts the behavior of the user regarding the task based on the stored learning data. For example, based on an abstract question such as "What do you think about the global warming problem?", the AI makes predictions about the grammar structure, the connection of topics, and the sentences that a person with such a writing style is likely to write. For example, based on the learning data of User A, the AI can generate a speculative sentence such as "Regarding global warming, it is necessary to take measures such as X1 and X2...". Based on the learning data of User B, it may generate a speculative sentence such as "Global warming has no scientific basis, so there is no need to take measures."

[0049] According to this embodiment, there are at least the following conveniences and industrial applicability. It is possible to save the same personality of oneself in a device. It is possible to scan past SNSs to find the user's thoughts. It is possible to answer questions (which may be synonymous with questions) to select the basis of the user's thoughts and create a cloned AI of the user. In the process, it is possible to extract the characteristic quantities of the user's personality. It is possible to rent consulting or the thought AI of a famous company president to assist in life and management. If the user is a designer, a famous manager, etc., the AI related to that user can be made to participate in an in-company meeting and give proposals for issues. It helps with consulting and company management.

[0050] Information regarding the user's words and deeds is disclosed for a device that is the user's SNS posting data. In at least one embodiment, the device refers to the user's SNS posting data. The device obtains proof information proving that the user has given permission. The user generates permission information permitting the AI to learn the posting data related to the SNS account owned by the user. As an example, an application implementing part or all of this embodiment performs user authentication and confirms that the user has permitted the AI to learn the posting data related to the SNS account owned by the user. The confirmation methods include the method of the user inputting the password of that SNS account, the authentication method linked with that SNS (including, as an example, inputting the password or biometric information in a Google (registered trademark) account), and combinations thereof. When the device obtains proof information proving that the user has permitted the AI to learn the posting data related to the SNS account owned by the user, the device requests the AI to learn based on the posting data of the user's SNS. According to this embodiment, there are the convenience and industrial applicability of preventing the posting data of the user's SNS from being used for learning in at least a form not desired by the user.

[0051] Disclosed is an apparatus that acquires a user's voice or image, requests an AI to converse with the user or ask the user questions, and uses the information regarding the conversation or questions as information regarding the user's actions. In at least one embodiment, the apparatus has voice acquisition means or image acquisition means. As an example, these may be provided in a user terminal. As an example, it includes a microphone or a camera of a smartphone or a tablet terminal as the user terminal. Separate devices may be made communicable with the apparatus. The apparatus requests an AI capable of natural language processing to converse with the user or ask the user questions. The apparatus stores initial question information to be asked initially and asks the user the information initially. Such question information is determined by the business operator providing the application that implements part or all of the present embodiment. Alternatively, it may be arbitrarily determined by the user. The AI converses with or asks the user based on the initial question information. Regarding this method, the conversation or question content is displayed in characters on the user terminal or output in voice. The AI further converses or asks questions based on the user's answer obtained from the user terminal (including the method of inputting in characters or the method of analyzing the content input in voice and converting it into characters). The AI continues the questions and conversation based on the input information of the user's answer. Regarding the questions and conversation, the question information to be asked is determined by the business operator providing the application that implements part or all of the present embodiment. The apparatus uses the information regarding the conversation or questions as information regarding the user's actions. According to the present embodiment, there are the advantages and industrial applicability that at least the user's characteristics can be efficiently acquired, or the user's characteristics that cannot be understood from SNS posts can be acquired.

[0052] Disclosed is an apparatus that obtains proof information proving that a user has been authenticated and provides the proof information or information related to the proof information to learning data corresponding to the user. In at least one embodiment, the user generates proof information proving that the user has been authenticated for predicting the behavior of the corresponding user for a certain task based on the learning data or the learning data. Authentication includes authenticating that the user reflects the characteristics of the user with respect to an AI that predicts the behavior of the user for a certain task based on the learning data or the learning data based on the user. For example, the user refers to the learning data of the user or examines the generated content of the AI based on the learning data through an application that implements part or all of the present embodiment, and determines whether they reflect the characteristics of the user. For example, User A is User A Look at the text generated by the AI with user-based learning data and determine whether it resembles oneself or not. When the user believes that the AI reflects the characteristics of the user, the user provides proof information. The proof information includes information such as the fact that the user has authenticated, that it is okay to use the learning data, the similarity of the user, and combinations of these. The similarity of the user is input by the user. For example, an AI that is 80% similar, an AI that is 40% similar, an AI that is not very similar, etc. The way of expression can be set arbitrarily. The device presents to the user an AI that predicts the user's behavior regarding a task based on user-based learning data or learning data, and the user authenticates the AI that predicts the user's behavior regarding a task based on the learning data or learning data. The device obtains proof information proving that the authentication has been done. For example, the proof information includes proof information based on an electronic signature, the input of a predetermined password, biometric authentication, and other available proof methods. The information regarding the proof information includes information such as the date of proof, the mode of proof (electronic signature, biometric authentication, etc.), the similarity of the AI, and combinations of one or more of these. The device gives the proof information or information regarding the proof information to the learning data corresponding to the user. For example, it includes associating and storing proof information and the like with the learning data, or attaching a timestamp to prove that the proof information has not been tampered with. According to this embodiment, it is determined whether the user has authenticated regarding at least the learning data of a certain user or the AI based on the learning data. By this, there are the conveniences and industrial applicability that the detectability of unauthorized use of the user's learning data is improved, or the credibility of the learning data and the AI based on it is improved.

[0053] Disclosed is an apparatus that displays, on a screen, content related to learning data to which proof information or information related to proof information is added, and displays authentication-related graphics on the display screen. In at least one embodiment, when operating AI, the apparatus checks whether the learning data has proof information or information related to proof information. If any of these exist, the apparatus displays authentication-related graphics on the display screen of the content related to the learning data or the user who uses the AI based on the learning data. The user referred to here includes not only the user on whom the learning data is based, but also general consumers or traders who use the learning data or the AI. The display screen includes the display screen of the user terminal when these users access the learning data, view it, or use the AI based on the learning data. The authentication-related graphics include information indicating that the user has been authenticated, proof information, information related to domain name information, the similarity of the user, and information of one or more combinations thereof. This includes the method of indicating this information in characters or displaying predetermined graphics corresponding to this information. The apparatus stores the information of these graphics and, when meeting the above conditions, displays the corresponding graphics. For example, when using the AI of User A, who has proof information authenticated by User A, on the display screen of the user terminal using it, graphics such as "Authenticated", "Proven", or a stamp indicating these are displayed. Of course, these are merely examples. In at least one embodiment, any display that can somehow specify that User A has been authenticated is determined to fall within the category of "authentication-related graphics". According to this embodiment, there are advantages and industrial applicability in that at least the detectability of unauthorized use of the user's learning data is improved, or the credibility of the learning data and the AI based on it is improved.

[0054] An apparatus is disclosed that requests an AI to predict the actions and speech of two or more users based on the learning data, and requests the AI to have the two or more users converse with each other about a certain task. In at least one embodiment, the apparatus stores two or more learning data for each user. The apparatus requests the AI to predict, for each user, the actions and speech of the corresponding user about a certain task based on the two or more learning data. The apparatus requests the AI to have the AIs based on the two or more users converse with each other about a certain task. The apparatus stores initial question information and asks the AI based on any of the users about the information initially. Such question information is determined by the business operator providing the application that implements part or all of this embodiment. Alternatively, it is arbitrarily determined by the user. For example, the AI is asked based on User A, and the AI predicts the actions and speech of User A, and the apparatus obtains the predicted language. Next, based on that language, the AI predicts the language of User B and obtains the predicted language. Furthermore, based on that language, the AI predicts the actions and speech of User A. By repeating this, the AI causes the AIs based on two or more personalities to converse or discuss. According to this embodiment, there is the convenience and industrial applicability that excellent ideas or judgments can be automatically generated by having the AIs based on at least two or more excellent users converse with each other.

[0055] The following discloses an overview of the embodiment described above.

[0056] In a state where at least two or more users exist, for each user, obtain information on the actions and speech of the user on at least two or more days, request the AI to perform supervised learning based on the information, store the learning data, request the AI to predict the actions and speech of the corresponding user about a certain task based on the specified learning data, Apparatus.

[0057] The apparatus described above, Information regarding the user's actions is the user's SNS post data. Device.

[0058] The above device, acquires the user's voice or image, requests the AI to converse with the user or ask the user questions, and uses the information regarding the conversation or question as information regarding the user's actions. Device.

[0059] The above device, acquires proof information proving that the user has been authenticated, and gives the proof information or information regarding the proof information to the learning data corresponding to the user. Device.

[0060] The above device, acquires proof information proving that the user has been authenticated, gives the proof information or information regarding the proof information to the learning data corresponding to the user, and when displaying the content related to the learning data or the AI based on the learning data to which the proof information or information regarding the proof information is attached on the screen, displays a graphic related to authentication on the display screen. Device.

[0061] Based on the above learning data, requests the AI to predict the actions of two or more users, and requests the AI to have the two or more users converse with each other about a certain issue. Device.

[0062] In at least one embodiment, the device according to any of the above, acquires the user's voice or image, and uses the information regarding the voice or image as information regarding the user's actions. Device.

[0063] In at least one embodiment, the device acquires the user's voice or image. The user speaks to the device on their own initiative without receiving a conversation or question from the AI. The device acquires the user's voice or image using voice acquisition means or image acquisition means. The device regards at least the information regarding the voice or image as information regarding the user's speech and actions. According to this embodiment, there is at least the convenience and industrial applicability that the user can spontaneously work to improve the accuracy and similarity of their AI.

[0064] In at least one embodiment, the information regarding the user's speech and actions is video or photo data owned by the user. The videos or photos owned by the user include, for example, video or photo data stored in the user's cloud. As an example, Google Photo (registered trademark) can be mentioned. Of course, this is just an example, and any form in which the data is stored may be acceptable as long as it is video or photo data owned by the user. As an example, the photo or video is one taken or created by the user. As an example, the photo or video may further include illustrations or graphics created by the user. The device acquires authentication data for authenticating that the user has accessed or used the video or photo. After acquiring the authentication data, the device requests the AI to perform supervised learning based on the video or photo. According to this embodiment, there is at least the convenience and industrial applicability that an AI based on data reflecting at least the user's preferences and characteristics can be provided. As a result of the inventor's earnest consideration, compared to the case of performing supervised learning only with the user's SNS posting data, it is possible to create an AI more similar to the user when performing supervised learning including the user's videos or photos, illustrations, and graphics. This configuration includes at least a novel point that has not been clearly disclosed in the past, and there is the convenience and industrial applicability that an AI or learning data more similar to the user can be created.

[0065] The invention according to the present disclosure only needs to be able to exhibit at least one of the above-described effects.

Claims

1. 1. A system comprising: The device, In a state where there are at least two users, for each user, Obtain information about the user's behavior for at least two or more days; Request the AI ​​to perform supervised learning based on that information, storing learning data obtained by the learning; Get information about the issue, Requesting the AI ​​to predict the user's corresponding behavior regarding the task based on the specified learning data; Present the learned data or the contents of the prediction to the user terminal; The user terminal: Generate proof information based on the fact that the learned data or the content of the prediction input from the user reflects the characteristics of the user or the similarity of the user; The device stores the learning data in association with the certification information, or assigns a timestamp to the certification information to prove that the certification information has not been tampered with; system.

2. 1. A system comprising: The device, For each user, we obtain information about the user's behavior. Request the AI ​​to perform supervised learning based on that information, storing learning data obtained by the learning; Get information about the issue, Requesting the AI ​​to predict the user's corresponding behavior regarding the task based on the specified learning data; Present the learned data or the contents of the prediction to the user terminal; The user terminal: Generate proof information based on the fact that the learned data or the content of the prediction input from the user reflects the characteristics of the user or the similarity of the user; The device stores the learning data in association with the certification information, or assigns a timestamp to the certification information to prove that the certification information has not been tampered with; system.

3. 3. A system according to claim 1 or 2, comprising: When the user device generates the credentials, The certification information includes information that the training data may be used. system.

4. 3. A system according to claim 1 or 2, comprising: When the user device generates the credentials, The authentication information may include an electronic signature, a password, biometric authentication, or a combination of one or more of these. system.

5. 3. A system according to claim 1 or 2, comprising: When the user device generates authentication information, The certification information includes the certification date, the mode of certification (including electronic signature or biometric authentication), the similarity of the AI, or a combination of one or more of these. system.

6. 3. A system according to claim 1 or 2, comprising: The apparatus further comprises: When displaying the contents related to the learning data to which the certification information has been added on the screen, a graphic related to the certification information is displayed on the display screen. system.

7. 3. A system according to claim 1 or 2, comprising: The apparatus further comprises: When displaying the content related to the learning data to which the certification information has been added on the screen, displaying the words "authenticated" or "certified" or a stamp graphic indicating these on the display screen; system.

8. A method comprising: The device, For each user, we obtain information about the user's behavior. Request the AI ​​to perform supervised learning based on that information, storing learning data obtained by the learning; Get information about the issue, Requesting the AI ​​to predict the user's corresponding behavior regarding the task based on the specified learning data; Present the learned data or the contents of the prediction to the user terminal; The user terminal: Generate proof information based on the fact that the learned data or the content of the prediction input from the user reflects the characteristics of the user or the similarity of the user; The device stores the learning data in association with the certification information, or assigns a timestamp to the certification information to prove that the certification information has not been tampered with; method.