KR20220113248A - System and method for providing virtual reality service based on artificial intelligence - Google Patents

Abstract

The present invention discloses a virtual reality service system. More specifically, the present invention relates to an artificial intelligence-based virtual reality service system and method for providing a service with a new concept which allows real people or pets, which existed before, to be met again at any time by implementing the real people or pets in a virtual space. According to an embodiment, attribute data is derived by collecting various types of raw data from which the characteristics of existed or existing objects such as people and animals can be extracted and classifying the raw data to be converted into data, a virtual object corresponding to a real object is created through machine learning and content based on communication with the real object is provided such that a user can experience a realistic experience as if the user is directly communicating with the person or pet and various application contents based on the same is provided to arouse the user's interest.

Description

SYSTEM AND METHOD FOR PROVIDING VIRTUAL REALITY SERVICE BASED ON ARTIFICIAL INTELLIGENCE

The present invention relates to a virtual reality service system, and in particular, real people or pets that existed before but are not currently are implemented in virtual space so that they can always meet again, and virtual space objects in everyday life in the real world. It relates to an artificial intelligence-based virtual reality service system and method that provides a service of a new concept that is applied closely to loosen the boundary.

In the light of human history, human beings are making infinite progress. History is the product of records and shows the development of technology through successive generations. Artificial intelligence technology, which is emerging recently, is also reaching the level of human intelligence.

For a long time, humans have been recorded in someone's writings, drawings, photos, and videos about the history of their lives, but they will not be able to actually meet them and experience the environment directly.

In particular, when a family member, close friend, friend, or pet that has been with you for a long time in your life suddenly dies, those who remain may have a hard time longing for the deceased.

To overcome this problem, Korean Patent Application Laid-Open No. 10-2021-0015977 uses data such as habits of the deceased who died at an early age and artificial intelligence, assuming that the deceased is currently alive, Disclosed is a device for implementing dialogue with a deceased person by implementing it so that a user can have a conversation with a virtual deceased as if the deceased is still alive.

According to the prior art described above, the voice of the deceased is received from the user terminal using the voice of the deceased that matches the voice of the deceased to the age of the user, and divided data is generated for generating divided data obtained by dividing the voice of the deceased into syllable units. Aging voice data obtained by aging the voice of the segmented data of the deceased according to the current age of the deceased when the deceased is alive with a machine learning algorithm using voice data according to the age of people as learning data is starting

However, according to this prior art, only limited words and images of the deceased are provided in a limited form, and there is a limitation that it is only an image for commemoration.

Recently, various virtual experience services such as visiting a virtual space that do not actually exist, such as virtual reality technology, augmented reality technology, etc., or meeting and interacting with a virtual person are being studied, and the present invention Based on this latest virtual reality technology, it enables communication with people and animals that do not exist but existed in the past, and performs activities necessary for daily life in the real world through objects that exist in virtual space. We want to implement a service that makes this possible.

Patent Publication No. 10-2021-0015977 (published date: February 10, 2021)

The present invention has been devised to overcome the above-mentioned limitations and provide a service of a new experience, and at the present time when artificial intelligence technology is developing day by day, it stores and converts humans into data, and converges with artificial intelligence technology to create someone forever in the future. There is a task to provide a new concept of service that allows you to feel and experience emotions in the memory of

In addition, the present invention is based on a database of various information about real entities such as people and animals that have existed or exist in the past or present, and based on data accumulated using artificial intelligence technology, the closest to the entity that exists in the past or present. It is possible to communicate with a virtual object that has been implemented in a well-implemented manner, and there is a problem in providing various and useful services in real life based on the communication.

In order to solve the above problems, the artificial intelligence-based virtual reality service system according to an embodiment of the present invention collects a plurality of raw data that can be converted into data extracted from a plurality of viewpoints with respect to an actual object that is a target of virtualization, A data center server that classifies and stores the collected raw data for each object according to data properties, and a virtual object corresponding to a real object using a plurality of property data for each object stored in the data center server at the request of a user terminal and a content providing server that provides content based on communication between a user and a virtual entity through the user terminal.

The data center server includes a data collection unit that collects raw data obtained directly or indirectly for an actual entity from one or more data collection terminals, an entity registration unit that registers a real entity to be converted into data from a user terminal, and the data collection unit The raw data collected by It may include a data classification unit for deriving attribute data by classifying it as archive data on achievements performed during the existence of an existing entity, and a data storage for storing the attribute data for each entity.

The data collection terminal may include a computing device possessed by an actual entity or including an image sensor or a microphone sensor capable of obtaining raw data for an actual entity, or a computing device capable of inputting text by another user.

The data center server, with respect to the property data of the registered real entity, in accordance with the request of the user terminal of the user who has the right to use the data or the user who has the permission from the user who has the right to use the property data, and The method may further include a data providing unit that provides attribute data online.

The content providing server includes a data transfer unit that receives one or more attribute data for a real entity registered from the data center server, and a virtual object that corresponds to the real entity by using the attribute data and implements a virtual entity that operates in a virtual space. An entity implementation unit, an entity action generating unit that sets an action of a running virtual entity according to attribute data of the virtual entity, a service determining unit that determines a provision form of a virtual entity according to a setting by a user, and the user terminal It may include a service providing unit that provides the content to the user terminal in response to a request of the user.

The content providing server includes a learning data DB that stores learning data extracted from a plurality of sample entities and learning data generated by modulating a certain part from publicly available attribute data stored in the data center server, and one or more predefined learning and a machine learning unit that performs machine learning by applying the learning data to a model, wherein the virtual object implementation unit and the object action generation unit apply the learning results derived from the machine learning unit to the virtual object implementation and virtual object action generation, respectively. can reflect

The virtual object may be displayed on the user terminal as any one or a combination of two or more of a VR image, an augmented image, a 2D image, and an audio.

The content providing server further includes a member management unit that performs a membership registration procedure according to a request of a user who has the right to use attribute data for an existing entity, and performs a login procedure of a registered user, wherein the data transfer unit , when requesting virtual object content from the user terminal, confirming the right to use the attribute data of the real object to the corresponding user, and requesting the data center server to provide the attribute data within the scope of the use right.

The content may provide at least one of a dialog function between a user and a virtual object in the user terminal, a schedule management function that displays a schedule notification on the user terminal at a time set by the user, and a game function between the user and the virtual object have.

In addition, the artificial intelligence-based virtual reality service method according to an embodiment of another aspect of the present invention for solving the above-mentioned problems, (a) a data center server is extracted from a plurality of viewpoints with respect to an actual entity that is a target of virtualization Collecting a plurality of raw data that can be converted into data, (b) the data center server classifies and stores the collected raw data for each object according to data properties, (c) the content providing server according to the request of the user terminal implementing a virtual object corresponding to an actual object using a plurality of attribute data for each object stored in the data center server; It may include providing content.

In the step (a), the data center server collects raw data obtained directly or indirectly about an actual entity from one or more data collection terminals, and the data center server is an object to be converted into data from a user terminal. and receiving the registration of, in step (b), the raw data collected by the data center server, external data indicating external disposition including appearance and words and behavior, and internal product including personality and habit of a real entity A step of deriving attribute data by classifying it into internal data describing the propensity, behavioral data on the behavior of the real entity, and archive data on the achievements performed during the existence of the real entity, and storing the attribute data for each entity may include.

The data collection terminal may include a computing device possessed by an actual entity or including an image sensor or a microphone sensor capable of obtaining raw data for an actual entity, or a computing device capable of inputting text by another user.

Prior to step (c), the data center server responds to a request from a user terminal of a user who has the right to use the data or another user who is permitted to use the property data of the registered entity from the user who has the right. Accordingly, the method may further include verifying the usage right and providing the attribute data online.

In the step (c), (c1) the content providing server receives one or more attribute data for a registered real entity from the data center server, (c2) the content providing server exists using the attribute data Implementing a virtual object corresponding to the object and operating in a virtual space, (c3) the content providing server setting the behavior of the running virtual object according to the attribute data of the virtual object, and (c4) providing the content The method may include determining, by the server, a form of providing the virtual object according to the setting by the user.

In the steps (c2) and (c3), the content providing server stores the learning data extracted from a plurality of sample entities and the learning data generated by modulating a certain part from the publicly available attribute data stored in the data center. , performing, by the content providing server, machine learning by applying the learning data to one or more predefined learning models, and reflecting the derived learning results by the content providing server to virtual object implementation and virtual object behavior generation may include steps.

The virtual object may be displayed on the user terminal as any one or a combination of two or more of a VR image, an augmented image, a 2D image, and an audio.

Prior to the step (c1), the content providing server further includes the step of performing a membership registration procedure according to a request of a user having the right to use attribute data for an existing entity, and performing a login procedure of the registered user and, in the step (c1), when the content providing server requests the virtual object content from the user terminal, confirming to the corresponding user the right to use the attribute data of the real object; and requesting the data center server to provide the attribute data.

The content may provide at least one of a dialog function between a user and a virtual object in the user terminal, a schedule management function that displays a schedule notification on the user terminal at a time set by the user, and a game function between the user and the virtual object have.

According to an embodiment of the present invention, various types of raw data capable of extracting characteristics of existing or existing entities, such as people and animals, are collected and classified so as to be data-enabled to derive attribute data, and real entities through machine learning By creating virtual objects corresponding to There is an effect that can arouse the interest of the user.

In addition, according to an embodiment of the present invention, information from various viewpoints such as appearance, conversation, and habits of influencers and public figures who want to provide experiential services as well as family or acquaintances that individuals want to remember are databased, and artificial By implementing the function as a virtual object in the virtual space by applying the technology, it is possible to provide various types of services derived from the virtual object, such as conversation with the virtual object, schedule management, and secretary, according to the request of the customer. .

1 is a diagram schematically showing the overall structure of an artificial intelligence-based virtual reality service system according to an embodiment of the present invention.
2 is a diagram showing the structure of a data center server of an artificial intelligence-based virtual reality service system according to an embodiment of the present invention.
3 is a diagram illustrating the structure of a content providing server of an artificial intelligence-based virtual reality service system according to an embodiment of the present invention.
4 is a diagram illustrating an AI-based virtual reality service method according to an embodiment of the present invention.
5 is a diagram illustrating an artificial intelligence-based virtual reality service method according to an embodiment of the present invention as a procedure between each component.
6 to 9 are diagrams illustrating screens provided in an artificial intelligence-based virtual reality service according to an embodiment of the present invention.

When a part "includes" or "includes" a certain component throughout the specification, this means that other components may be further included, rather than excluding other components, unless otherwise stated. In addition, terms such as "...unit" and "...system" described in the specification mean a unit that processes one or more functions or operations, which are hardware, software, or hardware and a combination of software.

Also, in this specification, the term "embodiment" is meant to serve as an illustration, example, or illustration, but the subject matter of the invention is not limited by such examples. Also, "comprising", "comprising", "having" and other similar terms are used, but when used in the claims, "comprising" is an open transition word that does not exclude any additional or other elements. It may be used generically in a manner similar to the term "Comprising".

The various techniques described herein may be implemented with hardware or software, or a combination of both, where appropriate. As used herein, terms such as "...Unit" and "...System" likewise refer to computer-related entities, i.e. hardware, a combination of hardware and software, software or execution. It can be treated as equivalent to the city's software. In addition, each function executed in the program of the present invention may be configured in a module unit, and may be recorded in one physical memory, or may be recorded while being dispersed between two or more memories and recording media.

In the following description, the term referring to "artificial intelligence-based virtual reality service system" of the present invention may be abbreviated as "virtual reality service system" or "system" for convenience of description.

Hereinafter, an artificial intelligence-based virtual reality service system and method according to an embodiment of the present invention will be described in detail with reference to the drawings.

1 is a diagram schematically showing the overall structure of an artificial intelligence-based virtual reality service system according to an embodiment of the present invention.

Referring to FIG. 1 , an artificial intelligence-based service system according to an embodiment of the present invention collects a plurality of raw data that can be converted into data extracted from a plurality of viewpoints with respect to an actual object that is a target of virtualization, and the collected raw data In response to a request from the data center server 100 and the user terminal 50 for classifying and storing the and may include a content providing server 200 that implements a virtual object that provides a virtual object and provides content based on communication between a user and the virtual object through the user terminal 50 .

The user terminal 50 implements not only acquaintances such as family, acquaintances, and friends that have existed before or currently exist through the system of the present invention, but also celebrities such as singers, actors, and comedians as virtual objects acting in virtual space. It is a terminal device that enables a user to communicate.

Here, the virtual object according to an embodiment of the present invention may include not only humans, but also pets and virtual entities (eg, dinosaurs, cartoon characters, etc.).

The user may register the user terminal 50 possessed or used by the user as a member in the content providing server 200 , and may request the content providing server 200 for content based on a virtual object with which he/she wants to communicate. The above-described virtual object may be implemented as a VR image, AR image, 2D or 3D image, or voice, and the user terminal 50 reproduces the VR image streamed from the content providing server 200 in real time to communicate with the user. can be implemented.

The user terminal 50 may be a computing device including at least one processing unit and a memory. Here, the processing unit may include, for example, a central processing unit (CPU), a graphic processing unit (GPU), a microprocessor, an Application Specific Integrated Circuit (ASIC), Field Programmable Gate Arrays (FPGA), etc., It may have a plurality of cores. The memory 1120 may be a volatile memory (eg, RAM, etc.), a non-volatile memory (eg, ROM, flash memory, etc.), or a combination thereof. In addition, the user terminal 50 may include additional storage. Storage includes, but is not limited to, magnetic storage, optical storage, and the like.

In addition, as the user terminal 50, a VR head mounted device equipped with a display capable of expressing depth information, a goggles-type AR device capable of displaying a virtual object by overlapping a real background, etc. may be used, and a known smart phone may be used. Alternatively, a tablet PC or the like may be used, and a plurality of devices may support each other to feel a virtual object or space as if they were real.

The data center server 100 is a server device operated in a data center that stores and manages attribute data, which is a source for realization of virtual objects, and may store overall characteristics and patterns of real people and pets as a database and store them. .

Such a data center server 100 may be built in a cloud manner, and may receive various raw data about an actual object to be converted into data through an information and communication network, classify and systematize it, and store it during the service period, and use the data It can be provided to users with privileges.

In particular, according to an embodiment of the present invention, the data center server 100 may provide attribute data for an existing entity stored according to a user's request to the content providing server 200 linked according to the agreement. Such attribute data is data classified by systematizing not only the appearance of the real entity, but also voice, conversational habits, intonation, habit, etc., and its actual behavior pattern and personality. These attribute data are virtual by the content providing server 200 . It can be used to create objects.

In detail, the AI-based virtual reality service system of the present invention can be reproduced using voice analysis technology, such as conversation habits, dialects and intonations, through their voice data forever even when humans or animals are born and die by using artificial intelligence technology. Voices may be implemented, and the data center server 100 may collect raw data for these voices.

This virtual reality service can be viewed as a kind of metabus service that provides augmented reality or mixed reality to users. Metaverse is a compound word of 'meta', meaning fictitious and abstract, and 'universe', meaning the real world, meaning a three-dimensional virtual world. Metaverse is a more advanced concept than the conventional virtual reality environment, and can provide an augmented reality environment in which virtual worlds such as the web and the Internet are absorbed into the real world.

In addition, with respect to various emotional expressions during conversation with a virtual object having an implemented voice, the data center server 100 may collect raw data obtained by scanning the real face of the real object with a 3D scanner technology, and if the real object In the case where it is difficult to 3D scan the face, such as a deceased person in the past, the recorded photograph of the subject is collected as raw data and can be used for 3D modeling data production by the content providing server 200 later.

As such scanning technology and 3D modeling technology are introduced, the system of the present invention can produce and rent clothes or accessories that the user's deceased family members, relatives, and friends usually wear through the 3D modeling service.

In addition, if the virtual object is a celebrity, it can be used to extract behavior data by recognizing the face of the real celebrity through face tracking technology and use it to implement the emotional expression of the virtual object, and exist through voice analysis technology. It is also possible to implement a virtual object having the same voice as that of a celebrity. In addition, the data center server 100 of the present invention provides content to be described later by databaseizing various habits such as daily habits, facial expressions, and gait of real people or animals. With artificial intelligence technology according to the learning of facial expressions or motion patterns by the server 200, the virtual object maintains the memories of the past alive, and also adds new memories through conversation with the user and data center server 100 ) by providing a record service as new raw data, it is possible to implement a service of living together in the space of a new virtual world in the metaverse era between users and subjects.

In particular, the data center server 100 according to an embodiment of the present invention can materialize a virtual object in two steps to realize a more natural person at the current level of technology when the above-described real person is converted into a database.

First, face information is obtained by taking a picture of the front of a target for which a virtual object is to be created.

Next, prepare the role of the person in question, take a picture of the person's dialogue, prepare an image of the actions that the speaker can take in a conversation situation such as mouth shape and facial expression as well as gestures, By applying it to modeling, it is possible to implement a dialogue between a user and a virtual object. In this case, the person in the band may prepare the learning data by recording the voice for implementing the conversation for 30 seconds or more.

In addition, the data center server 100 stores emotional data corresponding to various situations, and as the emotional data is wrapped in 3D modeling of a virtual object, more interactive content can be provided. In addition, an embodiment of the present invention According to an example, it is possible to provide a conversation content service with a virtual object for the user himself and not other people. This service implements a conversation between a user and his or her own clone (clone), and the user registers his/her memories and other memory information such as memories in the database center 100 in advance and virtual objects in the manner described above. can create

Here, when memory information is registered in the database center 100, a list of questions for expected questions and answers can be provided, converted into text, and stored, and relatives, friends, etc. appearing therein based on the user's memory information Conversations with others can be collected and reflected in conversations with clones.

In addition, according to an embodiment of the present invention, the above-described conversation service with the virtual object may be extended and provided to the level of an ancestor, such as one's own parent, great-grandfather, or the like.

The content providing server 200 is a service providing server device that implements a virtual object and provides various contents based on communication with the virtual object to the user terminal 50 , and according to the request of the user terminal 50 , a specific person , it is possible to create a virtual object corresponding to an animal, and provide content based thereon. Such content may be implemented in various genres such as simple conversation with virtual objects, schedule management, shopping with virtual objects, games, and the like, and may be provided to the user terminal 50 through an information communication network.

To this end, the content providing server 200 receives, from the agreed data sensor server 100, attribute data for a specific object requested by the user, and simulates the real object using the built-in artificial intelligence-based machine learning module. It is possible to create a virtual object that has a close, appearance, voice, and personality and takes action in a virtual space accordingly, and provides it as content in an appropriate form that can be reproduced in the user terminal 50 .

In particular, the content providing server 200 receives the celebrity modeling source stored from the data center server 100 in order to implement the appearance, such as the face, body shape, etc. of a virtual object for a celebrity, and extracts information about the skeleton and joints to create a polygon layer and map the texture on the polygon layer to create a 3D virtual object corresponding to the entertainer.

In addition, the present invention can be provided to the user through an algorithm that can imitate all actions of the subject using artificial intelligence deep learning technology based on such a database.

In addition, according to an embodiment of the present invention, the content providing server 200 is a voice synthesis AI engine deep learning technology, a conversation analysis technology with an interlocutor (user), and an analysis algorithm for a dialogue sentence with an AI virtual object, It enables the realization of emotional expression through facial expression changes and body movements.

In addition, the content providing server 200 records the voice of repeated daily conversations between the user and the virtual object in real time, converts the text information converted through a voice analysis algorithm into computer code, and encrypts it in the data center server 100 . so you can save it.

According to the above-described structure, the artificial intelligence-based virtual reality service system according to an embodiment of the present invention is the first time in human history that a person who existed in a virtual space without disappearing even if the existence of life dies is a virtual existence, but his appearance and voice, Using habits and various memories, they can exist forever even if they die, and can present a new business model for the world of the new metaverse where users can talk, sympathize, laugh, worry, and rejoice through meeting with users. have.

In other words, through a business service model that combines deep learning artificial intelligence technology that can implement conversations with humans, three-dimensional face scanning technology, expression recognition technology, and emotion recognition technology, it is possible to conceptually store and subordinate living things forever in virtual reality. can

In addition, the artificial intelligence-based virtual reality service system according to an embodiment of the present invention manages and operates data based on Internet cloud technology, and enables meeting and conversation with virtual creatures created based on this. In particular, in an encounter with a virtual creature, an interactive graphic engine linkage technology capable of real-time physical contact feedback can be used.

In addition, the user may set public or private rights in the data center server 100 for a family registered by the user, which is a real entity registered by the user, or a family registered by a relative, or may be set to be disclosed only to specific persons. Accordingly, it is possible to search for family members, relatives, friends, etc. through the database through the data center server, and then to proceed with the meeting in the form of a virtual object. In this case, the permission to use when registering the virtual object may be divided into public, private, and specific person public. To this end, the user can set the right for this meeting service after obtaining approval for the use of the portrait rights of a third party, such as an individual's family, companion animal, or a celebrity he or she likes.

In addition, according to an embodiment of the present invention, the system can also create the same environment as real living beings such as clothing, accessories, and furniture, and sometimes provide content that provides food, etc. to the virtual object through the virtual shopping solution category. can provide In this case, the virtual entity may wear the medical accessory received as a gift or eat the provided food.

In addition, through the virtual reality space, you can have a meeting with family members who are already dead or alive at any time. can be set to do so.

In addition, the service operator provides information to users according to service contract requirements such as disclosure and non-disclosure by integrating management and operation of data of virtual objects registered by individuals through the service of the present invention, and content provision by virtual objects. make it possible

On the other hand, according to an embodiment of the present invention, a person who is currently alive, a person who has died or is dying in the past, and a companion animal may be service targets, and through the construction of a database for this, the user can view their appearance in virtual reality at any time. Through artificial intelligence technology, more realistic communication can be realized.

In addition, a person, such as a specific celebrity, or a company holding such portrait rights or copyrights can generate revenue by providing a virtual person meeting service for celebrities through the B2B business model of the present invention. In detail, when registering a database related to virtual objects about famous celebrities or public figures in a data center or providing a virtual person meeting service as content, it is not private, but has full or partially permitted rights. It is possible to provide paid or free content in the form of a VR environment or mobile environment, etc., to fans around the world by accessing their favorite entertainers in a virtual space through a user terminal.

On the other hand, as an extension of the service of the present invention, a search function is provided on the network to find a registered friend or family member, and in a virtual space, each person tries to meet each other at a remote location through a virtual object reflecting their real face. content can be provided.

In addition, it is possible to provide a service for registering or deleting the family genealogy between blood relatives to the data center, and the operation cost for data storage and management in the data center can be paid in the form of a monthly fixed amount.

And, all databases can apply blockchain encryption distributed ledger storage, proof technology and KYC identity authentication security technology.

In particular, according to an embodiment of the present invention, the database may be tokenized according to the standard in an 'non-fungible token (NFT)' and recorded in connection with the blockchain mainnet.

Since NFT is based on a blockchain, all relevant information such as ownership of data is stored in the blockchain, so the owner of the data can be checked at any time, making it impossible to forge. In addition, while well-known virtual assets such as cryptocurrencies have equal conditions depending on the issuer, NFTs contain a separate unique recognition value and cannot be exchanged with each other. It should be managed and utilized in an irreplaceable form.

In addition, the blockchain mainnet can issue an NFT for the data when data about a virtual object is created, and record the NFT and metadata on the distributed ledger. The NFT applied to the embodiment of the present invention can correspond to Ethereum standards such as ERC-721 and ERC-1155, and the information about the generated NFT token is the It can be recorded on a distributed ledger.

In addition, at the time of the service contract of the present invention, the operator may provide a service of recording all databases for the restoration of a specific person by visiting the contractor or visiting the contractor's facility.

Hereinafter, a data center server of an artificial intelligence-based virtual reality service system according to an embodiment of the present invention will be described in detail with reference to the drawings.

2 is a diagram showing the structure of a data center server of an artificial intelligence-based virtual reality service system according to an embodiment of the present invention.

Referring to FIG. 2 , the data center server 100 of the artificial intelligence-based virtual reality service system according to an embodiment of the present invention is raw data directly or indirectly obtained from one or more data collection terminals 30 about an existing entity. The data collection unit 110 that collects the data, the object registration unit 120 that receives registration of a real object that is an object to be converted into data from the user terminal, and the raw data collected by the data collection unit 110, external tendency including appearance and behavior Attributes are classified into extrinsic data representing The data classification unit 130 for deriving data, the data storage 140 for storing attribute data for each entity, and the attribute data of the registered real entity, from a user who has the right to use data or from a user with permission In response to a request of a user terminal of another user who has been permitted to use, the data providing unit 150 may include a data providing unit 150 that confirms the right to use and provides attribute data online.

The data collection unit 110 may collect various raw data for an actual entity that is a target of database formation through various paths through an information and communication network. According to an embodiment of the present invention, the data center server 100 may collect features, patterns, etc. derived from various viewpoints with respect to an actual object that is a target of a virtual reality service, and store it as a database for each object.

The raw data collected by the data collection unit 110 may include external elements such as the appearance, appearance, and voice of an actual entity, internal elements such as personality and disposition, and the like, and can be used in various ways through online can be collected.

In particular, the data collection terminal 30 may include a computing device possessed by an actual entity or an image sensor or a microphone sensor capable of acquiring raw data for an actual entity, or a computing device capable of text input by another user. can

The object registration unit 120 may receive and register an actual object to be converted into data according to a request of a user who wants to use a service based on a virtual object through the system of the present invention.

Here, the user is limited to those who have the right to use information such as achievements, as well as the face and voice of the real object, and the object registration unit 120 performs the registration procedure after confirming these permissions when registering the real object, , when the registration procedure is completed, the data storage 140 may create an object table for the corresponding object.

The data classifying unit 130 may classify various raw data for a registered real entity collected from the data collecting unit 110 into predetermined pieces according to properties of the data. According to an embodiment of the present invention, in realizing a real object as a virtual object, the appearance displayed or output is determined by reflecting the appearance and voice, and the conversation method and behavior by reflecting the personality, habit, and attitude in the virtual object etc. will be decided.

To this end, the data classification unit 130 classifies the raw data for each existing entity according to its properties and stores it in the data storage 140 , and externally recognizable data such as appearance and voice are external data (D1). Data on personality, emotion, attitude, etc. can be classified as internal data (D2). In addition, data on the behavior, gait, eating habits, etc. of an actual entity can be classified as behavioral data (D3), and data on the occupation, academic background, and biography of an actual entity can be classified as archive data (D4). can

The data storage 140 may store the data classified by the data classifier 130 as attribute data in the entity tables 141 and 142 defined for each entity. An independent table for each registered entity may be formed and allocated, and classified attribute data is sequentially stored in the entity tables 141 and 142 . As described above, a storage space for accumulating at least the external data D1, the internal data D2, the behavior data D3, and the archive data D4 may be allocated to each of the entity tables 141 and 142 as described above. Data of other classifications for implementing the virtual object may be further stored.

The data providing unit 150 may receive a request for the attribute data for each entity stored in the data storage 140 according to the request of the agreed content providing server 200 , and extract and reply from the data storage 140 .

According to an embodiment of the present invention, the data center server 100 may provide the stored attribute data for each object to the content providing server 200 for a virtual reality service. The content providing server 200 may request attribute data for the corresponding object according to the request of the user having the authority, and the data providing unit 150 responds to the request to the user and the content providing server 200 of the object. It is possible to check whether the usage right for the data exists, search the object table for the corresponding object of the checked request, extract the requested attribute data, and transmit it to the content providing server 200 .

In addition, the data center server of the present invention is a server operated in a data center that stores and manages data about a plurality of existing or currently existing entities such as people and animals, and in addition to the content providing server 200 of the present invention, objects Accumulated data can be provided to universities, research institutes, etc. that require big data according to the characteristics of Of course, externally provided data may be provided only in a form in which the use of data has been approved in advance or in a form permitted by the relevant laws and regulations without personal approval, in a form in which personal information is masked and altered.

According to the above-described structure, the data center server 100 collects and manages data for providing a virtual reality service, and may provide it when necessary, and provides a virtual reality service using this attribute data with reference to the drawings below. The structure of the content providing server 200 will be described in detail.

Hereinafter, a content providing server of an artificial intelligence-based virtual reality service system according to an embodiment of the present invention will be described in detail with reference to the drawings.

3 is a diagram illustrating the structure of a content providing server of an artificial intelligence-based virtual reality service system according to an embodiment of the present invention.

Referring to FIG. 3 , the content providing server 200 of the artificial intelligence-based virtual reality service system according to the embodiment of the present invention includes a data transfer unit ( 210), the virtual object implementation unit 220 for realizing a virtual object that corresponds to a real object and is active in a virtual space using property data, and an object action that sets the behavior of a running virtual object according to the property data of the virtual object The generation unit 230 , the service determining unit 240 that determines a provision form of the virtual object according to the setting by the user, and the service providing content to the user terminal 50 according to the request of the user terminal 50 . The provision unit 250, the training data extracted from a plurality of sample entities, and the training data DB 260 for storing the training data generated by modulating a certain part from the publicly available attribute data stored in the data center server 100, and one or more A machine learning unit 270 that performs machine learning by applying learning data to a predefined learning model, performs a membership registration procedure at the request of a user who has the right to use attribute data for an existing object, and a registered user It may include a member management unit 280 for performing the login procedure and a member DB 285 for storing registered member information.

The data transfer unit 210 serves to request and receive a reply from the data sensor server 100 for attribute data about a person, animal, etc. according to the virtual reality service request of the user terminal 50 . The data transfer unit 210 may request data transfer for an object that is a service target stored in an external data center, and the data center server 100 may return attribute data of the object in response to a legitimate transfer request.

In particular, when a virtual object content request is received from the user terminal 50 , the data transfer unit 210 confirms the right to use the property data of the real object to the corresponding user, and sends the property data to the data center server 100 within the range of the usage right. will be asked to provide Attribute data may include sensitive personal information, so only users who have a legitimate right to use the attribute data can use the data in the virtual reality service, and the data transfer unit 210 is verification process will be performed.

The virtual object implementation unit 220 may implement the virtual object by using the provided object attribute data. The virtual object implementation unit 220 may materialize the appearance of the virtual object by performing 2D or 3D modeling using external data, which may be provided in a form displayable by the user terminal 50 .

Also, the virtual object implementation unit 220 may reflect the content of the conversation constructed using the internal data in a response to the user's utterance input during communication with the virtual object and the user.

In addition, the virtual object implementation unit 220 may reflect the action shown when the virtual object is output on the screen of the user terminal 50, which is determined using the action data, and the conversation topic determined using the archive data; Content, etc. can be reflected in the response.

Such a virtual object may be displayed on the user terminal 50 as any one or a combination of two or more of a VR image, an augmented image, a 2D image, and an audio, and may provide a real-time conversation function.

The object action generation unit 230 may generate action information on words, gestures, etc. of a virtual object in a virtual space displayed on the screen of the user terminal 50 and provide it to the virtual object implementation unit 220 .

The virtual object displayed on the user terminal 50 may not only respond to the user's utterance, but may also take an autonomous action, move freely in the virtual space, or move objects as well as facial expressions, hand gestures, and gestures. An action such as picking may be performed, and the virtual object implementation unit 220 may receive the action information provided in real time from the object action generator 230 and reflect it on the virtual object.

In particular, according to an embodiment of the present invention, the action of the virtual object may be determined according to the type of content set by the user. As an example, when the content is a conversation with the deceased, the virtual object may communicate with the user while standing or sitting on the screen, or may perform a conversational action while walking in a virtual space. In addition, the virtual space may be a space arbitrarily set by the system or a space in which a memory place with the deceased set by a user is reproduced virtually.

In addition, when the content is the celebrity's virtual assistant, the virtual object may store the schedule transmitted by the user through conversation, appear on the screen according to the schedule, and deliver the schedule content to the entertainer's voice.

As described above, the object action generating unit 230 generates action information of a virtual object appropriate to the user's intention according to the type of current content, so that the action performed by the virtual object during service is determined.

The above-described virtual object implementation unit 220 and object action generation unit 230 reflect the learning results derived from the machine learning unit 270 to be described later in virtual object implementation and virtual object action generation, respectively.

The service determiner 240 may determine a content type based on a virtual object according to a user's setting. As described above, the system according to an embodiment of the present invention may provide various contents based on communication with a virtual object. Such content provides at least one of a dialog function between a user and a virtual object in the user terminal 50, a schedule management function that displays a schedule notification on the user terminal at a time set by the user, and a game function between the user and the virtual object may be doing

In addition, as an example of the content provided by the virtual reality service of the present invention, when clothing is purchased in a virtual space through an in-app payment method, content for a virtual object to wear the clothing may be provided.

The service providing unit 250 is connected to the user terminal 50 through the information and communications network, receives attribute data for the corresponding virtual object from the data center according to the user's request to implement the virtual object, and also selects the type of content from the user. A virtual space is prepared to respond to the setting, and a virtual object appears to provide a virtual reality service to the user terminal 50 .

In the virtual reality service, the virtual object target and service range can be determined according to the user's member information, and the service providing unit 250 refers to the member information stored in the member DB 285 to check the target object and service range. and the content determined by the service determining unit 240 may be provided to the user terminal 50 . Such content may be provided in a real-time 2D or 3D video streaming method for its type, only the voice of a virtual object may be provided, and conversation contents may be provided in the form of text or SMS text.

The learning data DB 260 may store various learning data for machine learning that is reflected in the above-described modeling of the virtual object and generation of its behavior. According to an embodiment of the present invention, the learning data may be input and stored on the system operating side, or may be stored after being supplied from one or more data centers. Such learning data may be in the same format as each data of the attribute data, and may be used to learn the appearance, voice, behavior, etc. of the virtual object. In addition, the learning data DB 260 accumulates and stores the result of the conversation between the user and the virtual object as learning data so that it can be utilized for machine learning.

In particular, the learning data DB 260 may be stored in a storage space allocated for each real person corresponding to the virtual object, and the habits, facial expressions and gestures of the real person are learned through machine learning in advance in the user terminal 50 later. It allows you to implement animations that improvise actions for each situation rather than produced.

The machine learning unit 270 may use a plurality of learning data stored in the learning data DB 260 to model a virtual object, generate a response to a conversation, and generate an action.

The machine learning unit 270 may build a deep learning probabilistic inference model by using the learning data collected and stored in the learning data DB 260 . The model 205 constructed in this way is not fixed and completed, but when conversations and exchanges between a plurality of users and virtual objects are accumulated, it can be supplemented by receiving feedback from it and repeatedly learning it again.

In addition, the machine learning unit 270 according to an embodiment of the present invention may be based on a sequence-to-sequence framework and an encoder-decoder model in the case of dialogue. The S2S model can be composed of two Recurrent Neural Networks (RNNs), the first RNN splits a sentence into word units and encodes them into one vector, and the second RNN converts the encoded vector into one word. It may be a learning model of a method of decoding each and finally constructing one sentence.

In addition, in the case of response generation, the machine learning unit 270 may process the content of the user's utterance as a pre-trained word embedding model. This is an artificial neural network, which can be composed of two layers, converts the input speech content into text, receives it as an input, and finds a way to express the words of the text as a vector. Here, the value of the vector should be a value that well expresses the meaning or role of the word in the text, and the word is expressed as a vector in consideration of the meaning and context of the word. Such a word embedding model can be used as a preprocessing step of a deep neural network.

That is, the machine learning unit 270 may obtain a vector corresponding to a word for each word, and input the vector into a deep neural network to perform additional work or to determine a relationship such as word similarity.

Also, the machine learning unit 270 may obtain the similarity between words in order to understand the sentence. Word embedding is to find a vector value corresponding to each word so that similar words are located closer together.

On the other hand, if the amount of data is sufficient, word embedding can grasp the meaning of a word quite accurately. Using this, not only the meaning of a word but also the relationship between several words can be found. The word embedding model can be used to classify not only words but also larger units of sentences or documents. In addition, if sufficient data is given, it is also possible to infer a word that is predetermined as having a high similarity with respect to a specific word through machine learning of the learning data.

Also, the machine learning unit 270 may learn the meaning of a word by using a relationship between a word in an input sentence and an adjacent word through connection with a neural network used for deep learning. The target word can be predicted using the context created by the surrounding words, and words that can come around can be predicted based on a single word.

Also, according to an embodiment of the present invention, the machine learning unit 270 may present a visual conversation using camera image information about the speaker input from the user terminal 50 , that is, the user. In a conversation with a general virtual object, a number of dialogue pairs are presented, each sentence of the dialogue is decomposed into morpheme units, an appropriate vector is created from it, and a response is derived by grasping the meaning. Information according to the facial expression may be additionally provided to conduct a conversation, or may be reflected in the virtual object's own facial expression.

That is, the accuracy can be further improved by adding visual information as real-time input information of the user as well as learning data. Such visual information can be obtained by well-known facial recognition technology and facial expression recognition technology, and a conversation can be continued in consideration of the emotion according to the expression.

In addition, according to an embodiment of the present invention, the machine learning unit 270 re-establishes the 'relationship' between the user and the virtual object according to the accumulation of conversations and activities occurring between the user and the virtual object and applies the concept of growing the virtual object. can do.

As an example, as the user uses the service related to the exchange with the virtual object for a certain period of time or more, as data on conversations and actions is accumulated, the virtual object repeats the initially specified lines, expressions, and actions in each situation in the same way. Rather, it can be continuously updated to take appropriate actions for each user through machine learning based on data accumulation.

The member management unit 280 serves to store member information of the registered user, perform a login procedure of the user terminal 50, or set and authenticate user rights.

In particular, when a user registers as a member, the member management unit 280 registers a virtual object and performs a procedure of authenticating whether a user who wants to use content has the right to use attribute data for the virtual object, thereby using the virtual object thereafter. When the request of the user terminal 50 is requested, the transfer of the attribute data can be requested to the data transfer unit 210 only when the authority of the corresponding user is confirmed.

The member DB 285 may store member information of a user registered as a member in the system. The member information stored and managed by the content providing server 200 of the present invention may include the user's name, account name, password, and the identifier of the virtual object to which the user has the right to use, the login of the user terminal 50, When creating a virtual object and providing content, the user and the virtual object may be identified, and login or content provision may be approved.

According to the above-described structure, the content providing server 200 according to the embodiment of the present invention can provide various types of content based on communication between the user and the virtual object by the user terminal 50 .

Hereinafter, an artificial intelligence-based virtual reality service method according to an embodiment of the present invention will be described in detail with reference to the drawings.

4 is a diagram illustrating an AI-based virtual reality service method according to an embodiment of the present invention. In the following description, the execution subject of each step becomes the system of the present invention and its constituent parts, even if there is no separate description.

Referring to FIG. 4 , the AI-based virtual reality service method according to an embodiment of the present invention is an AI-based virtual reality service method, in which a data center server is extracted from a plurality of viewpoints with respect to an actual object to be virtualized. Collecting a plurality of raw data that can be converted into data (S100), the data center server classifying and storing the collected raw data for each object according to data properties (S110), the content providing server data according to the request of the user terminal A step of implementing a virtual object corresponding to an actual object by using a plurality of attribute data for each object stored in the center server (S120), and the content providing server provides content based on communication between the user and the virtual object through the user terminal It may include a step (S130) of doing.

In detail, in the step (S100) of the data center server collecting a plurality of raw data that can be converted into data extracted from a plurality of viewpoints with respect to an actual object targeted for virtualization, the data center negotiated with the system operating side of the present invention Collects raw data about registered real objects from data center servers operated by .

Here, when the real object is a human, the raw data may be collected in a direct manner from a data collection terminal including a smart phone possessed by the real object or a sensor installed around the real object, or data possessed by people around the real object Raw data may be collected in a way that is indirectly input through a collection terminal.

Also, when the real object is a pet, the owner who registered the real object may collect raw data from his/her smartphone or the like.

Next, in the data center server classifying and storing the collected raw data for each object according to the data properties ( S110 ), the data center classifies various raw data of the corresponding real object for each object according to the properties of the data. The raw data may include not only data on the appearance, such as an appearance, voice, etc., of a corresponding real entity, but also data such as personality and habits input by people around. The data center server classifies each data according to the properties of the data and accumulates and stores each object to build the data center.

Next, in the step (S120) of the content providing server implementing a virtual object corresponding to the real object by using a plurality of attribute data for each object stored in the data center server according to the request of the user terminal, first, the content providing server is connected to the system Upon receipt of a request for a virtual reality service for a registered real object from a user terminal, the authority of the user who requested the service is checked, the real object is identified, and attribute data of the real object is requested from the data center server.

Accordingly, when the data center server provides the attribute data of the real object, the content providing server creates a virtual object for the real object in response to the attribute data and provides it to the user terminal.

And, in the step (S130) of the content providing server providing the content based on the communication between the user and the virtual object through the user terminal, the content providing server implements the virtual object using a plurality of attribute data transferred, and the user According to the set content type, content including virtual objects is provided.

Hereinafter, the technical idea of the present invention will be described in detail with reference to the drawings showing the flow of procedures between each component constituting the artificial intelligence-based virtual reality service system according to an embodiment of the present invention.

5 is a diagram illustrating an artificial intelligence-based virtual reality service method according to an embodiment of the present invention as a procedure between each component.

Referring to FIG. 5 , according to the artificial intelligence-based virtual reality service method according to an embodiment of the present invention, first, with respect to a real object to be implemented as a virtual object, the data collection terminal 30 provides raw data from various viewpoints. , and provides the sensed data to the data center server 100 (S200).

Then, the data center server 100 stores the collected raw data in the storage for each object (S210). At this time, the stored raw data is classified according to properties and divided and stored in an object table.

Thereafter, the user may access the content providing server 200 using his/her user terminal 50 , perform a member registration procedure, and request a virtual reality service based on the registered entity ( S220 ). Here, the registered entity may be a family member, a relative, a friend directly related to the user, or a pet. Or, depending on the type of service, it may be a celebrity such as a singer or an actor. If it is related to a real object such as a family member, the user must register the real object in the data center server 100 in advance. The service becomes available only after setting the registration of the virtual object and granting the user the right to use the virtual object.

Next, when the user's right to use the real object is normally confirmed, the content providing server 200 requests the data center server 100 to provide attribute data for the real object (S240).

Accordingly, the data center server 100 checks the usage right for the data of the real object of the user who requested the service (S250), searches the object table for the real object for which the confirmation is completed, extracts attribute data, and provides the content server It replies to (200) (S260).

Next, the content providing server 200 to which the attribute data of the real object has been transferred creates a virtual object in the virtual space corresponding to the real object by using the attribute data (S270). The reproducibility of such a virtual object may be improved based on machine learning, and more natural communication with the user is possible by determining the appearance and voice of the virtual object, as well as conversation contents and behavior.

When the virtual object is created, the content providing server 200 provides virtual reality content based on the virtual object to the user terminal 50 according to the type of content set by the user. Such virtual reality content may be reproduced in the user terminal 50 in the form of VR, AR, or general image, and may be content capable of communication by outputting a response in response to the user's utterance.

Hereinafter, the form of content provided by the system of the present invention will be described in detail through an example of a screen provided in an AI-based virtual reality service according to an embodiment of the present invention with reference to the drawings.

6 to 9 are diagrams illustrating screens provided in an artificial intelligence-based virtual reality service according to an embodiment of the present invention.

Referring to FIG. 6 , the artificial intelligence-based virtual reality service according to an embodiment of the present invention implements a person, animal, etc. that currently exist or exist in the past as virtual objects in a virtual space, and is based on communication with the user. It is characterized in that it is possible to perform a conversation while watching the appearance of a virtual object in HMD, AR glasses, etc., as well as TV, PC, etc., with such content.

Here, the real and virtual objects may be not only the user's acquaintances, but also entertainers, historical figures, and the like. In particular, according to an embodiment of the present invention, as the 3D appearance and voice of the virtual object modeled using the appearance data, as well as the tone, personality, and habits of the virtual object are reflected in the words and actions of the virtual object, the user can meet the real deceased. You can have an experience like

If the virtual object is a deceased person who has been close to the user, the user can experience conversations with the person who is not currently available to meet again in the virtual space and ask for their regards.

In addition, if the virtual entity is an existing or previously existing singer, the user can meet directly with his/her favorite singer and have a one-on-one conversation, and watch a virtual concert featuring the singer.

In addition, if the virtual entity is a historical great who existed in the past, you can talk about his achievements at the virtual ruins with the era and background of his existence, and experience the same as hearing the explanation of specific facts directly from the person concerned. can

In particular, in the virtual reality service according to an embodiment of the present invention, when a tangible terminal such as VR or AR is used as a user terminal, the user may experience a more realistic situation.

Referring to FIG. 7 , the virtual reality service according to an embodiment of the present invention can implement a conversation based on an actual memory or event in the past by archive data applied to the implemented virtual object in communication with the virtual object. have. The system can receive the history that actually occurred through the data collection terminal and implement the actual event between the user and the real object through conversation with the virtual object.

A user can inquire about a point in the past included in the historical data provided in advance during a conversation, and the virtual object can respond to events that occurred at that point in time extracted from the system in the form of a conversation.

Accordingly, in the virtual reality service of the present invention, when the virtual object is an acquaintance of the user and the user is currently deceased, the user may recall memories of the user and the acquaintance in the past and experience a conversation as in daily life based on the present time. In this case, the virtual object may perform facial expressions, speech tones, habits, and actions implemented by artificial intelligence.

Referring to FIG. 8 , the virtual reality service according to the embodiment of the present invention is available not only in virtual reality-only devices such as VR and AR, but also in mobile devices such as smartphones owned by anyone, and not only daily conversation content, You can use the virtual assistant contents, which is a schedule management function.

For example, when a user selects a schedule management content that uses a celebrity registered for his or her favorite service as a virtual object as virtual assistant content, and inputs and stores schedules such as to-dos, reminders, and anniversaries by date in the smartphone, When a virtual object with the appearance of a celebrity appears on the screen at that time to inform the schedule, or when a user asks a virtual object on the screen for a schedule at a specific point in time, the record stored in the virtual object is extracted and responded with the celebrity's voice will do

In addition, according to an embodiment of the present invention, various communication with virtual objects is possible in the real world, and natural communication that can occur frequently in daily life as well as virtual assistant contents by the aforementioned virtual objects can be implemented.

In detail, as conversational content according to various topics, quiz content in fields such as comics, common sense, science and technology, commercialized external DB, as an example, information providing content based on Google and Wikipedia, etc. based on AI natural language Conversation with virtual objects can be provided.

In addition, as a shopping function, when a virtual object is requested in a conversational format, the virtual object may perform automatic log-in to a specific online shopping mall and product order on behalf of the user based on the user's log-in information.

In addition, as an extended dialog function, when a user delivers an anecdote at a specific point in time in the past to the virtual object in the form of a conversation, the virtual object can store the content as private information in the database, and later in the life memory vault service. can be utilized.

In addition, the above-described memory storage function can be applied to various useful services. For example, it can be extended to the contents of my life memory that allows you to look back on the memory of a specific point in time at any time, and important information storage contents that store important information such as wills and passwords.

At this time, since the above-described private information and important information have the highest security level, security technologies such as biometric data verification may be applied, and access rights of parents, children, etc. may be set by the user. For reference, the virtual reality service according to an embodiment of the present invention may provide content in the form of a game played with a virtual object. A user can use his/her smartphone to run a virtual object and use game content that progresses with the user in a virtual space.

As an example, the user may execute a chess game in which the user competes with the virtual object, and the virtual object may enjoy the game together with the user as an opponent. When the game content is executed, a chessboard on which chess pieces are placed may be displayed on the screen together with the virtual object, and the user may enjoy playing chess when facing the virtual object. Here, the chess pieces can be moved through an input to the user's touch panel, and the user and the virtual object can enjoy the chess game by moving the chess pieces when their turns return, respectively. In particular, as game content, such as chess, proceeds when the user faces the virtual object, the user can enjoy the chess game as if he or she is with the other party, rather than playing the game alone. In this case, the virtual object may perform actions such as facial expressions, hand gestures, and gestures corresponding to the situation in which the game is currently being played according to the set personality, habits, etc., which may be reflected and displayed in real time on the user terminal.

In addition, although not shown, the virtual reality service according to an embodiment of the present invention may provide various contents for interaction with a virtual object in a virtual space.

As an example, shopping malls, restaurants, cafes, etc. exist in the real world on the virtual space in which the virtual object appears, and the user selects a shopping mall in the virtual space, purchases virtual clothes, accessories, etc. may be

Here, the payment method set in the user terminal may be used for payment of the product, and when the payment is completed, the system pays the corresponding product to the virtual object, and the virtual object may wear or use the graphically processed product.

In addition, as a useful function, it is possible to provide a navigation service that provides a virtual map for driving by receiving a destination from a user in a conversational format through interworking with a navigation solution.

In addition, although not described above, the system may provide content for various types of interactive implementation between a user and a virtual object.

Although many matters are specifically described in the above description, these should be construed as examples of preferred embodiments rather than limiting the scope of the invention. Therefore, the invention should not be defined by the described embodiments, but should be defined by the claims and equivalents to the claims.

30: data collection terminal 50: user terminal
100: data center server 110: data collection unit
120: entity register 130: data classification unit
140: data store 141: data table
150: data storage 200: content providing server
210: data transfer unit 220: virtual object implementation unit
230: entity action generating unit 240: service determining unit
250: service provider 260: learning data DB
270: machine learning unit 280: member management unit
285: Member DB

Claims (18)

a data center server that collects a plurality of raw data that can be converted into data extracted from a plurality of viewpoints with respect to an actual object that is a target of virtualization, and classifies and stores the collected raw data for each object according to data properties; and
At the request of the user terminal, a virtual object corresponding to the real object is implemented using a plurality of attribute data for each object stored in the data center server, and content based on communication between the user and the virtual object is provided through the user terminal content providing server
Artificial intelligence-based virtual reality service system that includes. The method of claim 1,
The data center server,
a data collection unit that collects raw data directly or indirectly about an actual entity from one or more data collection terminals;
an entity registration unit receiving registration of a real entity, which is an object to be converted into data, from a user terminal;
The raw data collected by the data collection unit includes external data indicating an external tendency including appearance and words and behavior, internal data describing an internal tendency including the personality and habits of an actual entity, and behavior of an actual entity. a data classification unit for deriving attribute data by classifying behavior data and archive data on achievements performed during the existence of an actual entity; and
A data storage that stores the attribute data for each object
Artificial intelligence-based virtual reality service system that includes. 3. The method of claim 2,
The data collection terminal,
An artificial intelligence-based virtual reality service system including a computing device possessed by a real object or a computing device including an image sensor or a microphone sensor capable of acquiring raw data for a real object, or a computing device capable of inputting text by another user. 3. The method of claim 2,
The data center server,
With respect to the property data of a registered real entity, according to the request of the user terminal of the user who has the right to use the data or the user who has the right to use the user, the right to use is checked and the property data is transmitted online. data provider to provide
Artificial intelligence-based virtual reality service system further comprising a. The method of claim 1,
The content providing server,
a data transfer unit receiving one or more attribute data of a registered entity from the data center server;
a virtual object implementation unit that implements a virtual object that corresponds to a real object and is active in a virtual space by using the attribute data;
an object action generating unit configured to set an action of a running virtual object according to the property data of the virtual object;
a service determining unit that determines a form of providing a virtual object according to a setting by a user; and
A service providing unit that provides the content to the user terminal according to the request of the user terminal
Artificial intelligence-based virtual reality service system that includes. 6. The method of claim 5,
The content providing server,
a learning data DB for storing learning data extracted from a plurality of sample entities and learning data generated by modulating a certain part from publicly available attribute data stored in the data center server; and
A machine learning unit for performing machine learning by applying the learning data to one or more predefined learning models,
The virtual object implementation unit and the object action generation unit,
An artificial intelligence-based virtual reality service system that reflects the learning results derived from the machine learning unit in realizing virtual objects and generating virtual object actions, respectively. 6. The method of claim 5,
The virtual object is
VR image, augmented image, 2D image and audio, any one or a combination of two or more will be displayed on the user terminal, artificial intelligence-based virtual reality service system. 6. The method of claim 5,
The content providing server,
Further comprising a member management unit that performs a membership registration procedure according to a request of a user who has the right to use attribute data for an existing entity, and performs a login procedure of a registered user,
The data transfer unit,
When a virtual object content is requested from the user terminal, the user confirms the right to use the attribute data of the real object, and requests the data center server to provide the attribute data within the scope of the use permission, artificial intelligence-based virtual reality service system. 6. The method of claim 5,
The content is
Artificial intelligence-based, which provides at least one of a dialog function between a user and a virtual object in the user terminal, a schedule management function that displays a schedule notification on the user terminal at a time set by the user, and a game function between the user and the virtual object Virtual reality service system. As an artificial intelligence-based virtual reality service method,
(a) collecting, by a data center server, a plurality of raw data that can be converted into data extracted from a plurality of viewpoints with respect to an actual object that is a target of virtualization;
(b) classifying and storing, by the data center server, the collected raw data for each object according to data properties;
(c) implementing, by the content providing server, a virtual object corresponding to a real object by using a plurality of attribute data for each object stored in the data center server according to a request of a user terminal; and
(d) providing, by the content providing server, content based on communication between a user and a virtual entity through the user terminal
Artificial intelligence-based virtual reality service method comprising a. 11. The method of claim 10,
The step (a) may include: collecting, by the data center server, raw data obtained directly or indirectly about a real entity from one or more data collection terminals; and
Comprising the step of receiving, by the data center server, a real object that is a target to be converted into data from a user terminal,
Step (b) is,
The raw data collected by the data center server includes external data representing external tendencies including appearance and words and actions, internal data describing internal tendencies including personality and habits of real entities, and behaviors on behaviors of real entities deriving attribute data by classifying the data and archive data on achievements performed during the existence of the real entity; and
Storing the attribute data for each object
Artificial intelligence-based virtual reality service method comprising a. 12. The method of claim 11,
The data collection terminal,
An artificial intelligence-based virtual reality service method including a computing device possessed by a real entity or a computing device including an image sensor or a microphone sensor capable of acquiring raw data for a real entity, or a computing device capable of inputting text by another user. 13. The method of claim 12,
Before step (c),
With respect to the attribute data of the real entity registered by the data center server, according to the request of the user terminal of the user who has the right to use the data or the user who has the permission from the user who has the right, the use right is checked and the attribute Steps to provide data online
Artificial intelligence-based virtual reality service method further comprising a. 11. The method of claim 10,
Step (c) is,
(c1) receiving, by the content providing server, one or more attribute data for a registered entity from the data center server;
(c2) realizing, by the content providing server, a virtual object that corresponds to a real object and operates in a virtual space using the attribute data;
(c3) setting, by the content providing server, an action of the running virtual object according to the attribute data of the virtual object; and
(c4) determining, by the content providing server, the form of provision of the virtual object according to the setting by the user
Artificial intelligence-based virtual reality service system that includes. 15. The method of claim 14,
Steps (c2) and (c3) are,
storing, by the content providing server, learning data extracted from a plurality of sample entities and learning data generated by modulating a certain part from publicly available attribute data stored in the data center;
performing, by the content providing server, machine learning by applying the learning data to one or more predefined learning models; and
Reflecting, by the content providing server, the derived learning results in virtual object implementation and virtual object behavior creation, respectively
Artificial intelligence-based virtual reality service method comprising a. 15. The method of claim 14,
The virtual object is
VR image, augmented image, 2D image and audio, any one or a combination of two or more will be displayed on the user terminal, artificial intelligence-based virtual reality service method. 15. The method of claim 14,
Prior to step (c1), the content providing server further includes the step of performing a membership registration procedure according to a request of a user who has the right to use attribute data for an existing entity, and performing a login procedure of the registered user do,
The step (c1) is,
confirming, by the content providing server, the right to use the attribute data of the real object to the corresponding user when the virtual object content is requested from the user terminal; and
requesting, by the content providing server, to provide the attribute data to the data center server within the scope of usage rights
Artificial intelligence-based virtual reality service method comprising a. 15. The method of claim 14,
The content is
Artificial intelligence-based, which provides at least one of a dialog function between a user and a virtual object in the user terminal, a schedule management function that displays a schedule notification on the user terminal at a time set by the user, and a game function between the user and the virtual object Virtual reality service method.

Images