KR20230096805A - Metaverse lifelogging method and apparatus using artificial intelligence-based geo-tagging - Google Patents

Abstract

A metaverse lifelogging method and device using artificial intelligence-based geotagging are presented. In the metaverse lifelogging method using artificial intelligence-based geotagging implemented by a computer system according to an embodiment of the present invention, a point of interest that exists within a predetermined distance from meta information of a photo or video or location information identified through GPS Deriving a candidate list of (Point of Interest, POI); extracting at least one or more data of information collected from a device sensor, place-related information, and a past visit history of the user from the derived POI candidate list; and inputting the extracted data into a predictive model to select a place that the user is likely to visit as a visit place, and a lifelogging service may be provided based on the visit place.

Description

Metaverse lifelogging method and apparatus using artificial intelligence-based geotagging {METAVERSE LIFELOGGING METHOD AND APPARATUS USING ARTIFICIAL INTELLIGENCE-BASED GEO-TAGGING}

Embodiments of the present invention below relate to a metaverse lifelogging method and apparatus using geotagging, and more particularly, to a metaverse lifelogging method and apparatus using geotagging based on artificial intelligence.

Lifelogging is a service that automatically records all information that an individual sees, hears, meets, and feels while living, and can upload data to a website regardless of place and time. Lifelogging is a core and comprehensive technology from the viewpoint of building an integrated database (DB) related to a specific user in the era of big data, and is the ultimate goal of global SNS services such as Instagram, Facebook, and Twitter. Due to the limitations of human memory, a diary to record an individual's daily life is an analog form of lifelogging that has existed since the past, and lifelogging in the 21st century is evolving using digital technology.

On the other hand, real-time location information using a mobile device sensor has a limitation that only lifelogging from the start of service use is possible. In order to expand the collection of lifelogging data to the past prior to the point of service use, a technology that can utilize various records such as photos stored in the device is required.

Korean Patent Registration No. 10-1706371 describes a technology related to a mobile terminal and a server that performs such a lifelog service.

Korean Patent Registration No. 10-1706371

Embodiments of the present invention describe a metaverse lifelogging method and apparatus using artificial intelligence-based geotagging, and more specifically, record places visited by users using artificial intelligence-based geotagging, and users who have visited the same place Provides lifelogging technology that connects

Embodiments of the present invention use big data and geotagging to automatically tag visited places using meta information recorded in photos, thereby quickly generating lifelogging data and providing lifelogging information about the user's past visit history. It is to provide a metaverse lifelogging method and device using artificial intelligence-based geotagging that can expand the temporal range.

In addition, the embodiments of the present invention provide a metaverse service that connects hyperlocal communities in individual places based on lifelogging, thereby providing artificial intelligence-based geotagging that can form a strong bond based on emotional distance rather than physical distance. It is to provide a metaverse lifelogging method and device using.

In the metaverse lifelogging method using artificial intelligence-based geotagging implemented by a computer system according to an embodiment of the present invention, a point of interest that exists within a predetermined distance from meta information of a photo or video or location information identified through GPS Deriving a candidate list of (Point of Interest, POI); extracting at least one or more data of information collected from a device sensor, place-related information, and a past visit history of the user from the derived POI candidate list; and inputting the extracted data into a predictive model to select a place that the user is likely to visit as a visit place, and a lifelogging service may be provided based on the visit place.

The method may further include determining captured location information through meta information of a photo or video taken by the user at present or in the past.

The method may further include constructing a POI database for geotagging and location analysis, and a POI candidate list may be derived based on the constructed POI database.

Further comprising the step of learning the predictive model based on the user's feedback, wherein the step of learning the predictive model determines a false value when the user modifies the place selected through the predictive model. And, if the place is not modified, the prediction model can be trained by determining it as a true value.

The user's past visit history may be obtained by automatically geotagging the visited place using meta information included in a photo or video stored in the user's terminal.

In the step of extracting the data, the data may be extracted by extracting a place name or a keyword from which the place may be inferred from the text of the post left by the user, grasping information on a point of interest (POI), and extracting the data.

The step of inputting the data to a predictive model and selecting a place that the user is likely to visit as a visit place may include using location information of the photo or video and attribute information of the candidate list of the POI to be visited by other users. You can select a place to visit based on big data including photos or videos of

The step of identifying the captured location information through meta information of a photo or video taken by the user at present or in the past may include, when meta information can be obtained by accessing a photo or video taken at the present or in the past, the meta information. Based on the information, it is possible to record a life log of the past.

The step of identifying the captured location information through meta information of a photo or video taken by the user in the present or in the past may include, when access to a photo or video taken in the present or in the past cannot obtain meta information, the user Including the step of identifying the captured location information using at least one or more information of message records, payment details, and the user's movement stored in the terminal, and based on the captured location information, a life log of the past can be recorded. there is.

In the metaverse lifelogging device using artificial intelligence-based geotagging according to another embodiment of the present invention, a point of interest (POI) existing within a predetermined distance from meta information of a photo or video or location information identified through GPS a POI candidate list derivation unit for deriving a candidate list of ); an input data extractor extracting at least one or more of data collected from a device sensor, place-related information, and a past visit history of the user from the derived POI candidate list; and a prediction model inputting the extracted data to select a place the user is likely to visit as a visit place, and providing a lifelogging service based on the visit place.

The user may further include a location information determiner for recognizing captured location information through meta-information of a photo or video taken in the past or currently by the user.

A POI database for storing POI data for geotagging and location analysis may be further included, and a POI candidate list may be derived based on the POI database. there is.

Further comprising a prediction model learning unit for learning the prediction model based on the user's feedback, wherein the prediction model learning unit determines a false value when the user modifies the place selected through the prediction model , If the place is not modified, the prediction model may be trained by determining a true value.

The user's past visit history may be obtained by automatically geotagging the visited place using meta information included in a photo or video stored in the user's terminal.

The predictive model may select a visit place based on big data including pictures or videos of other users by using location information of the picture or video and attribute information of the POI candidate list.

The location information determining unit may record a lifelog of the past based on the meta information when meta information can be obtained by accessing a photo or video taken at present or in the past.

The location information determination unit uses at least one of information stored in the user's terminal, including message records, payment details, and the user's movement, when meta information cannot be obtained by accessing a photo or video taken at present or in the past. After grasping the captured location information, a past lifelog may be recorded based on the captured location information.

According to embodiments of the present invention, by automatically tagging visited places using meta information recorded in photos using big data and geotagging, lifelogging data is quickly generated, and the life history of the user's past visits It is possible to provide a metaverse lifelogging method and device using artificial intelligence-based geotagging that can expand the temporal range of logging.

In addition, according to the embodiments of the present invention, by providing a metaverse service that connects hyperlocal communities in individual places based on lifelogging, an artificial intelligence-based connection that can form a strong bond based on emotional distance rather than physical distance It is possible to provide a metaverse lifelogging method and device using geotagging.

1 is a block diagram for explaining an example of an internal configuration of a computer system according to an embodiment.
2 is a block diagram illustrating components that may be included in a processor of a computer system according to an exemplary embodiment.
3 is a flowchart illustrating a metaverse lifelogging method using artificial intelligence-based geotagging that can be performed by a computer system according to an embodiment.
4 is a diagram for explaining a metaverse lifelogging mobile platform according to an embodiment of the present invention.
5 is a diagram for explaining lifelogging using meta information stored in a photo according to an embodiment of the present invention.
6 is a diagram for explaining the configuration of a lifelogging mobile platform through a geotagging prediction model according to an embodiment of the present invention.
7 is a diagram for explaining the configuration of an AI-based geotagging service according to an embodiment of the present invention.
8 is a diagram for explaining an example of a metaverse lifelogging method using artificial intelligence-based geotagging according to an embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the described embodiments may be modified in many different forms, and the scope of the present invention is not limited by the embodiments described below. In addition, several embodiments are provided to more completely explain the present invention to those skilled in the art. The shapes and sizes of elements in the drawings may be exaggerated for clarity.

Android-based Wi-Fi indoor positioning technology is applied to automatically record the exact places visited by users using background location information, and provide real-time conversations and friend connection functions between users visiting the same place.

However, as the Android OS policy has strengthened the user consent process for the use of background location permission, only a small number of users (5% of all users) are lifelogging with Wi-Fi indoor positioning technology. In addition, in the case of Wi-Fi indoor positioning technology using a mobile device sensor and GPS (Global Positioning System), visit place misrecognition or omission occurs due to limitations in precision and recall performance. In addition, it takes a considerable period of time after the start of the service to accumulate lifelogging data, which is a premise for interaction with local communities or other users, and user departure at the initial stage of subscription may occur.

Accordingly, it is possible to record after the mobile platform service is installed only with the real-time location information of the mobile device, but it is necessary to expand the temporal scope of lifelogging using meta information of photos stored in the device in order to secure the user's lifelogging data before the service is installed. .

Embodiments of the present invention below may provide a lifelogging mobile platform and its operating method for recording places visited by a user in the present or in the past using artificial intelligence-based geotagging and connecting users who have visited the same place. According to embodiments of the present invention, by automatically tagging visited places using meta information recorded in photos using big data and geotagging, lifelogging data is quickly generated, and the life history of the user's past visits The temporal scope of logging can be extended. Accordingly, the lifelogging range can be expanded to photos or images of the past or photos or images before the application is installed.

In addition, according to embodiments of the present invention, by providing a metaverse service that connects hyperlocal communities in individual places based on lifelogging, it is possible to form a strong bond based on emotional distance rather than physical distance.

1 is a block diagram for explaining an example of an internal configuration of a computer system according to an embodiment. For example, a metaverse lifelogging device using artificial intelligence-based geotagging according to embodiments of the present invention may be implemented through the computer system 100 of FIG. 1 . As shown in FIG. 1, the computer system 100 includes a processor 110, a memory 120, a permanent storage device 130, It may include a bus 140 , an input/output interface 150 and a network interface 160 .

Processor 110 may include or be part of any device capable of processing any sequence of instructions. Processor 110 may include, for example, a computer processor, a processor in a mobile device or other electronic device, and/or a digital processor. Processor 110 may be included, for example, in a server computing device, server computer, series of server computers, server farm, cloud computer, content platform, mobile computing device, smartphone, tablet, set top box, media player, and the like. Processor 110 may be connected to memory 120 through bus 140 .

Memory 120 may include volatile, permanent, virtual or other memory for storing information used by or output by computer system 100 . The memory 120 may include, for example, random access memory (RAM) and/or dynamic RAM (DRAM). Memory 120 may be used to store any information, such as state information of computer system 100. The memory 120 may also be used to store instructions of the computer system 100, including instructions for a metaverse lifelogging device using, for example, artificial intelligence-based geotagging. Computer system 100 may include one or more processors 110 as needed or appropriate.

Bus 140 may include a communications infrastructure that enables interaction between the various components of computer system 100. Bus 140 may carry data between components of computer system 100, for example, between processor 110 and memory 120, for example. Bus 140 may include a wireless and/or wired communication medium between components of computer system 100, and may include parallel, serial, or other topological arrangements.

Persistent storage device 130 is a component such as a memory or other persistent storage device as used by computer system 100 to store data for some extended period of time (e.g., relative to memory 120). may include Persistent storage 130 may include non-volatile main memory as used by processor 110 in computer system 100 . Persistent storage device 130 may include, for example, flash memory, a hard disk, an optical disk, or other computer readable medium.

Input/output interface 150 may include interfaces to a keyboard, mouse, voice command input, display, or other input or output device. Configuration commands and/or data for the metaverse lifelogging device using AI-based geotagging may be received through the input/output interface 150 .

Network interface 160 may include one or more interfaces to networks, such as a local area network or the Internet. Network interface 160 may include interfaces for wired or wireless connections. Configuration commands and/or data for the metaverse lifelogging device using AI-based geotagging may be received through the network interface 160 .

Also, in other embodiments, computer system 100 may include more components than those of FIG. 1 .

2 is a block diagram showing components that may be included in a processor of a computer system according to an embodiment, and FIG. 3 is a metaverse life using artificial intelligence-based geotagging that a computer system according to an embodiment may perform. It is a flow chart showing the logging method.

As shown in FIG. 2, the processor 110 includes a location information determination unit 210, a POI candidate list derivation unit 220, an input data extraction unit 230, a prediction model 240, and a prediction model learning unit 250. ) may be included. Also, according to embodiments, a point of interest (POI) database may be further included. Here, the processor 110 may be referred to as a metaverse lifelogging device using artificial intelligence-based geotagging. Components of the processor 110 may represent different functions performed by the processor 110 according to a control command provided by at least one program code. For example, a location information determination unit as a functional expression that controls the computer system 100 so that the processor 110 determines location information of a photo or video taken by a user currently or in the past through meta information. (210) may be used. The processor 110 and components of the processor 110 may perform steps S310 to S350 included in the metaverse lifelogging method using artificial intelligence-based geotagging of FIG. 3 . For example, the processor 110 and components of the processor 110 may be implemented to execute an instruction according to an operating system code included in the memory 120 and at least one program code described above. Here, at least one program code may correspond to a code of a program implemented to process the metaverse lifelogging method using the AI-based geotagging.

The metaverse lifelogging method using artificial intelligence-based geotagging may not occur in the order shown, and some of the steps may be omitted or additional processes may be included.

In step S310, the location information determiner 210 may grasp location information through meta information of a photo or video taken by the user in the present or in the past.

For example, when the location information determiner 210 can obtain meta information by accessing a photo or video taken at present or in the past, it can record a past lifelog based on the meta information. As another example, when the location information determiner 210 cannot acquire meta information by accessing a photo or video taken at present or in the past, at least one of message records, payment details, and the user's movement path stored in the user's terminal After capturing location information and time information using the above information, a past lifelog may be recorded based on the captured location information. For example, when the meta information of a past photo includes only time information, location information may be obtained through message records or payment details stored in the user's terminal corresponding to the time information. At this time, if it is a record that shows information about the location where the photo was taken, such as message records stored in the user's terminal, payment details, and user's movement, as well as location information of other photos taken at similar times, it can be additionally used, and additional information The use of can be set to be used according to the consent of the user.

Meanwhile, a POI database for storing POI data for geotagging and place analysis may be further included. Accordingly, a POI candidate list may be derived based on the POI database.

In step S320, the POI candidate list derivation unit 220 derives a candidate list of points of interest (POIs) existing within a predetermined distance from meta information of a photo or video or location information obtained through GPS. can For example, a long-list POI list existing within a radius of 100 m may be derived based on the user's GPS coordinates or location information of a photo or video.

In step S330, the input data extractor 230 extracts at least one or more of information collected from the device sensor, place-related information, and the user's past visit history from the derived POI candidate list. can Here, the user's past visit history may be obtained by automatically geotagging the visited place using meta information included in a photo or video stored in the user's terminal. In addition, information on a point of interest (POI) can be grasped by extracting a place name or a keyword from which a place can be inferred from the text of a post left by a user. At this time, the posts left by the user may be collected through an application that provides a lifelogging mobile platform service, and may be collected through other applications permitted by the user or the web according to embodiments.

In step S340, the prediction model 240 may input the extracted data and select a place where the user is likely to visit as a visit place. The prediction model 240 may select a place where the user is likely to visit by utilizing methodologies such as logistics regression and neural network. For example, the predictive model 240 may select a place to visit based on big data including photos or images of other users by using location information of photos or images and attribute information of a POI candidate list. Accordingly, a lifelogging service may be provided based on the visited place.

In step S350, the predictive model learning unit 250 may learn the predictive model based on the user's feedback. More specifically, the predictive model learning unit 250 determines a false value when the user modifies the selected place through the predictive model, and determines a true value when the user does not modify the place, thereby forming the predictive model. can be learned

In this way, according to embodiments, a lifelogging function can be provided through geotagging, and in particular, a lifelogging period for a record prior to the point of service use can be extended by utilizing image information stored in a user terminal.

In addition, according to embodiments, service usability can be enhanced, and convenience and accuracy of a lifelogging function can be improved through a geotagging function for an accurate visit place.

4 is a diagram for explaining a metaverse lifelogging mobile platform according to an embodiment of the present invention.

Referring to FIG. 4 , a metaverse lifelogging mobile platform 400 that records places visited by users and connects users visiting the same place may be provided. For example, by using real-time location information 411 of a mobile device and meta information 412 of a stored photo, a place visited by a user may be automatically life-logged 410 in the form of “check-in”. In addition, a hyperlocal community 420 based on common interests can be formed on a mobile platform through real-time open chatting 421 between users visiting the same place.

Embodiments can provide a metaverse service that encompasses the hyperlocal service area through the 'place', which is the object of lifelogging, as a medium. In particular, the embodiments may provide a metabus service centered on specific individual places such as Jamsil Baseball Stadium, xx University, and neighborhood cafes, rather than neighborhoods or physical streets. As a result, a strong bond can be formed based on emotional distance rather than physical distance.

5 is a diagram for explaining lifelogging using meta information stored in a photo according to an embodiment of the present invention.

Referring to FIG. 5, lifelogging data is quickly generated at the initial stage of subscription by automatically tagging (520) the place to be visited by utilizing meta information recorded in a photo (510) stored in a mobile device (i.e., geotagging) , It is possible to increase the value of using the service by extending the temporal range of lifelogging for the user's past visit history.

To this end, according to an embodiment, it is possible to provide an artificial intelligence prediction model that automatically selects a place visited by a user based on GPS coordinates where the picture was taken and surrounding POI (Point of Interest) property information, and machine learning is used to Geotagging performance can be continuously improved.

Therefore, according to the embodiments, it is possible to provide a lifelogging metaverse service in which movement is automatically recorded without the inconvenience of running an application (app) at each place visited. In addition, according to embodiments, lifelogging technology including the present and past of a user may be provided through lifelogging using big data and geotagging, not a mobile device sensor. In addition, according to embodiments, it is possible to provide a metabus service that connects hyperlocal communities in individual places based on lifelogging.

6 is a diagram for explaining the configuration of a lifelogging mobile platform through a geotagging prediction model according to an embodiment of the present invention.

Referring to FIG. 6 , first, location information obtained through a terminal or meta information 610 of a photo (video) may be automatically tagged to determine location information. The lifelogging mobile platform 620 may extract a list of nearby places using the identified location information (621), and estimate a visited place through a predictive model 623 using the user's lifelogging data 622. . Accordingly, the lifelogging service 630 may be provided using the estimated visit place.

Below, the configuration of a lifelogging mobile platform through a geotagging prediction model according to an embodiment will be described in detail.

According to an embodiment, a POI DB for geotagging and location analysis may be constructed. Here, POI data collection items for geotagging and location analysis can be determined, and for example, POI data collection items can be determined as shown in [Table 1].

[Table 1]

In order to build a DB, methods such as web crawling and data purchase through government-sponsored data voucher business support can be used.

In addition, it is possible to provide a prediction model for implementation of AI-based geotagging function. 7 is a diagram for explaining the configuration of an AI-based geotagging service according to an embodiment of the present invention.

Referring to FIG. 7 , an artificial intelligence-based geotagging service according to an embodiment of the present invention may be provided, and a prediction model 740 may be provided for this purpose. First, a POI long-list 720 of POIs existing within a radius of 100 m based on the user's GPS coordinates may be derived. Information collected from the device sensor 731 from the POI candidate list 720, information such as the average number of visitors related to the place, type of business, operating hours, etc. 732, past visit history of the user 733, etc. input of the prediction model (input) data can be extracted. In addition, it is possible to provide a predictive model 740 for selecting 750 a place where a user is likely to visit by utilizing methodologies such as logistics regression and neural network. Here, based on the user's feedback 760, a learning model that can improve the accuracy of the prediction model 740 by determining a false value when the user modifies the corresponding place and a true value when registering the corresponding place as it is. can provide.

In addition, a server and DB providing a lifelogging mobile platform service can be constructed. For example, in order to build a cloud DB server that provides a lifelogging mobile platform service, a computing engine server on Google Cloud Platform can be built and data can be accumulated through SQL DB. In addition, you can configure a flexible server in preparation for traffic increase by using autoscaling, load balancer, Docker, etc. And you can manage Firewall and whitelist IP for cloud security.

And, REST API for lifelogging mobile platform service can be provided. For example, rest API can be provided by utilizing nest.js framework based on Node.js and typescript language to provide REST API for lifelogging mobile platform service. In addition, it is possible to implement a security authentication function using a JWT token. Security and usability can be pursued simultaneously through authentication token and refresh token. Also, you can systematically manage RESTful APIs by using Swagger.

An application providing a lifelogging mobile platform service may be provided, for example, a lifelogging mobile platform service Android application may be provided. For example, in order to provide a lifelogging mobile platform service Android application, Android native apps are provided using the Kotlin language, and a framework combining Dagger2 (Hilt), Retrofit, Kotlinx, Serialization, and Coil based on Clean Architecture is utilized. can In addition, you can use external libraries such as NAVER Maps SDK for map UI implementation, NAVER Place API for place search, Sendbird SDK for chatting, and Firebase FCM for notification function implementation.

8 is a diagram for explaining an example of a metaverse lifelogging method using artificial intelligence-based geotagging according to an embodiment.

Referring to FIG. 8 , a user may access an application provided with a lifelogging mobile platform service using a user terminal 810 and then upload a captured photo. At this time, it is possible to determine the captured location information through meta information such as time and coordinates included in the captured photo, and derive a candidate list 820 of points of interest (POIs) existing within a predetermined distance from the identified location information. can do. In this case, the POI candidate list 820 may be derived in consideration of the user's type of interest, physical distance, popularity of the place, business hours, and the like. Data such as information collected by the user terminal 810, place-related information, and the user's past visit history (history) may be extracted from the POI candidate list 820, and the visit place may be predicted. By inputting the extracted data to the model 830, a user may select a place that is highly likely to be visited as a visit place. At this time, the prediction model 830 may select a place that the user is likely to visit as a visit place based on user behavior data such as place information included in user posts in applications, etc., frequently visited industries, and past visit histories. there is.

As described above, according to the embodiments, by utilizing the geotagging function for lifelogging, it can be used as a digital journal service for individual users, and a platform for hyperlocal community users such as interest-based clubs centered on places can provide. In addition, it is possible to provide a direct communication channel for local users of local small business owners, eg. It is possible to communicate between the store owner and customers through a real-time chat room related to the store.

The embodiments expanded the lifelogging technology area through positioning using a mobile device location sensor, and expanded the technology area to lifelogging combining POI big data and a geotagging prediction model. In addition, the embodiments have enhanced the capability of the prediction model using the advanced and learning model for the place POI data collection technique.

In addition, the embodiments contributed to the vitalization of the overall mobile application-based lifelogging service and activated the offline interest community online. Communities among people who share interests based on the same place can be activated through mobile apps (eg, mom cafes in apartments, sports clubs at golf courses/tennis courts, study groups at universities/academies, etc.). Moreover, the embodiments provide local marketing opportunities that small business owners who have been alienated from digital marketing can easily access, and can serve as a regular customer management CRM tool through real-time chatting with regular store customers.

The devices described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. can be embodied in Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler.

As described above, although the embodiments have been described with limited examples and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (17)

In the metaverse lifelogging method using artificial intelligence-based geotagging implemented by a computer system,
deriving a candidate list of points of interest (POIs) existing within a predetermined distance from meta information of a photo or video or location information identified through GPS;
extracting at least one or more data of information collected from a device sensor, place-related information, and a past visit history of the user from the derived POI candidate list; and
Selecting a place where the user is likely to visit by inputting the extracted data into a predictive model as a visit place
including,
A method of operating a metaverse lifelogging mobile platform that provides a lifelogging service based on the visit place. According to claim 1,
Figuring out location information taken by the user through meta-information of a photo or video taken now or in the past
Further comprising, the operating method of the metaverse lifelogging mobile platform. According to claim 1,
Steps to build a point of interest (POI) database for geotagging and place analysis
Including more,
A method of operating a metaverse lifelogging mobile platform for deriving a candidate list of the point of interest (POI) based on the constructed point of interest (POI) database. According to claim 1,
Learning the predictive model based on the user's feedback
Including more,
The step of learning the predictive model,
Metaverse lifelogging, which determines a false value when the user modifies the place selected through the prediction model, and determines a true value when the place is not modified to learn the prediction model. How the mobile platform works. According to claim 1,
The user's past visit history,
Using meta information included in photos or videos stored in the user's terminal to automatically geotag and acquire the visited place
Characterized by, the operating method of the metaverse lifelogging mobile platform. According to claim 1,
The step of extracting the data is,
Extracting the data by extracting the place name or keyword that can infer the place from the text of the post left by the user, identifying information on a point of interest (POI)
Characterized by, the operating method of the metaverse lifelogging mobile platform. According to claim 1,
The step of inputting the data into a predictive model and selecting a place that the user is likely to visit as a visit place,
Selecting a place to visit based on big data including photos or images of other users by using location information of the photos or images and attribute information of the POI candidate list
Characterized by, the operating method of the metaverse lifelogging mobile platform. According to claim 2,
The step of identifying the location information taken through meta information of a photo or video taken by the user in the present or in the past,
If meta information can be obtained by accessing a photo or video taken in the present or in the past, recording a life log of the past based on the meta information
Characterized by, the operating method of the metaverse lifelogging mobile platform. According to claim 2,
The step of identifying the location information taken through meta information of a photo or video taken by the user in the present or in the past,
If meta information cannot be obtained by accessing a photo or video taken in the present or in the past, location information captured using at least one of message records, payment details, and user's movement stored in the user's terminal step to figure out
including,
Recording a past lifelog based on the captured location information
Characterized by, the operating method of the metaverse lifelogging mobile platform. In the metaverse lifelogging device using artificial intelligence-based geotagging,
a POI candidate list derivation unit for deriving a candidate list of points of interest (POIs) existing within a predetermined distance from meta information of a picture or video or location information identified through GPS;
an input data extractor extracting at least one or more of data collected from a device sensor, place-related information, and a past visit history of the user from the derived POI candidate list; and
A prediction model that inputs the extracted data and selects a place that the user is likely to visit as a place to visit.
including,
A metaverse lifelogging mobile platform that provides a lifelogging service based on the visit place. According to claim 10,
A location information determination unit for determining location information taken through meta information of a photo or video taken by the user in the present or in the past.
Further comprising, metaverse lifelogging mobile platform. According to claim 10,
Point-of-interest (POI) database to store point-of-interest (POI) data for geotagging and place analysis
Including more,
A metaverse lifelogging mobile platform that derives a candidate list of the point of interest (POI) based on the point of interest (POI) database. According to claim 10,
A predictive model learning unit for learning the predictive model based on the user's feedback.
Including more,
The predictive model learning unit,
Metaverse lifelogging, which determines a false value when the user modifies the place selected through the prediction model, and determines a true value when the place is not modified to learn the prediction model. mobile platform. According to claim 10,
The user's past visit history,
Using meta information included in photos or videos stored in the user's terminal to automatically geotag and acquire the visited place
Characterized by, metaverse lifelogging mobile platform. According to claim 10,
The predictive model,
Selecting a place to visit based on big data including photos or images of other users by using location information of the photos or images and attribute information of the POI candidate list
Characterized by, metaverse lifelogging mobile platform. According to claim 11,
The location information determination unit,
If meta information can be obtained by accessing a photo or video taken in the present or in the past, recording a life log of the past based on the meta information
Characterized by, metaverse lifelogging mobile platform. According to claim 11,
The location information determination unit,
If meta information cannot be obtained by accessing a photo or video taken in the present or in the past, location information captured using at least one of message records, payment details, and user's movement stored in the user's terminal After grasping, recording the past lifelog based on the photographed location information
Characterized by, metaverse lifelogging mobile platform.

Images