Methods, computer devices, and computer programs for providing AI avatars

Abstract

This invention provides a method for providing an AI avatar, a computer device, and a computer program. [Solution] The AI ​​avatar provision method includes the steps of: receiving a user's avatar generation request; assigning the avatar generation request to a specific time period based on the idle resource pattern of the avatar generation server in a unit of time; generating an avatar in the specific time period in response to the avatar generation request; and providing the generated avatar in response to the avatar generation request when the unit of time has elapsed.

Description

Technical Field

[0001] The present disclosure relates to a technology for providing an avatar that can be used on a social platform.

Background Art

[0002] An instant messenger, which is a frequently used communication tool, is software for transmitting and receiving messages and data in real time. A user can register a conversation partner in the messenger and communicate messages and the like in real time with the partner registered in the conversation list.

[0003] Such a messenger function has become popular not only on personal computers but also in the mobile environment of mobile communication terminals.

[0004] For example, Korean Patent Publication No. 10-2002-0074304 (Publication Date: September 30, 2002) discloses a mobile messenger service system for mobile communication terminals using a wireless communication network and a method thereof, which provides a messenger service between mobile messengers installed on mobile terminals.

[0005] With the spread of social platforms such as instant messengers, the functions provided using them have gradually become diversified.

Summary of the Invention

Problems to be Solved by the Invention

[0006] As an image product that can be used for a messenger's profile or the like, an AI (Artificial Intelligence) avatar can be provided.

[0007] To ensure a stable service, it can be implemented as a product option that generates and provides AI avatars with a time delay.

[0008] When generating AI avatars, a time-targeting distribution logic can be applied to ensure that server load is used evenly (flatly) across different time periods.

[0009] As part of the product options for AI avatars, it is possible to dynamically dimm the avatar in response to server load.

[0010] For each user, an AI avatar can be generated by performing real-time learning using images provided by that user. [Means for solving the problem]

[0011] An AI avatar provision method is provided, which is performed by a computer device, wherein the computer device includes at least one processor configured to execute computer-readable instructions contained in memory, and the AI ​​avatar provision method includes the steps of: receiving a user's avatar generation request by the at least one processor; assigning the avatar generation request to a specific time period based on the idle resource pattern of the avatar generation server in a unit of time; generating an avatar in the specific time period in response to the avatar generation request by the at least one processor; and providing the generated avatar in response to the avatar generation request at the time the unit of time has elapsed by the at least one processor.

[0012] According to one embodiment, the options for avatar products are divided into immediate products, which perform the avatar generation calculation immediately upon receiving the avatar generation request, and delayed products, which perform the avatar generation calculation at a later date. The step of receiving the avatar generation request may include receiving the avatar generation request according to the options for the delayed products.

[0013] According to another embodiment, the step of assigning the avatar generation request may include the steps of temporarily storing the avatar generation request in a queue and assigning the avatar generation request to the specific time period based on the resource usage of the avatar generation server.

[0014] In another embodiment, the step of assigning the avatar generation request may include the steps of: grasping the idle resource pattern for each time period based on the resource usage of the avatar generation server; determining the allowable allocation amount for each time period according to the idle resource pattern for each time period; and assigning the avatar generation request based on the allowable allocation amount for each time period.

[0015] In another embodiment, the avatar generation request includes at least one image provided by the user, and the step of generating the avatar may include the step of performing AI (Artificial Intelligence) learning using the image in response to the avatar generation request during the specific time period.

[0016] In another embodiment, the step of providing the avatar may involve holding the result of avatar generation from the time of avatar generation, and providing the generated avatar when the unit time has elapsed.

[0017] In another embodiment, the AI ​​avatar provision method may further include the step of displaying, as options for avatar products, an immediate product in which the avatar generation calculation is performed immediately upon the avatar generation request, and a time-delay product in which the avatar generation calculation is performed later, using the at least one processor.

[0018] In another embodiment, the step of displaying the immediate products and the time-delayed products may include a step of deciding whether or not to display the immediate products based on the load on the avatar generation server.

[0019] In another embodiment, the step of displaying the immediate product and the time-delayed product may include, if the load of the avatar generation server is below a threshold, the step of displaying both the immediate product and the time-delayed product, and if the load is above the threshold, the step of displaying the time-delayed product and dimming the immediate product.

[0020] In further embodiments, the instant product includes at least two product options depending on the number of avatar images to be provided, and the step of displaying the instant product and the time-delay product may include a step of determining whether to display at least one of the instant products based on the load on the avatar generation server.

[0021] The present invention provides a computer program, recorded on a computer-readable recording medium, for causing a computer device to execute the aforementioned AI avatar provision method.

[0022] The present invention provides a computer device comprising at least one processor configured to execute computer-readable instructions contained in memory, wherein the at least one processor processes: receiving a user's avatar generation request; assigning the avatar generation request to a specific time period based on the idle resource pattern of an avatar generation server in a unit of time; generating an avatar in the specific time period in response to the avatar generation request; and providing the generated avatar to the avatar generation request when the unit of time has elapsed. [Brief explanation of the drawing]

[0023] [Figure 1]This is a diagram showing an example of a network environment in an embodiment of the present invention. [Figure 2] This is a block diagram showing an example of a computer device according to an embodiment of the present invention. [Figure 3] This is a flowchart showing an example of a method that can be executed by a computer device according to an embodiment of the present invention. [Figure 4] This is a diagram showing an example of a resource usage pattern of an avatar generation server in an embodiment of the present invention. [Figure 5] This is a diagram showing an example of an avatar generation quota in an embodiment of the present invention. [Figure 6] This is a diagram showing an example of an AI avatar service screen in an embodiment of the present invention. [Figure 7] This is a diagram showing an example of an AI avatar service screen in an embodiment of the present invention. [Figure 8] This is a diagram showing an example of an AI avatar service screen in an embodiment of the present invention. [Figure 9] This is a diagram showing an example of an AI avatar service screen in an embodiment of the present invention. [Figure 10] This is a diagram showing an example of an AI avatar service screen in an embodiment of the present invention. [Figure 11] This is a diagram showing an example of an AI avatar service screen in an embodiment of the present invention. [Figure 12] This is a diagram showing an example of a process for displaying product options according to server load in an embodiment of the present invention. [Figure 13] This is a diagram showing an example of an avatar loading screen in avatar generation in an embodiment of the present invention.

Embodiments for Carrying Out the Invention

[0024] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0025] Embodiments of the present invention relate to a technology that provides avatars usable on social platforms.

[0026] Embodiments including those specifically disclosed herein may provide an AI avatar service that creates a 3D avatar resembling a user in combination with AI (artificial intelligence) technology, and in this case, the AI ​​avatar may be provided as an image product that can be used for social platform profiles, etc.

[0027] An AI avatar provisioning system according to an embodiment of the present invention may be implemented by at least one computer device, and an AI avatar provisioning method according to an embodiment of the present invention may be executed by at least one computer device included in the AI ​​avatar provisioning system. In this case, a computer program according to an embodiment of the present invention may be installed and executed on the computer device, and the computer device may execute the AI ​​avatar provisioning method according to an embodiment of the present invention in accordance with the control of the executed computer program. The above-described computer program may be recorded on a computer-readable recording medium in order to be combined with the computer device and cause the computer to execute the AI ​​avatar provisioning method.

[0028] Figure 1 shows an example of a network environment in one embodiment of the present invention. The network environment in Figure 1 shows an example that includes multiple electronic devices 110, 120, 130, 140, multiple servers 150, 160, and a network 170. Figure 1 is merely an example to illustrate the invention, and the number of electronic devices and servers is not limited to that shown in Figure 1. Furthermore, the network environment in Figure 1 is merely an example illustrating one of the environments applicable to this embodiment, and the environments applicable to this embodiment are not limited to the network environment in Figure 1.

[0029] The multiple electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals implemented by computer devices. Examples of the multiple electronic devices 110, 120, 130, and 140 include smartphones, mobile phones, navigation systems, PCs (personal computers), notebook PCs, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), and tablets. As an example, Figure 1 shows a smartphone as an example of electronic device 110, but in embodiments of the present invention, electronic device 110 may mean one of a variety of physical computer devices that can communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 via the network 170 using substantially wireless or wired communication methods.

[0030] The communication method is not limited, and may include not only communication methods that utilize communication networks that can be included in network 170 (for example, mobile communication networks, wired internet, wireless internet, broadcasting networks), but also short-range wireless communication between devices. For example, network 170 may include one or more arbitrary networks such as PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet. Furthermore, network 170 may include, but is not limited to, one or more network topologies, including bus networks, star networks, ring networks, mesh networks, star-bus networks, tree or hierarchical networks.

[0031] Servers 150 and 160 may each be implemented by one or more computer devices that communicate with multiple electronic devices 110, 120, 130, and 140 via the network 170 to provide commands, code, files, content, services, etc. For example, server 150 may be a system that provides services (such as a messenger service) to multiple electronic devices 110, 120, 130, and 140 connected via the network 170.

[0032] Figure 2 is a block diagram showing an example of a computer device according to one embodiment of the present invention. Each of the aforementioned electronic devices 110, 120, 130, and 140, as well as each of the servers 150 and 160, may be implemented by the computer device 200 shown in Figure 2.

[0033] Such a computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input / output interface 240, as shown in Figure 2. The memory 210 is a computer-readable recording medium and may include RAM (random access memory), ROM (read-only memory), and a permanent mass storage device such as a disk drive. Here, the permanent mass storage device such as ROM or a disk drive may be included in the computer device 200 as a separate permanent storage device distinct from the memory 210. The memory 210 may also contain an operating system and at least one program code. Such software components may be loaded into the memory 210 from a computer-readable recording medium separate from the memory 210. Such a separate computer-readable recording medium may include a floppy disk drive, disk, tape, DVD / CD-ROM drive, memory card, and other computer-readable recording media. In other embodiments, the software components may be loaded into the memory 210 through a communication interface 230, which is not a computer-readable recording medium. For example, software components may be loaded into the memory 210 of the computer device 200 based on a computer program installed by a file received via the network 170.

[0034] The processor 220 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor 220 by memory 210 or a communication interface 230. For example, the processor 220 may be configured to execute instructions received according to program code stored in a recording device such as memory 210.

[0035] The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (for example, the recording device described above) via the network 170. For example, requests, instructions, data, files, etc., generated by the processor 220 of the computer device 200 according to program code recorded in a recording device such as memory 210 may be transmitted to other devices via the network 170 under the control of the communication interface 230. Conversely, signals, instructions, data, files, etc., from other devices may be received by the computer device 200 via the network 170 through the communication interface 230 of the computer device 200. Signals, instructions, data, etc., received via the communication interface 230 may be transmitted to the processor 220 or memory 210, and files, etc., may be recorded on a recording medium (the persistent recording device described above) that the computer device 200 may further include.

[0036] The input / output interface 240 may be a means for interface with the input / output device 250. For example, the input device may include a microphone, keyboard, or mouse, and the output device may include a display or speaker. In another example, the input / output interface 240 may be a means for interface with a device that integrates input and output functions into one, such as a touchscreen. The input / output device 250 may consist of the computer device 200 and one other device.

[0037] In other embodiments, the computer device 200 may include fewer or more components than those shown in Figure 2. However, it is not necessary to explicitly show most of the conventional components in the figure. For example, the computer device 200 may be implemented to include at least some of the input / output devices 250 described above, and may further include other components such as transceivers and databases.

[0038] The following describes specific embodiments of methods and apparatus for providing AI avatars.

[0039] This embodiment may be applied to a social platform, in which case the social platform may mean not only a social networking service, but also a service platform that provides various services that utilize resources such as user profile information and friendship relationships within a social networking service.

[0040] In the following embodiments, a messenger will be used as a typical example of a social platform.

[0041] In this embodiment, an AI avatar service may be provided to create avatars that can be used for messenger profiles, etc., and in this case, in order to reduce infrastructure costs, a product option that enables server-distributed work may be operated.

[0042] The computer device 200 according to this embodiment may provide messenger services to a client by connecting to a dedicated application installed on the client or to a web / mobile site associated with the computer device 200. The computer device 200 may be configured with a computer-implemented AI avatar provisioning system. For example, the AI ​​avatar provisioning system may be implemented as an independently operating program, or it may be implemented in an in-app form for a specific application so that it can operate on the specific application.

[0043] The processor 220 of the computer device 200 may be implemented by components for performing the following AI avatar provision method. Depending on the embodiment, the components of the processor 220 may be selectively included in or excluded from the processor 220. Also, depending on the embodiment, the components of the processor 220 may be separated or merged for the expression of the functions of the processor 220.

[0044] Such a processor 220 and its components may control the computer device 200 to perform steps included in the following AI avatar provision method. For example, the processor 220 and its components may be implemented to execute instructions from the operating system code contained in the memory 210 and the code of at least one program.

[0045] Here, the components of the processor 220 may be representations of different functions that are executed by the processor 220 in accordance with instructions provided by the program code recorded in the computer device 200.

[0046] The processor 220 may read necessary instructions from the memory 210, which is loaded with instructions related to the control of the computer device 200. In this case, the instructions read may include instructions for controlling the processor 220 to perform the steps described below.

[0047] The steps included in the AI ​​avatar provision method described below may be performed in a different order than shown in the diagram, some steps may be omitted, or additional processes may be included.

[0048] The steps included in the AI ​​avatar provision method may be performed on server 150, and depending on the embodiment, some of the steps may be performed on the client.

[0049] Figure 3 is a flowchart showing an example of a method that a computer device can perform according to one embodiment of the present invention.

[0050] Referring to Figure 3, in step 310, the processor 220 may receive an avatar generation request from the user. The avatar generation request may include at least one image provided by the user, in which case the image is a photograph of the target person to be generated as an avatar, for example, a self-picture of the user. In the AI ​​avatar service according to the present invention, product options may be classified into immediate product options and delayed product options based on the time of avatar generation. An immediate product option means a product option in which the avatar generation calculation is performed immediately after receiving the user request and the result is provided as soon as the generation is completed. A delayed product option means a product option in which the avatar generation calculation is performed later, with a time difference of a unit period (e.g., 24 hours) in response to the user request, and the result is provided when the unit period has elapsed. The processor 220 may classify the product options purchased by the user and receive avatar generation requests for delayed product options.

[0051] In step 320, the processor 220 may allocate avatar generation requests to specific time slots based on the idle resource pattern for each time slot within a unit period. The processor 220 may obtain the resource usage (e.g., GPU usage) of the server (for example, server 160) that performs avatar generation calculations within a defined period to determine the average idle resource usage for each time slot. The processor 220 may allocate avatar generation requests to time slots with sufficient resources, taking into account the idle resource pattern within a unit period. For example, the processor 220 may determine the allocation amount for each time slot according to the idle resource pattern within a unit period, and then allocate avatar generation requests to specific time slots based on the allocation amount. In other words, the processor 220 may temporarily store avatar generation requests for time-difference product options in a queue and distribute them to time slots with low server load for throating.

[0052] In step 330, the processor 220 may perform an avatar generation calculation in response to an avatar generation request within the time slot allocated in step 320. At this time, the processor 220 may perform AI learning using the images included in the avatar generation request within the allocated time slot to generate an avatar for the target object. The processor 220 may generate an avatar for each avatar generation request by directly performing AI learning using the given images within the allocated time slot. In other words, in the case of an avatar generation request due to a time-difference product option, the processor 220 may not perform the avatar generation calculation immediately, but rather within the allocated time slot within the unit period.

[0053] In step 340, the processor 220 may, in response to the user's avatar generation request, provide the avatar generated in step 330 as a result at the time when a unit period has elapsed. The processor 220 may provide the result of avatar generation at the time when a unit period has elapsed from the time of the avatar generation request. In this case, the processor 220 may perform the avatar generation calculation within a unit period from the time of the avatar generation request, keep the result of avatar generation from the time of avatar generation, and provide it at the time when the unit period has elapsed.

[0054] Figure 4 shows an example of the resource usage pattern of an avatar generation server in one embodiment of the present invention.

[0055] Figure 4 shows a server resource usage graph 400 for a 24-hour period, where the unit period for the time-difference product option is set to 24 hours. For example, processor 220 may acquire server resource usage (e.g., GPU usage) for each time period in a 24-hour cycle over a month. In this case, the time slot may be determined based on the time required for avatar generation calculations. For example, the interval between time slots may be set to 1 hour, and depending on the embodiment, the time slots can be tuned to 40 minutes or 2 hours, etc. The server resource usage graph 400 shows the average resource usage for each time period over a month, and idle resources for each time period may be identified based on this.

[0056] When generating AI avatars, the processor 220 may apply a time-targeting distribution logic that evenly distributes the server load across time periods, taking into account the idle resource patterns for each time period within a unit period. The processor 220 may determine the permissible allocation amount for each time period within a range of threshold 401 that can guarantee stable service, according to the idle resource patterns for each unit period.

[0057] For example, as shown in Figure 5, the processor 220 may determine the allowable allocation amount 520 for avatar generation calculations for each time zone 510, taking into account the idle resource pattern in a unit period. Avatar generation requests for time-difference product options may be stored in chronological order, and time zones in which avatar generation processing can be performed may be allocated sequentially. As an example, avatar generation requests may be allocated in the order of 3:00, 4:00, 2:00, and 5:00, where the allowable allocation amount 520 is large. Of the avatar generation requests temporarily stored in the queue, avatar generation requests 1 to 400 may be allocated to 3:00 in order of request time, and avatar generation requests 401 to 750 may be allocated to 4:00. The rules for allocating avatar generation requests are not limited to this, and avatar generation requests may be allocated in various orders and methods within the range of the allowable allocation amount 520 for each time zone 510 by a distribution logic that evenly distributes the server load for each time zone.

[0058] The AI ​​avatar service according to the present invention does not involve pre-training an AI model and using the pre-trained model to serve the results at the service stage. Instead, it obtains results by performing AI learning in real time using images provided by the user during an allocated time slot for each user. Because real-time AI learning is performed at a predetermined time for each avatar generation request, different results can be obtained even if the same user provides the same image. By providing avatar results by performing AI learning each time, rather than using a pre-trained model, it is possible to obtain a variety of results and ensure superior quality.

[0059] Figures 6-11 show examples of AI avatar service screens in one embodiment of the present invention.

[0060] For example, as shown in Figure 6, the main home screen 610 or profile home screen 620 of the messenger may include an avatar menu 601 for accessing the AI ​​avatar service.

[0061] If the avatar menu 601 is selected on the main home screen 610, or if the avatar menu 601 is entered on the profile home screen 620, the processor 220 may move to the avatar home screen 700, as shown in Figure 7.

[0062] In addition to the access routes described above, access to the avatar home screen 700 may also be supported through various interface screens within the messenger.

[0063] Referring to Figure 7, the avatar home screen 700 may include an explanation of the AI ​​avatar service, as well as an avatar generation menu 701 for requesting avatar generation.

[0064] For example, if the avatar creation menu 701 is selected on the avatar home screen 700, the processor 220 may provide an avatar style guidance screen 810, as shown in Figure 8.

[0065] The avatar style guidance screen 810 may display at least one sample image representing the avatar styles provided by the AI ​​avatar service, and may include an avatar generation menu 811 for requesting avatar generation.

[0066] If the avatar generation menu 811 is entered on the avatar style guidance screen 810, the processor 220 may provide an image guide screen 820, as shown in Figure 8.

[0067] The processor 220 may provide image guide information via the image guide screen 820 when uploading training images necessary for avatar generation.

[0068] The image guide screen 820 may display examples of images that are suitable and unsuitable for training, and may include an upload menu 821 for uploading training images.

[0069] If the upload menu 821 is entered on the image guide screen 820, the processor 220 may provide an image selection screen 930, as shown in Figure 9.

[0070] In some cases, if the avatar creation menu 701 is entered on the avatar home screen 700, the avatar style guidance screen 810 and the image guide screen 820 may be skipped, and the user may proceed directly to the image selection screen 930.

[0071] The image selection screen 930 may display an image list 931 stored in a client such as a gallery, or in storage linked to the client. Interfaces such as individual selection, overall selection, and area selection may be included for selecting images to upload from the image list 931.

[0072] If the processor 220 has selected at least one image from the image list 931 of the image selection screen 930 and then pressed the selection complete button 932, it may provide the avatar gender selection screen 1040, as shown in Figure 10.

[0073] The avatar gender selection screen 1040 may consist of an interface for selecting gender, such as male, female, or genderqueer, as an example of avatar options.

[0074] If the user selects a gender on the avatar gender selection screen 1040 and then presses the selection completion button 1041, the processor 220 may provide the product option selection screen 1150, as shown in Figure 11.

[0075] Product options may be classified into two categories: instant products, which perform avatar generation immediately after purchase and provide the result as soon as generation is complete, and delayed products, which perform avatar generation after a time lag following purchase and provide the result 24 hours later.

[0076] Referring to Figure 11, the product option selection screen 1150 may consist of an interface for selecting either a time-delayed product option or an immediate product option.

[0077] For example, the product option selection screen 1150 may display, as a time-delay product option, a 100-time-delay product 1151 that provides 100 avatar images 24 hours later, and as an immediate product option, a 50-immediate product 1152 that provides 50 avatar images and a 100-immediate product 1153 that provides 100 avatar images.

[0078] The purchase costs for immediate items and delayed items may be set so that immediate items are more expensive than delayed items, and the purchase cost may be set in proportion to the number of avatar images. The cheapest is 100 delayed items for 1151, and the purchase costs may be set in the order of 50 immediate items for 1152, and 100 immediate items for 1153.

[0079] Furthermore, processor 220 may check the current load on the server performing the avatar generation calculation (for example, server 160) and decide whether to display the 100-time delay product 1151, the 50-immediate product 1152, and the 100-immediate product 1153.

[0080] Referring to Figure 12, the processor 220 may check whether the server load is below a threshold when entering the product option selection screen 1150 (S1201).

[0081] At this time, if the server load is below the threshold, the processor 220 may display all of the 100-time difference product 1151, the 50-immediate product 1152, and the 100-immediate product 1153 on the product option selection screen 1150 (S1202).

[0082] On the other hand, if the server load exceeds a threshold, the processor 220 may perform a damping process so that the 100-time difference product 1151 is displayed on the product option selection screen 1150, but the 50-immediate product 1152 and the 100-immediate product 1153 cannot be selected (S1203).

[0083] As another example, if the server load exceeds a threshold, the 100-time difference product 1151 and the 50-immediate product 1152 will be displayed, but the 100-immediate product 1153 can be treated as a DIMED item.

[0084] Depending on the embodiment, the criteria for determining the display of product options may be subdivided. For example, if the server load is less than the first threshold, all 100-time delay product 1151, 50-immediate product 1152, and 100-immediate product 1153 are displayed on the product option selection screen 1150; if the server load is greater than or equal to the first threshold but less than the second threshold (>first threshold), 100-time delay product 1151 and 50-immediate product 1152 are displayed, and 100-immediate product 1153 is dimmed; and if the server load is greater than or equal to the second threshold, 100-time delay product 1151 is displayed, and 50-immediate product 1152 and 100-immediate product 1153 are dimmed.

[0085] Therefore, the processor 220 can dynamically modify some of the product options related to the AI ​​avatar depending on the server load. For example, in a situation where traffic surges on the server for generating avatars, it may temporarily block the purchase of immediate products and guide users to purchase products with a time delay.

[0086] If the user selects a product option on the product option selection screen 1150 and then selects the avatar generation button 1154, the processor 220 may execute the avatar generation process (steps) according to that option. In the case of 50-immediate products 1152 and 100-immediate products 1153, the avatar generation calculation may be performed immediately at the time of the user's product purchase, and the result may be provided immediately upon completion of generation. On the other hand, in the case of 100-time-delayed products 1151, the avatar generation calculation may be performed not at the time of the user's product purchase, but during a time when the server load is low, and the result may be provided after 24 hours have elapsed.

[0087] If the avatar generation button 1154 is selected after selecting a product option on the product option selection screen 1150, the processor 220 may provide the avatar loading screen 1360 while the avatar generation calculation is being performed, as shown in Figure 13.

[0088] The processor 220 may provide a progress interface through the avatar loading screen 1360, corresponding to the product options purchased by the user. For example, the progress interface may display the remaining time until the avatar result is delivered.

[0089] Depending on the embodiment, the AI ​​avatar service may provide users with avatar generation information for purchased product options and related progress information in the form of chat room messages through a chat room 1370 using the AI ​​avatar service's official account.

[0090] Thus, according to embodiments of the present invention, it is possible to operate product options that create and provide AI avatars with a time lag for stable service. Furthermore, according to embodiments of the present invention, time-targeting distribution logic can be applied to generate AI avatars, ensuring that the server load is used evenly across different time periods. In addition, for each user, an AI avatar can be generated through real-time learning using images provided by that user.

[0091] The above-described apparatus may be implemented by hardware components, software components, and / or combinations of hardware and software components. For example, the apparatus and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as processors, controllers, ALUs (arithmetic logic units), digital signal processors, microcomputers, FPGAs (field programmable gate arrays), PLUs (programmable logic units), microprocessors, or various devices capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications running on the OS. The processing unit may also respond to software execution, access data, record, manipulate, process, and generate data. For convenience of understanding, it may be described as if a single processing unit is used, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Other processing configurations, such as parallel processors, are also possible.

[0092] Software may include computer programs, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or which may instruct the processing unit independently or collectively. Software and / or data may be embodied in any kind of machine, component, physical device, computer recording medium, or device for interpretation based on the processing unit or for providing instructions or data to the processing unit. Software may be distributed across a networked computer system, and may be recorded or executed in a distributed manner. Software and data may be recorded on one or more computer-readable recording media.

[0093] The methods according to the embodiment may be implemented in the form of program instructions executable by various computer means and recorded on a computer-readable medium. In this case, the medium may continuously record computer-executable programs or may temporarily record them for execution or download. Furthermore, the medium may be various recording or storage means in the form of a combination of one or more hardware components, and may be a medium directly connected to a computer system or distributed on a network. Examples of mediums include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and devices configured to record program instructions such as ROM, RAM, and flash memory. Other examples of mediums include recording media and storage media managed by app stores that distribute applications, and sites and servers that supply and distribute various other software.

[0094] As described above, embodiments have been explained based on limited embodiments and drawings, but those skilled in the art will be able to make various modifications and variations from the above description. For example, the described technique may be performed in a different order than described, and / or the components of the described system, structure, apparatus, circuit, etc. may be combined or assembled in a different manner than described, or opposed or replaced by other components or equivalents, and still achieve suitable results.

[0095] Therefore, even if the embodiment is different, it falls within the scope of the attached claims if it is equivalent to the claims.

Claims

1. A method for providing an AI avatar, which is performed by a computer device, The computer device includes at least one processor configured to execute computer-readable instructions contained in memory, The aforementioned AI avatar provision method is The process involves receiving a user's avatar generation request using at least one of the aforementioned processors, The steps include: using at least one processor to allocate the avatar generation request to a specific time period based on the idle resource pattern of the avatar generation server in a unit of time; The process involves, with at least one processor, generating an avatar in response to the avatar generation request during the specified time period, The steps include: providing the generated avatar to the at least one processor at the time the unit time has elapsed in response to the avatar generation request; A method for providing AI avatars, including the following.

2. Avatar product options are divided into immediate products, where the avatar generation calculation is performed immediately upon the avatar generation request, and delayed products, where the avatar generation calculation is performed at a later date. The step of receiving the aforementioned avatar generation request is: Receiving the avatar generation request via the time difference product option. The method for providing an AI avatar according to claim 1, characterized by the above.

3. The step of assigning the aforementioned avatar generation request is: The steps include temporarily storing the aforementioned avatar generation request in a queue, The steps include: assigning the avatar generation request to the specific time period based on the resource usage of the avatar generation server; The method for providing an AI avatar according to claim 1, including the following:

4. The step of assigning the aforementioned avatar generation request is: The steps include: understanding the idle resource patterns for each time period based on the resource usage of the avatar generation server; The steps include determining the permissible allocation amount for each time period according to the idle resource pattern for each time period, The steps include: assigning the avatar generation request based on the allowable allocation amount for each time period; The method for providing an AI avatar according to claim 1, including the following:

5. The avatar generation request includes at least one image provided by the user, The step of generating the aforementioned avatar is: The step of performing AI learning using the image in response to the avatar generation request during the specific time period. The method for providing an AI avatar according to claim 1, including the following:

6. The step of providing the aforementioned avatar is: The system retains the result of avatar generation from the time of avatar generation, and provides the generated avatar when the aforementioned unit of time has elapsed. The method for providing an AI avatar according to claim 1, characterized by the above.

7. The aforementioned AI avatar provision method is The step of displaying, using at least one processor, the following options for avatar products: an immediate product in which the avatar generation calculation is performed immediately upon the avatar generation request, and a delayed product in which the avatar generation calculation is performed later. The method for providing an AI avatar according to claim 1, further comprising:

8. The step of displaying the immediate product and the time-delayed product is, The step of determining whether to display the instant product based on the load on the avatar generation server. The method for providing an AI avatar according to claim 7, including the following:

9. The step of displaying the immediate product and the time-delayed product is, If the load on the avatar generation server is below a threshold, the steps include displaying both the immediate product and the time-delayed product, If the load on the avatar generation server exceeds a threshold, the steps include displaying the time-delayed products and processing the immediate products accordingly. The method for providing an AI avatar according to claim 7, including the following:

10. The aforementioned instant product includes at least two product options depending on the number of avatar images to be provided. The step of displaying the immediate product and the time-delayed product is, The step of determining whether to display at least one of the instant products based on the load on the avatar generation server. The method for providing an AI avatar according to claim 7, including the following:

11. A computer program recorded on a computer-readable recording medium for causing a computer device to execute the AI ​​avatar provision method described in any one of claims 1 to 10.

12. A computer device, At least one processor configured to execute computer-readable instructions contained in memory Includes, The aforementioned at least one processor is The steps include receiving a user's request to generate an avatar, The steps include: assigning the avatar generation request to a specific time period based on the idle resource pattern of the avatar generation server in a given time period; In response to the aforementioned avatar generation request, the steps include generating an avatar during the specified time period, The steps include providing the generated avatar to the user at the time the unit of time has elapsed in response to the avatar generation request, A computer device that processes data.

13. Avatar product options are divided into immediate products, where the avatar generation calculation is performed immediately upon the avatar generation request, and delayed products, where the avatar generation calculation is performed at a later date. The step of receiving the aforementioned avatar generation request is: Receiving the avatar generation request via the time difference product option. The computer device according to claim 12, characterized by the above.

14. The aforementioned at least one processor is The aforementioned avatar generation request is temporarily stored in a queue. Based on the resource usage of the avatar generation server, the avatar generation request is allocated to the specified time period. The computer device according to claim 12, characterized by the above.

15. The aforementioned at least one processor is Based on the resource usage of the avatar generation server, the idle resource patterns for each time period are identified. The allowable allocation amount for each time period is determined according to the idle resource pattern for each time period. The avatar generation request is allocated based on the permissible allocation amount for each time period. The computer device according to claim 12, characterized by the above.

16. The avatar generation request includes at least one image provided by the user, The aforementioned at least one processor is In response to the avatar generation request, perform AI learning using the image during the specified time period. The computer device according to claim 12, characterized by the above.

17. The aforementioned at least one processor is The system retains the result of avatar generation from the time of avatar generation, and provides the generated avatar when the aforementioned unit of time has elapsed. The computer device according to claim 12, characterized by the above.

18. The aforementioned at least one processor is As an option for avatar products, display an "instant" product where the avatar generation calculation is performed immediately upon the avatar generation request, and a "delayed" product where the avatar generation calculation is performed later. The computer device according to claim 12, characterized by the above.

19. The aforementioned at least one processor is The decision of whether or not to display the instant product is based on the load on the avatar generation server. The computer device according to claim 18, characterized by the above.

20. The aforementioned at least one processor is If the load on the avatar generation server is below a threshold, both the immediate product and the time-delayed product will be displayed. If the load on the avatar generation server exceeds a threshold, the time-delayed products will be displayed and the immediate products will be processed as DIMED. The computer device according to claim 18, characterized by the above.

Images