Method and system for managing text corresponding to emoticon / sticker for communication with chatbot

The method and system for managing text corresponding to emoticons/stickers allows chatbot systems to recognize and respond to emoticons/stickers by converting them into text, improving user interaction and interface functionality.

WO2024237509A1PCT designated stage expired Publication Date: 2024-11-21LINE PLUS
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2024/005436
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-12
Filing Date
2024-04-23
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Chatbot systems, such as chatGPT-3.5 and chatGPT-4, are unable to recognize or respond to emoticons and stickers directly, limiting their functionality in text-based and image-based communication.

Method used

A method and system for managing text corresponding to emoticons/stickers by receiving an image-like representation, obtaining and storing associated text, and transmitting this text to the chatbot system, either by inserting it into the image-type representation as a watermark or using a mapping table to assign category indexes, allowing the chatbot to understand and respond to emoticons/stickers.

Benefits of technology

Enables the use of emoticons and stickers in chatbot communication by converting them into text that the chatbot can process, enhancing user interaction and providing a more intuitive interface.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2024005436_21112024_PF_FP_ABST
    Figure KR2024005436_21112024_PF_FP_ABST
Patent Text Reader

Abstract

Disclosed are a method and system for managing a text corresponding to an emoticon / sticker for communication with a chatbot. The method for managing a text, according to one embodiment, may comprise the steps of: receiving, from a creator, an image-type expression comprising an emoticon or a sticker; acquiring a text corresponding to the image-type expression; and linking the image-type expression and the text and storing same. In this case, in response to a request for delivering the image-type expression to a chatbot system, the text linked to the image-type expression and stored can be delivered to the chatbot system.
Need to check novelty before this filing date? Find Prior Art

Description

Method and system for managing text corresponding to emoticons / stickers for communication with chatbots

[0001] The following description describes a method and system for managing text corresponding to emoticons / stickers for communication with a chatbot.

[0002] ChatGPT is a conversational AI service based on GPT-3.5 and GPT-4. When communicating with chatbot systems like ChatGPT, stickers and emoticons are not recognized. For example, ChatGPT-3.5 only uses text-based chat functions, and ChatGPT-4, while capable of image recognition through a vision-based deep learning model, primarily provides services by first inputting an image and then providing answers through text questions about the input image. It cannot respond to emoticons or stickers themselves.

[0003] A method and system are provided for creating and managing text corresponding to image-type expressions such as stickers or emoticons registered by a creator.

[0004] A text management method of a computer device including at least one processor, comprising: receiving, by the at least one processor, an image-type expression including an emoticon or a sticker from a creator; obtaining, by the at least one processor, a text corresponding to the image-type expression; and storing, by the at least one processor, the image-type expression and the text in association with each other, wherein, in response to a request to transmit the image-type expression to a chatbot system, the text stored in association with the image-type expression is transmitted to the chatbot system.

[0005] According to one aspect, the storing step may be characterized by including a step of inserting the text into the image-type expression in a watermark manner; and a step of storing the image-type expression into which the text is inserted.

[0006] According to another aspect, the inserting step may be characterized by inserting the text into the last n columns of the image-type expression (where n is a natural number) in a binary coding manner.

[0007] According to another aspect, in response to the request, the text inserted in the image-type expression in a watermark manner may be extracted, and the extracted text may be transmitted to the chatbot system.

[0008] According to another aspect, the text management method may further include a step of categorizing a plurality of meanings by the at least one processor to obtain a mapping table in which meanings and category indices are mapped.

[0009] According to another aspect, the obtaining step may be characterized by including a step of finding a category index mapped to a meaning corresponding to the image-type expression in the mapping table and assigning the category index to the image-type expression.

[0010] According to another aspect, the storing step may be characterized by including a step of inserting the assigned category index into the image-type representation in a watermark manner.

[0011] According to another aspect, the method may be characterized in that a category index assigned to the image-type expression is obtained in response to the request, and the obtained category index and a meaning mapped in the mapping table are transmitted to the chatbot system.

[0012] According to another aspect, the obtaining step may be characterized by including a step of generating text corresponding to the image-type expression using an image-to-text model.

[0013] According to another aspect, the text management method may further include a step of providing the producer with a function to transmit the text to the producer in association with the image-type representation by the at least one processor and to receive confirmation from the producer as to whether the text matches the producer's intention.

[0014] According to another aspect, it may be characterized in that at least a part of the text of the response content of the chatbot system is converted into the image-type representation and displayed.

[0015] A computer program stored on a computer-readable recording medium is provided for executing the above method on a computer device in combination with a computer device.

[0016] A computer-readable recording medium having recorded thereon a program for executing the above method on a computer device is provided.

[0017] A computer device is provided, comprising at least one processor configured to execute computer-readable instructions, wherein the computer device receives an image-type expression including an emoticon or a sticker from a creator by the at least one processor, obtains text corresponding to the image-type expression, stores the image-type expression and the text in association with each other, and transmits the image-type expression to a chatbot system in response to a request for transmitting the image-type expression to the chatbot system, wherein the text stored in association with the image-type expression is transmitted to the chatbot system.

[0018] You can create and manage text corresponding to image-type expressions such as stickers or emoticons registered by the creator.

[0019] FIG. 1 is a diagram illustrating an example of a network environment according to one embodiment of the present invention.

[0020] FIG. 2 is a block diagram illustrating an example of a computer device according to one embodiment of the present invention.

[0021] FIG. 3 is a drawing showing an example of a general appearance of a text management system according to one embodiment of the present invention.

[0022] FIG. 4 is a flowchart illustrating an example of a text management method according to one embodiment of the present invention.

[0023] FIG. 5 is a diagram illustrating an example of a process for automatically generating text for an image-type expression using machine learning in one embodiment of the present invention.

[0024] FIG. 6 is a diagram illustrating an example of a process for providing a chatbot service in one embodiment of the present invention.

[0025] Hereinafter, the detailed description will be given with reference to the attached drawings.

[0026] A text management system according to embodiments of the present invention may be implemented by at least one computer device. In this case, a computer program according to an embodiment of the present invention may be installed and run on the computer device, and the computer device may perform a text management method according to embodiments of the present invention under the control of the run computer program. The computer program described above may be stored on a computer-readable recording medium, which may be coupled to the computer device and cause the computer to execute the text management method.

[0027] FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention. The network environment of FIG. 1 represents an example including a plurality of electronic devices (110, 120, 130, 140), a plurality of servers (150, 160), and a network (170). FIG. 1 is merely an example for explaining the invention, and the number of electronic devices or servers is not limited to that of FIG. 1. In addition, the network environment of FIG. 1 merely illustrates one example of environments applicable to the present embodiments, and the environments applicable to the present embodiments are not limited to the network environment of FIG. 1.

[0028] The plurality of electronic devices (110, 120, 130, 140) may be fixed terminals or mobile terminals implemented as computer devices. Examples of the plurality of electronic devices (110, 120, 130, 140) include smart phones, mobile phones, navigation systems, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, etc. For example, in FIG. 1, the shape of a smart phone is shown as an example of the electronic device (110), but in embodiments of the present invention, the electronic device (110) may actually mean one of various physical computer devices that can communicate with other electronic devices (120, 130, 140) and / or servers (150, 160) via a network (170) using a wireless or wired communication method.

[0029] The communication method is not limited, and may include not only a communication method that utilizes a communication network (e.g., a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network) that the network (170) may include, but also short-range wireless communication between devices. For example, the network (170) may include any one or more of a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), the Internet, and the like. In addition, the network (170) may include any one or more of a network topology including, but not limited to, a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree, or a hierarchical network.

[0030] Each server (150, 160) may be implemented as a computer device or multiple computer devices that communicate with multiple electronic devices (110, 120, 130, 140) via a network (170) to provide commands, codes, files, contents, services, etc. For example, the server (150) may be a system that provides services to multiple electronic devices (110, 120, 130, 140) connected via a network (170).

[0031] FIG. 2 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. Each of the multiple electronic devices (110, 120, 130, 140) or servers (150, 160) described above can be implemented by the computer device (200) illustrated in FIG. 2.

[0032] Such a computer device (200) may include a memory (210), a processor (220), a communication interface (230), and an input / output interface (240), as illustrated in FIG. 2. The memory (210) may be a computer-readable recording medium, and may include a random access memory (RAM), a read only memory (ROM), and a non-permanent mass storage device such as a disk drive. Here, the non-permanent mass storage device such as a ROM and a disk drive may be included in the computer device (200) as a separate permanent storage device distinct from the memory (210). In addition, an operating system and at least one program code may be stored in the memory (210). These 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 computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, a memory card, etc. In another embodiment, the software components may be loaded into the memory (210) via a communication interface (230) other than a computer-readable recording medium. For example, the software components may be loaded into the memory (210) of the computer device (200) based on a computer program installed by files received over a network (170).

[0033] The processor (220) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (220) via the memory (210) or the communication interface (230). For example, the processor (220) may be configured to execute instructions received according to program code stored in a storage device such as the memory (210).

[0034] The communication interface (230) may provide a function for the computer device (200) to communicate with other devices (e.g., the storage devices described above) via the network (170). For example, requests, commands, data, files, etc. generated by the processor (220) of the computer device (200) according to program codes stored in a recording device such as the memory (210) may be transmitted to other devices via the network (170) under the control of the communication interface (230). Conversely, signals, commands, data, files, etc. from other devices may be received by the computer device (200) via the communication interface (230) of the computer device (200) via the network (170). Signals, commands, data, etc. received via the communication interface (230) may be transmitted to the processor (220) or the memory (210), and files, etc. may be stored in a storage medium (the permanent storage device described above) that the computer device (200) may further include.

[0035] The input / output interface (240) may be a means for interfacing with an input / output device (250). For example, the input device may include a device such as a microphone, a keyboard, or a mouse, and the output device may include a device such as a display or a speaker. As another example, the input / output interface (240) may be a means for interfacing with a device that integrates input and output functions, such as a touchscreen. At least one of the input / output devices (250) may be configured as a single device with the computer device (200). For example, a touchscreen, a microphone, a speaker, etc. may be implemented in a form included in the computer device (200), such as a smartphone.

[0036] Additionally, in other embodiments, the computer device (200) may include fewer or more components than those illustrated in FIG. 2. However, it is not necessary to explicitly illustrate most conventional components. For example, the computer device (200) may be implemented to include at least some of the input / output devices (250) described above, or may further include other components such as a transceiver, a database, etc.

[0037] FIG. 3 is a diagram illustrating an example of a general overview of a text management system according to an embodiment of the present invention. The embodiment of FIG. 3 illustrates a service system (310), a plurality of users (320), a chatbot system (330), a text management system (340), and a plurality of creators (350). Here, each of the plurality of users (320) and each of the plurality of creators (350) may correspond to an electronic device utilized by the user and / or creator.

[0038] The service system (310) can provide chatbot services to multiple users (320) by linking with the chatbot system (330). Depending on the embodiment, the service system (310) may include the chatbot system (330), or conversely, the chatbot system (330) may include the service system (310).

[0039] As previously explained, the chatbot system (330) is implemented in a form that provides a response based on text or provides a response to an image based on text input together with the input image, making it difficult to utilize emoticons or stickers.

[0040] To enable the use of such emoticons or stickers in the chatbot system (330), a text management system (340) may be utilized. In the embodiment of FIG. 3, the text management system (340) is shown as a separate system separated from the chatbot system (330) and the service system (310). However, depending on the embodiment, the text management system (340) may be implemented in a form that is included in the chatbot system (330) or included in the service system (310).

[0041] The text management system (340) can receive image-type expressions from at least some of the creators (350) who create image-type expressions such as emoticons or stickers. Thereafter, the text management system (340) can obtain text for such image-type expressions and store the image-type expressions and the text in association with each other. This process can be performed for various image-type expressions. Thereafter, when any user among the plurality of users (320) requests the service system (310) to transmit any image-type expression to the chatbot system, the service system (310) can obtain text corresponding to the image-type expression from the text management system (340) and transmit the obtained text instead of the image-type expression to the chatbot system (330). In this case, the chatbot system (330) can provide a response to the transmitted text to the corresponding user through the service system (310), thereby also providing a response to image-type expressions such as emoticons or stickers.

[0042] FIG. 4 is a flowchart illustrating an example of a text management method according to an embodiment of the present invention. The text management method according to the present embodiment can be performed by a computer device (200) that implements the text management system (340) described through FIG. 3. At this time, the processor (220) of the computer device (200) can be implemented to execute control instructions according to the code of the operating system included in the memory (210) or the code of at least one computer program. Here, the processor (220) can control the computer device (200) so that the computer device (200) performs steps (410 to 430) included in the method of FIG. 4 according to the control instructions provided by the code stored in the computer device (200).

[0043] In step (410), the computer device (200) can categorize multiple meanings and obtain a mapping table in which meanings and category indices are mapped. For example, the computer device (200) can directly create the mapping table. As another example, the computer device (200) can receive and utilize a mapping table generated by a manufacturer, service system (310), or chatbot system (330). This mapping table can be utilized by the computer device (200) to find text corresponding to an image-type expression. In some embodiments, step (410) may be omitted if the mapping table is not used.

[0044] In step (420), the computer device (200) may receive an image-type expression including an emoticon or sticker from the creator. For example, the computer device (200) may provide a user interface for registering the image-type expression to the creator who accesses the text management system (340). The creator may register the image-type expression he or she created with the text management system (340) through this user interface. For example, the user interface may be provided to the creator in the form of a web page or mobile page.

[0045] In step (430), the computer device (200) can obtain text corresponding to the image-type expression.

[0046] In one embodiment, the computer device (200) may generate text corresponding to an image-type expression using an image-to-text model. In this case, since artificial intelligence models that output visual information are primarily trained through general images, they may not function well with image-type expressions such as emoticons or stickers. Therefore, in this case, the computer device (200) may perform step (440). Depending on the embodiment, step (440) may be omitted.

[0047] In another embodiment, the computer device (200) may find a category index mapped to a meaning corresponding to an image-type expression in a mapping table and assign it to the image-type expression. For example, the computer device (200) may generate text corresponding to an image-type expression using the image-to-text model described above, and then find a category index mapped to the meaning according to the generated text in the mapping table and assign it to the image-type expression. In other words, if text corresponding to each emoticon and sticker is mapped, the problem of increased memory usage may occur. To save such memory usage, a category index instead of text may be mapped to the image-type expression. In this case, a process of finding the mapped meaning (text) in the mapping table through the category index may be added, but the problem of increased memory usage can be reduced.

[0048] At step (440), the computer device (200) may provide the creator with a function to link text with an image-like representation and transmit it to the creator, thereby obtaining confirmation from the creator whether the text matches the creator's intent. For example, this function may be provided in conjunction with the user interface for registering an image-like representation in step (420).

[0049] In step (450), the computer device (200) can store image-type expressions and text in association.

[0050] In an embodiment utilizing a mapping table to address the aforementioned memory usage increase issue, the computer device (200) can store image-type representations and the category indexes assigned to the image-type representations in a linked manner. In this case, text corresponding to the image-type representation can be obtained by finding the meaning mapped to the category index in the mapping table.

[0051] In another embodiment, the computer device (200) can insert text into the image-type expression as a watermark. For example, the computer device (200) can insert text into the last n (where n is a natural number) column of the image-type expression using binary coding. If the size of the last column of the sticker is 64 and n is 3, the computer device (200) can binary-code the column as 64bitX3 using odd / even numbers, etc., and insert and store text about the meaning of the sticker into the sticker.

[0052] In another embodiment, the computer device (200) may embed the assigned category index into the image-type representation in a watermark manner. In this case, after extracting the category index embedded in the image-type representation, the meaning (text) mapped to the category index can be found in a mapping table, thereby obtaining the text corresponding to the image-type representation.

[0053] Thereafter, in response to a request to transmit an image-type expression to the chatbot system (330), the text stored in association with the image-type expression may be transmitted to the chatbot system (330). For example, when a first user among multiple users (320) receives a chatbot service through the service system (310), the first user may input an image-type expression. In this case, the service system (310) may find a text corresponding to the input image-type expression through the text management system (340) and transmit the text to the chatbot system (330). The text stored in association with the image-type expression may be stored in the image-type expression in a watermark manner as described above. In this case, the text inserted in the image-type expression in a watermark manner may be extracted, and the extracted text may be transmitted to the chatbot system (330). In addition, a category index mapped to the meaning corresponding to the text in a mapping table, rather than the text itself, may be stored in association with the image-type expression. In this case, a category index stored in conjunction with an image-type expression is acquired, and the acquired category index and the meaning mapped in the mapping table can be transmitted to the chatbot system (330). In cases where both the watermark method and the mapping table are utilized, a category index inserted into an image-type expression is acquired, and the acquired category index and the meaning mapped in the mapping table can be transmitted to the chatbot system (330).

[0054] FIG. 5 is a diagram illustrating an example of a process for automatically generating text for an image-type expression using machine learning in one embodiment of the present invention.

[0055] The input process (510) may be an example of a process in which a text management system (340) receives an image-type expression (512) such as an emoticon or sticker from a producer (511).

[0056] The image-to-text conversion process (520) may be an example of a process in which a text management system (340) generates text (522) corresponding to an image-type representation (512) using an image-to-text model (521).

[0057] The process for providing a correction function (530) is such that the text management system (340) provides an image-type expression (512) and text (522) to the producer (511), and can confirm whether the text (522) is suitable for the production intention of the image-type expression (512). If the text (522) is not suitable for the production intention of the image-type expression (512), a function for directly receiving text corresponding to the image-type expression (512) from the producer (511) can be provided.

[0058] The database registration process (540) may be an example of a process in which a text management system (340) links an image-type expression (512) with text (522) and stores it in a database (541). In this case, the service system (310) or chatbot system (330) can use the database (541) to provide a chatbot service capable of providing appropriate responses to emoticons, stickers, etc.

[0059] In addition, at least a portion of the text in the response provided by the chatbot system (330) may be converted into an image representation and displayed. At this time, the conversion of the text into an image representation may be performed by the chatbot system (330) or the service system (310). For example, the service system (310) may extract texts from the response provided by the chatbot system (330) and then check whether an image representation corresponding to the extracted text exists in the database (541). If an image representation corresponding to the extracted text exists, the service system (310) may replace the extracted text in the response with an image representation and provide it to the user, thereby providing a chatbot service capable of responding with emoticons or stickers. In addition, a promotional effect for emoticons or stickers currently on sale can be expected through the emoticons or stickers displayed through the chatbot service.

[0060] FIG. 6 is a diagram illustrating an example of a process for providing a chatbot service in one embodiment of the present invention.

[0061] In the process of providing a chatbot service to a first user among multiple users (320), the service system (310) may receive input (610) from the first user.

[0062] At this time, the service system (310) can first check (620) whether the input (610) is text. If the input (610) is text, the service system (310) can directly transmit the text to the chatbot system (330) through a query process (630).

[0063] If the input (610) is not text, the service system (310) can check (640) whether the input (610) is an image. Here, images and image-type expressions can be used separately. Available emoticons or stickers can be pre-registered as image-type expressions in the service system (310), through which the service system (310) can distinguish between images and image-type expressions. If the input (610) is an image, the service system (310) can first extract the text contained in the image through OCR (Optical Character Recognition, 641). In addition, the service system (310) can convert the image into text using an image-to-text model (642). In this case, the service system (310) can transmit text obtained through OCR (641) and / or text obtained through an image-to-text model (642) to the chatbot system (330) through a query process (630).

[0064] If the input (610) is not an image, the service system (310) can check (650) whether the input (610) is an image-type expression. If the input (610) is not an image-type expression, the chatbot service for the input (610) can be terminated. If the input (610) is an image-type expression, the service system (310) can obtain a text mapped to the image-type expression. For example, the parser (651) of the service system (310) can extract a text stored in a database (541) in association with the image-type expression, extract a text inserted in the image-type expression in a watermark manner, or extract a meaning (text) mapped to a mapping table through a category index obtained through the image-type expression. Thereafter, the service system (310) can transmit the extracted text to the chatbot system (330) through a query process (630).

[0065] Thereafter, the service system (310) can receive (660) a response from the chatbot system (330) and transmit an output (670) according to the response to the first user as a response corresponding to the first user's input (610).

[0066] In this way, according to embodiments of the present invention, text corresponding to image-type expressions such as stickers or emoticons registered by a producer can be created and managed.

[0067] The systems or devices described above may be implemented as hardware components, or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0068] Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may independently or collectively command the processing device. The software and / or data may be embodied in any type of machine, component, physical device, virtual equipment, computer storage medium, or device for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

[0069] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., singly or in combination. The medium may continuously store a computer-executable program, or may temporarily store it for execution or download. In addition, the medium may be various recording means or storage means in the form of a single or multiple hardware combinations, and is not limited to a medium directly connected to a computer system, but may also be distributed over a network. Examples of the medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and those configured to store program commands, including ROM, RAM, and flash memory. In addition, examples of other media may include recording media or storage media managed by app stores that distribute applications, sites that supply or distribute various software, servers, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0070] Although the embodiments described above have been described by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above teachings. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0071] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims described below.

Claims

1. A text management method of a computer device including at least one processor, A step of receiving an image-type expression including an emoticon or sticker from a producer by at least one processor; obtaining text corresponding to the image-type representation by at least one processor; and A step of linking and storing the image-type expression and the text by at least one processor Including, In response to a request to transmit the image-type expression to the chatbot system, the text stored in connection with the image-type expression is transmitted to the chatbot system. A text management method characterized by .

2. In paragraph 1, The above saving step is, A step of inserting the above text into the image-type expression in a watermark manner; and A step of saving an image-type representation with the above text inserted. A text management method comprising:

3. In paragraph 2, The above inserting step is, A text management method characterized by inserting the text into the last n columns (where n is a natural number) of the image-type expression using binary coding.

4. In paragraph 2, In response to the above request, the text inserted in the image-type expression in a watermark manner is extracted, and the extracted text is transmitted to the chatbot system. A text management method characterized by .

5. In paragraph 1, A step of categorizing a plurality of meanings by at least one processor to obtain a mapping table in which meanings and category indices are mapped. A text management method that further includes:

6. In paragraph 5, The above acquisition steps are: A step of finding a category index mapped to the meaning corresponding to the image-type expression in the mapping table and assigning it to the image-type expression. A text management method comprising:

7. In paragraph 6, The above saving step is, A step of inserting the above-mentioned assigned category index into the image-type expression in a watermark manner. A text management method comprising:

8. In paragraph 6, In response to the above request, a category index assigned to the image-type expression is obtained, and the obtained category index and the meaning mapped in the mapping table are transmitted to the chatbot system. A text management method characterized by .

9. In paragraph 1, The above acquisition steps are: A step of generating text corresponding to the image-type expression using an image-to-text model. A text management method comprising:

10. In paragraph 1, A step of providing the producer with a function to receive confirmation from the producer as to whether the text matches the producer's intention by transmitting the text to the producer in association with the image-type expression by at least one processor. A text management method that further includes:

11. In paragraph 1, A text management method characterized in that at least a portion of the text in the response content of the chatbot system is converted into the image-type representation and displayed.

12. A computer program stored on a computer-readable recording medium for executing the method of any one of claims 1 to 11 on a computer device in combination with a computer device.

13. A computer-readable recording medium having recorded thereon a computer program for executing the method of any one of claims 1 to 11 on a computer device.

14. At least one processor implemented to execute computer-readable instructions. Including, By at least one processor, Receive an image expression containing an emoticon or sticker from the creator, Obtain the text corresponding to the above image-type expression, The above image-type expression and the above text are linked and stored, In response to a request to transmit the image-type expression to the chatbot system, the text stored in connection with the image-type expression is transmitted to the chatbot system. A computer device characterized by:

15. In paragraph 14, By at least one processor, Insert the above text into the image expression as a watermark, Saving an image representation with the above text inserted A computer device characterized by:

16. In paragraph 14, By at least one processor, By categorizing multiple meanings, a mapping table is obtained in which meanings and category indices are mapped, Finding a category index mapped to the meaning corresponding to the image-type expression in the mapping table and assigning it to the image-type expression. A computer device characterized by:

17. In paragraph 16, By at least one processor, Inserting the above-mentioned assigned category index into the image-type expression in a watermark manner. A computer device characterized by:

18. In paragraph 14, By at least one processor, Generating text corresponding to the image-type representation using an image-to-text model A computer device characterized by:

19. In paragraph 14, By at least one processor, Providing the producer with a function to transmit the text in association with the image-type expression to the producer and receive confirmation from the producer as to whether the text matches the producer's intention. A computer device characterized by:

20. In paragraph 14, A computer device characterized in that at least a portion of the text of the response content of the chatbot system is converted into the image-type representation and displayed.

Citation Information

Patent Citations

  • Method, Apparatus and System for Inserting Watermark, Method and Apparatus for Detecting Watermark, and System for Protecting Digital Document

    KR1020140140928A

  • Deep learning CNF-based detection and classification system for electrode coating defects of secondary batteries

    KR1020240007837A

  • PCB heat dissipation plate with coolant circulation unit

    KR1020240084673A

  • Avatar visual conversion apparatus expressing text message into V-moji and message conversion method

    KR102078209B1

  • Method and apparatus for embedding electronic watermark, and computer product

    US20060078159A1