Message summarization method, computer device, and program
The message summarization method in chat rooms uses AI to generate summaries with relevant images, addressing the lack of comprehensive conversation summaries in instant messaging systems and enhancing user engagement.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-08-27
- Publication Date
- 2026-04-03
AI Technical Summary
Existing instant messaging systems lack the ability to provide a comprehensive summary of chat room conversations, including relevant images, which can enhance user understanding and engagement.
A message summarization method that includes generating a summary of chat room messages using AI, accompanied by images relevant to the summary, through a computer device or system, utilizing a processor to execute instructions for image search and display.
Enhances user engagement by providing a clear and intuitive summary of chat room discussions, incorporating images that are highly relevant to the message content, thereby improving user interaction and information retention.
Smart Images

Figure 2026058320000001_ABST
Abstract
Description
Technical Field
[0001] The following description relates to a technique for providing a message summary of a talk room.
Background Art
[0002] As a general communication tool, an instant messenger is software for transmitting and receiving messages and data in real time. A user can register a talk partner and exchange messages in real time with the partner registered in the talk list.
[0003] Using such a messenger function has become widespread not only in the PC environment but also in the mobile environment of mobile communication terminals.
[0004] For example, Patent Document 1 (Publication Date: September 30, 2002) discloses a mobile messenger service system and method for a mobile communication terminal using a wireless communication network that can provide a messenger service between mobile messengers installed in mobile terminals.
[0005] In addition, with the spread of instant messengers, the functions provided through them are becoming increasingly diverse. Among them, the importance of personal information protection has been increasing, and an openchat function has been provided that allows chatting via a link without exposing personal information such as phone numbers and IDs.
Prior Art Documents
Patent Documents
[0006]
Patent Document 1
Summary of the Invention
[0007] When providing a message summary that summarizes messages within a chat room, it is possible to also provide images that are highly relevant to the message summary. [Means for solving the problem]
[0008] A message summary 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 message summary provision method includes the steps of: requesting an image search by at least one processor in relation to a message summary generated based on messages in a talk room; receiving an image group containing at least one image in response to the image search request by at least one processor; and displaying the image group in relation to the message summary by at least one processor.
[0009] According to one embodiment, a message summary can be generated in a chat room using text-type messages sent and received since the last message summary as the messages to be summarized.
[0010] According to another embodiment, a message summary may be generated using the reordered messages after the order of the messages to be summarized has been corrected based on the relationships between the messages.
[0011] In another embodiment, the message summary is generated using the message to be summarized in addition to metadata of the chat room, and the metadata may include at least one of the following: the chat room title, description, topic, or category.
[0012] In another embodiment, the image group may consist of images related to the message summary that have been sent or received in the chat room since the previous message summary.
[0013] In another embodiment, the image group may consist of a predetermined number of images that have been sent or received in the chat room since the last message summary, sorted in descending order of similarity score to the message summary.
[0014] Furthermore, according to other embodiments, the image group may consist of images whose similarity score to the message summary is above a threshold.
[0015] Furthermore, according to another embodiment, the image group is composed of images whose similarity score to the message summary is above a threshold, and if the number of images with a similarity score to the message summary above a predetermined number is less than a predetermined number, images from an external server may be added to constitute the group.
[0016] In another embodiment, the image group may consist of images from an external server that are related to message summarization.
[0017] In other embodiments, the step of displaying a group of images may include the step of sorting the images included in the group based on their similarity score to the message summary.
[0018] Furthermore, according to other embodiments, the step of displaying the image group may include the step of displaying a message summary and core keywords representing the message summary together with the image group.
[0019] A program is provided, recorded on a non-temporary, computer-readable recording medium, for causing a computer device to execute a message summarization method. A program is also provided for causing a computer device to execute a message summarization method.
[0020] A computer device includes at least one processor configured to execute computer-readable instructions included in a memory. The at least one processor processes steps of requesting an image search in relation to a message summary generated based on a message in a talk room, receiving an image group including at least one image in response to the image search request, and displaying the image group in association with the message summary, and provides the computer device.
Brief Description of Drawings
[0021] [Figure 1] It is a diagram showing an example of a network environment in an embodiment of the present invention. [Figure 2] It is a block diagram showing an example of a computer device in an embodiment of the present invention. [Figure 3] It is a flowchart showing an example of a method executable by a computer device in an embodiment of the present invention. [Figure 4] It is a diagram showing an example of a process for determining whether to generate a message summary of a talk room in an embodiment of the present invention. [Figure 5] It is a diagram showing an example of a message summary generation process in an embodiment of the present invention. [Figure 6] It is a diagram showing an example of an image search process in an embodiment of the present invention. [Figure 7] It is a diagram showing an example of a message summary providing process in an embodiment of the present invention. [Figure 8] It is a diagram showing an example of a message summary providing process in an embodiment of the present invention. [Figure 9] It is a diagram showing an example of a message summary providing process in an embodiment of the present invention. [Figure 10] It is a diagram for explaining an example of utilizing a message summary in an embodiment of the present invention. [Figure 11]This figure illustrates an example of using message summarization in one embodiment of the present invention. [Modes for carrying out the invention]
[0022] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0023] Embodiments of the present invention relate to a technology for providing message summaries in a chat room.
[0024] Embodiments including those specifically disclosed herein can summarize messages that occur in a chat room and, when providing a message summary, can also provide images to appropriately illustrate the message summary.
[0025] A message summarization provision system according to an embodiment of the present invention is implemented by at least one computer device, and a message summarization provision method according to an embodiment of the present invention may be executed by at least one computer device included in the message summarization provision system. In this case, a computer program according to one embodiment of the present invention is installed and executed in the computer device, and the computer device may execute the message summarization provision 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 combined with the computer device and recorded on a computer-readable recording medium in order to have the computer execute the message summarization provision method.
[0026] 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 a plurality of electronic devices 110, 120, 130, 140, a plurality of servers 150, 160, and a network 170. Figure 1 is merely an example for the purpose of explaining 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 for the purpose of explaining an environment applicable to this embodiment, and the environment applicable to this embodiment is not limited to the network environment in Figure 1.
[0027] 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.
[0028] The communication method is not limited, and Network 170 may include not only communication methods that utilize communication networks (for example, mobile communication networks, wired internet, wireless internet, and broadcasting networks), but also short-range wireless communication between devices. For example, Network 170 may include one or more arbitrary networks from among 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.
[0029] Servers 150 and 160 can each be implemented by one or more computer devices that communicate with multiple electronic devices 110, 120, 130, and 140 via the network 170 and provide instructions, 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.
[0030] Figure 2 is a block diagram showing an example of a computer device in 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, can be realized by the computer device 200 shown in Figure 2.
[0031] 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 ROM and the permanent mass storage device such as a disk drive may be included in the computer device 200 as separate permanent storage devices distinct from the memory 210. The memory 210 may also store 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, or memory card. 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 can 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.
[0032] 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 recorded in a recording device such as memory 210.
[0033] 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 and memory 210, and files, etc., may be recorded in a recording medium (the persistent recording device described above) that the computer device 200 may further include.
[0034] 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.
[0035] 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 prior art components in the figure. For example, the computer device 200 may be configured to include at least some of the input / output devices 250 described above, and may further include other components such as transceivers and databases.
[0036] The following describes specific embodiments of a method and apparatus for providing message summaries and related images together.
[0037] In the following embodiments, we will use instant messengers as a representative example, but the principles can be applied to any social platform that provides various services utilizing resources such as user profile information and friendship relationships within social networking services, not just social networking services such as communities other than messengers.
[0038] In this specification, "Open Chat" refers to a chat service where users can enjoy conversations on topics of interest, and it is a community service that allows users to join a chat immediately via a link such as a URL, without requiring a process of adding friends using phone numbers or IDs. Open Chat links may include a function that, when the link is clicked, launches a messenger and opens the linked chat room, allowing the user to start chatting immediately.
[0039] This embodiment may summarize messages generated in an open chat talk room via an AI (artificial intelligence) solution, and in this case, the message summary may be displayed to users who have accumulated unread messages in the talk room.
[0040] In particular, in this embodiment, when providing a message summary of an open chat talk room, images that are highly relevant to the message summary may be provided together with the message summary.
[0041] In the following embodiments, we will use Open Chat as a representative example, but we are not limited to this. In addition to Open Chat, we can also apply this to all chat rooms related to instant messengers, such as group chat rooms and official account chat rooms, not just one-on-one chat rooms based on relationship information.
[0042] The computer device 200 according to this embodiment can provide messenger services to a client by connecting to a dedicated application installed on the client side or to a web / mobile site associated with the computer device 200. The computer device 200 may be configured with a message summarization system implemented by the computer. For example, the message summarization system may be implemented in the form of an independently operating program, or it may be configured in an in-app form for a specific application and implemented to be operable within that specific application.
[0043] The processor 220 of the computer device 200 may be implemented by components for performing the following message summarization 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 to represent the functionality of the processor 220.
[0044] Such a processor 220 and its components can control the computer device 200 to perform steps included in the following message summarization method. For example, the processor 220 and its components can 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 message summarization method described below may be performed in a different order than shown in the diagrams, and some steps may be omitted or additional steps may be included.
[0048] The steps included in the message summary provision method may be performed on the client side, but depending on the embodiment, at least some of the steps may be performed on the server 150 side.
[0049] Figure 3 is a flowchart showing an example of a method that a computer device in one embodiment of the present invention can perform.
[0050] Referring to Figure 3, in step 310, the processor 220 may request an image search in relation to the most recently generated message summary (hereinafter referred to as the "first message summary") among the message summaries in the talk room.
[0051] The processor 220 may determine whether to generate a message summary for an open chat talk room using predetermined message summary generation conditions. For example, the message summary generation conditions may include conditions related to the number of messages sent and received in the talk room. For instance, if the number of messages that have occurred in the talk room since the last message summary is greater than or equal to a threshold, that talk room may be determined to be a talk room that requires a message summary, i.e., a talk room to be summarized. In this case, the message summary generation conditions may be set as fixed conditions common to all open chat talk rooms. The threshold for determining whether a message summary will be summarized and the period (or time) for determining whether a message summary will be generated may be applied in the same way to all talk rooms. For example, the number of messages may be checked at predetermined intervals for all talk rooms, and talk rooms where the number of messages is greater than or equal to the threshold may be classified as talk rooms to be summarized. Depending on the embodiment, the threshold for determining whether a message summary will be summarized and the period (or time) for determining whether a message summary will be generated may be set taking into account the characteristics of each talk room. The processor 220 analyzes the message traffic per unit time for each open chat room and, based on the analysis results, can set a threshold for message summarization and a period for determining when to generate a message summary. For example, the threshold can be set higher for chat rooms with a high volume of messages, resulting in a shorter generation period. If the specified conditions are met within the period set for each chat room, it can be determined that the chat room requires message summarization.
[0052] The processor 220 can generate a message summary using at least some of the messages contained in a talk room if the talk room satisfies the message summary generation conditions. The processor 220 can generate a message summary by calling a message summarization interface that cooperates with server 150 or other server 160. For example, the processor 220 can call a language model API for summarizing messages (e.g., GPT (generative pre-trained transformer)) and generate a message summary using an AI solution that utilizes the language model. In this case, the processor 220 can select messages that correspond to the text type from among the messages that have occurred in the talk room since the last message summary and summarize them. In some embodiments, the processor 220 can also use metadata of the talk room to summarize the messages to be summarized, in which case the metadata may include at least one of the following: the talk room title, description, topic, or category.
[0053] The processor 220 can, at each message summary generation cycle, transmit to the server 150 the message summary generated during that cycle, i.e., the image search request related to the first message summary.
[0054] In step 320, the processor 220 may receive from the server 150 a first image group, which includes at least one image related to the first message summary, in response to the image search request in step 310.
[0055] According to the message summary generation cycle, among the messages that occurred in the chat room during the time interval from the previous message summary to the present, messages of type text become the messages to be summarized for generating the first message summary. At the same time, among the messages that occurred in the chat room during that time interval, messages of type image may become the image search targets for the first message summary. In other words, the processor 220 searches for images within the chat room, and can search for images related to the first message summary among the images that were actually sent and received in the chat room during the time interval corresponding to the first message summary.
[0056] Depending on the embodiment, images related to the first message summary can be searched using images from external servers accessible by server 150 (e.g., server 160) as the search target. For example, if the number of images related to the first message summary among the images in the talk room is less than a predetermined number, the missing images can be searched for and incorporated from external servers.
[0057] In step 330, the processor 220 may display a message summary of an open chat room in accordance with a user request, and in doing so, may also display an image group associated with each message summary. When the processor 220 displays the first message summary for an open chat room, it may display the first image group associated with the first image summary. If no images with a high degree of relevance to the message summary are found in the image search results, the processor may display only the message summary without displaying the image group.
[0058] The processor 220 may obtain image groups related to the message summary by image search within the chat room at the time a message summary is generated for each time interval in the chat room.
[0059] Figure 4 shows an example of the process for determining whether to generate a message summary of a chat room in one embodiment of the present invention.
[0060] Referring to Figure 4, the processor 220 can check the API call conditions that indicate the message summary generation conditions (S401). The API call conditions include a period (or time) for determining the generation of a message summary and a threshold that is the target condition for message summarization. These may be set commonly for all talk rooms or may be set differently for each talk room.
[0061] The processor 220 can determine, based on the API call conditions, whether the number of text-type messages generated in the talk room between the last message summary and the present time exceeds a certain threshold (S402).
[0062] If the number of text messages in the talk room since the last message summary is below a threshold, the processor 220 may count the number of text messages over a maximum time length (S403).
[0063] The processor 220 can determine whether the number of text messages counted over the maximum time period is greater than or equal to a threshold that is a condition for message summarization (S404).
[0064] If the number of text messages counted over the maximum time period is less than a threshold, the processor 220 may determine that the conditions for generating a message summary are not met and may execute a call to the message summary interface (S405).
[0065] If the number of text messages accumulated in the talk room between the last message summary and the present time exceeds a threshold, the processor 220 may call the language model API for message summarization as the message summarization interface and generate a message summary (S406).
[0066] The processor 220 can store and manage message summaries generated through an AI solution utilizing a language model, associating them with the talk room (S407).
[0067] The above process (S401-407) is repeated for each talk room at a predetermined interval (or time), and a message summary can be generated for talk rooms that meet the conditions for message summary generation.
[0068] According to this embodiment, message summarization is not performed for each individual client according to user requests, but rather a single message summary common to all talk rooms can be generated, stored, and managed on the server 150 side.
[0069] Figure 5 shows an example of a message summarization process in one embodiment of the present invention.
[0070] The processor 220 may generate a message summary for each talk room that satisfies the message summary generation conditions.
[0071] Referring to Figure 5, the processor 220 can select text-type messages that have occurred in the talk room during the time interval from the previous message summary to the present as messages to be summarized (S501).
[0072] If the chat room has a history of previous message summaries, the processor 220 may select text messages sent and received in the chat room since the previous summary message as images to be summarized.
[0073] The processor 220 may correct the order of the messages to be summarized based on the relationships between the messages (S502).
[0074] For example, the processor 220 may modify the order of messages among those to be summarized, in the case of messages created by the reply or mention function, so that the message order is such that the message follows the related message. For example, regarding message A, if a considerable amount of time has passed since message A was sent, and a reply to message A has been sent and received after several messages on different topics have been sent and received, generating a message summary without correcting the order of message A and the reply message may degrade the summarization performance. To improve summarization performance, the order may be adjusted so that the reply to message A is the message immediately following message A.
[0075] The processor 220 can generate a message summary using the metadata of the talk room in addition to the reordered messages to be summarized (S503). The metadata may include at least one of the following: the title of the talk room, a description of the talk room created by at least one of the administrators or participants of the talk room, the topic of the talk room analyzed by the processor 220, or the category of the talk room created by the administrator or participants of the talk room or analyzed by the processor 220. The processor 220 may also use the metadata of the talk room as a content boundary for summarizing the messages in the talk room.
[0076] The processor 220 can generate message summaries by summarizing target messages using large-scale language models or document summarization models. In this case, a large-scale language model can refer to a language model that can perform inference without fine-tuning using methods such as few-shot learning, but has, for example, more than 10 times the number of parameters (e.g., more than 110 billion parameters) compared to existing general language models. For example, large-scale language models such as GPT-3 and HyperClova are excellent few-shot learners that advance control based on natural text prompts, and are capable of in-context learning, which has the ability to understand patterns with only a small amount of data through prompts and solve NLP problems. When summarizing messages, in addition to few-shot learning methods that use prompt examples, zero-shot learning methods that perform control through instructional sentences even without prompt examples, and learning methods based on fine-tuning can also be utilized. Furthermore, a document summarization model may refer to a learning model that grasps the structural features of a document, structures it according to predetermined rules, extracts frequently occurring patterns in the structured paragraphs of the document, and automatically summarizes the message to be summarized into at least one keyword using natural language processing (NLP) techniques. The processor 220 may use a language-based learning model, such as a large-scale language model or a document summarization model, to generate a message summary for each talk room, summarizing the message to be summarized in each talk room into at least one keyword.
[0077] Figure 6 shows an example of an image search process in one embodiment of the present invention. The image search process can be executed on the server 150 side, but depending on the embodiment, at least some of the steps can be executed on the client side.
[0078] Referring to Figure 6, the server 150 can select searchable images from the images in the chat room (S601). The server 150 can select messages that correspond to image type from messages that occurred in the chat room during the time interval from the previous message summary to the present, which is the time interval in which the first message summary was generated, as image search targets for the first message summary.
[0079] Server 150 can calculate a similarity score between each image selected for search and the first message summary (S602). For example, Server 150 can convert the search target images into text (hereinafter referred to as "image text"), vectorize the first message summary and the image text, and then calculate the cosine similarity between the first message summary and the image text.
[0080] With respect to the first message summary, the server 150 may determine a first image group that includes at least one image based on the similarity score with the first message summary (S603). The server 150 may also configure a predetermined number of images (e.g., the top 5) from among the images selected for the search target as the first image group, determined in descending order of similarity score with the first message summary.
[0081] If images are selected solely based on their high scores to form the first image group, there is a possibility that images unrelated to the first message summary may be included. Therefore, in order to ensure a certain degree of relevance to the first message summary, the images that make up the first image group can be restricted to images whose similarity score to the first message summary is above a threshold. In other words, the server 150 can form the first image group with a predetermined number of images that have a similarity score to the first message summary above a threshold, and which have the highest similarity scores.
[0082] In this embodiment, images within the chat room are used as the search target, but the system is not limited to this, and it is also possible to search for images with a high degree of relevance to the first message summary from an external server. Server 150 may configure a first image group consisting of the top predetermined number (for example, 5) of images with high similarity scores to the first message summary from among the images from accessible external servers.
[0083] In some embodiments, a first image group is formed from images within the chat room. However, if the number of images with a similarity score above a threshold to the first message summary is less than a predetermined number, the missing images can be searched for on an external server and supplemented to reach the predetermined number, thereby forming the first image group. In other words, the server 150 can search both the image set within the chat room and the external image set to generate a first image group with a high degree of relevance to the first message summary.
[0084] Message summaries are generated at predetermined time intervals (or periods of time), and each message summary may contain at least one topic, where at least one bullet, representing individual sentence units, can form a single topic. In other words, each message summary may consist of at least one bullet.
[0085] When server 150 receives a first message summary as an image search request, it calculates a similarity score between the text and the image text, targeting the text corresponding to the entire bullet points that make up the first message summary, and obtains a first image group with a high degree of relevance to the first message summary.
[0086] Depending on the embodiment, it is also possible to search for images that are highly relevant to each bullet that constitutes the first message summary, and provide the image search results (image groups) for each bullet as images related to the first message summary.
[0087] Figures 7-9 show an example of a message summarization process in one embodiment of the present invention.
[0088] Referring to Figure 7, the processor 220 may, upon entering the talk room screen 700 in response to a user's request to join, display a UI (71) for accessing the message summary on the talk room screen 700.
[0089] For example, when a user request to join a talk room is received, the processor 220 can check the read status of the user's messages in the talk room. The processor 220 can determine whether there are more than a predetermined number (N) of unread messages in the talk room, and whether more than a predetermined amount of time (M hours) has passed since the user last visited the talk room, as part of the user's message read status. When the processor 220 enters the talk room screen 700 in accordance with the user's request to join, if both the condition that there are more than a predetermined number of unread messages in the talk room and the condition that more than a predetermined amount of time has passed since the last visit are met, the processor 220 can display a UI (71) for accessing the message summary on the talk room screen 700.
[0090] Referring to Figure 8, the processor 220 may provide a message summary page 810 when the user enters the talk room screen 700 and selects the message summary UI (71).
[0091] The message summary page 810 may display message summaries in simple bullet points for each time interval based on a defined period (or time), and each message summary may include summary content 811 that summarizes the message being summarized, core keywords 812 that represent the summary content 811, and image groups 813 that are highly relevant to the summary content 811.
[0092] As shown in Figure 9, the processor 220 can display both a summary content 811, which is a summary of text-type messages from the talk room messages that occurred between the start time (summary start time) and the end time (summary end time) of a defined time interval, and an image group 813, which is an image search result for image-type messages.
[0093] The core keywords 812 of the message summary can be extracted by applying known techniques that extract the most important words from a document based on word importance, such as TF-IDF and Text-rank.
[0094] In this embodiment, for each message summary, images related to the message summary can be searched, and the image group 813 configured as the image search result can be associated with the summary content 811 and displayed together.
[0095] The images in image group 813 may be sorted in descending order of similarity score to the summary content 811. In addition to the similarity criterion, the images in image group 813 may also be sorted in descending order of message transmission / reception time, or a random sorting order may be applied.
[0096] Based on the image search results, if image group 813 consists of images from within the chat room and images from an external server, the system may apply a priority order to the images within the chat room, prioritizing them higher in the search results.
[0097] Depending on the embodiment, if the summary content 811 consists of two or more bullets, it is also possible to display an image that is highly relevant to each bullet, associated with that bullet.
[0098] Figures 10 and 11 illustrate an example of utilizing message summarization in one embodiment of the present invention.
[0099] The processor 220 can utilize message summaries generated periodically in a chat room as content to introduce that chat room. As an example, referring to Figure 10, the processor 220 allows the user to access the Open Chat Cover screen 1000 in response to the user's request to access the Open Chat Cover, at which point the Open Chat Cover screen 1000 may display at least one message summary 1010. The Open Chat Cover screen 1000 may refer to the home screen (main screen) where the profile information of the Open Chat chat room (e.g., Open Chat name, profile picture, Open Chat description, number of participating members, etc.) is displayed. The message summaries 1010 displayed on the Open Chat Cover screen 1000 may include, for example, the most recently created message summary, the message summary with the most messages to be summarized, or the message summary with the most participants in the conversation of the message to be summarized. In this case, in addition to the message summary 1010, the Open Chat Cover screen 1000 may also display an image group that is highly relevant to the message summary 1010.
[0100] Furthermore, in this embodiment, message summaries generated periodically in the chat room can be utilized to provide a personalized feed for the user. The processor 220 may provide message summaries from among the message summaries generated for each chat room, in which core keywords match interest tags pre-set by the user, as the user's personal recommendation feed.
[0101] As shown in Figure 11, the processor 220 may provide the user with a feed page 1100 that utilizes message summaries as one of the service menus related to open chat. In this case, the feed page 1100 may include message summaries 1110 that match tags set in advance by the user. The processor 220 may provide message summaries 1110 that correspond to the user's interests as a feed, and in this case, it may also provide an open chat link 1111 for each message summary 1110 to move to the open chat talk room from which the message summary 1110 originated. Furthermore, when providing message summaries 1110 as a feed, the processor 220 may provide a group of images that are highly relevant to the message summary 1110 in association with the message summary 1110.
[0102] Thus, according to the embodiments of the present invention, when summarizing messages generated in a chat room and providing a message summary, an interface environment can be provided that makes the explanation of the message summary more intuitive by also providing images that are highly relevant to the message summary.
[0103] The apparatus described above 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.
[0104] 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 in order to be interpreted based on the processing unit or to provide instructions or data to the processing unit. Software may be distributed across a networked computer system and may be executed even when recorded in a distributed manner. Software and data may be recorded on one or more computer-readable recording media.
[0105] The methods according to the embodiment can 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 it 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 not only a medium directly connected to a computer system but also 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 ROMs, RAMs, and flash memories. 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.
[0106] 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.
[0107] Therefore, even if the embodiment is different, if it is equivalent to the claims, it falls within the scope of the attached claims.
[0108] This application claims priority based on Patent Application No. 10-2024-0128908, filed with the Korean Intellectual Property Office on 24 September 2024, and the entire contents of said Patent Application No. 10-2024-0128908 are incorporated into this application by reference. [Explanation of Symbols]
[0109] 110, 120, 130, 140: Electronic equipment 150, 160: Server 170: Network
Claims
1. A method for providing message summaries, performed by a computer device, The computer device includes at least one processor configured to execute computer-readable instructions contained in memory, The aforementioned message summary provision method is: The steps include: requesting an image search in relation to a message summary generated by at least one processor based on messages in a talk room; The steps include: receiving an image group containing at least one image in response to an image search request using the aforementioned at least one processor; The steps include: displaying the image group in association with the message summary using at least one of the processors; A method for providing message summaries, including the above.
2. The message summary is generated in the talk room using text-type messages sent and received since the last message summary as the messages to be summarized. A method for providing a message summary according to claim 1, characterized by the above.
3. The message summary is generated using the messages to be summarized after the order of the messages to be summarized has been corrected based on the relationships between the messages. A method for providing a message summary according to claim 2, characterized by the above.
4. The message summary is generated using the message to be summarized, in addition to the metadata of the talk room. The aforementioned metadata includes at least one of the following: the title, description, topic, or category of the talk room. A method for providing a message summary according to claim 2, characterized by the above.
5. The image group consists of images related to the message summary that were sent or received in the talk room after the previous message summary. A method for providing a message summary according to claim 1, characterized by the above.
6. The image group consists of a predetermined number of images that have been sent or received in the talk room since the last message summary, and are sorted in descending order of similarity score to the message summary. A method for providing a message summary according to claim 1, characterized by the above.
7. The image group consists of images whose similarity score to the message summary is above a threshold. A method for providing a message summary according to claim 6, characterized by the above.
8. The image group consists of images whose similarity score to the message summary is equal to or greater than a threshold, and if the number of images whose similarity score to the message summary is equal to or greater than a threshold is less than the predetermined number, images from an external server are added to form the group. A method for providing a message summary according to claim 6, characterized by the above.
9. The aforementioned image group consists of images from an external server that are related to the message summary. A method for providing a message summary according to claim 1, characterized by the above.
10. The step of displaying the aforementioned group of images is: The step of sorting the images included in the image group based on their similarity score to the message summary. A method for providing a message summary according to claim 1, including the method described in claim 1.
11. The step of displaying the aforementioned group of images is: The message summary and the core keywords representing the message summary are displayed together with the image group. A method for providing a message summary according to claim 1, characterized by the above.
12. A program for causing the computer device to execute the message summarization method described in any one of claims 1 to 11.
13. 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 requesting an image search in relation to the message summary generated based on messages in the chat room, The steps include receiving an image group containing at least one image in response to an image search request, The steps include displaying the image group in association with the message summary, A computer device that processes data.
14. The message summary is generated in the talk room using text-type messages sent and received since the last message summary as the messages to be summarized. The computer device according to claim 13, characterized by the above.
15. The image group consists of images related to the message summary that were sent or received in the talk room after the previous message summary. The computer device according to claim 13, characterized by the above.
16. The image group consists of a predetermined number of images that have been sent or received in the talk room since the last message summary, and are sorted in descending order of similarity score to the message summary. The computer device according to claim 13, characterized by the above.
17. The image group consists of images whose similarity score to the message summary is above a threshold. The computer device according to claim 16, characterized by the above.
18. The image group consists of images whose similarity score to the message summary is equal to or greater than a threshold, and if the number of images whose similarity score to the message summary is equal to or greater than a threshold is less than the predetermined number, images from an external server are added to form the group. The computer device according to claim 16, characterized by the above.
19. The aforementioned image group consists of images from an external server that are related to the message summary. The computer device according to claim 13, characterized by the above.
20. The aforementioned at least one processor is The images included in the image group are sorted based on their similarity score to the message summary. The computer device according to claim 13, characterized by the above.
Citation Information
Patent Citations
Service system and method for mobile messenger ofmobile phone using wireless communication network
KR1020020074304A