Methods and systems for managing informant information based on conversations with informants.

Abstract

This provides a method and system for managing information about information providers based on conversations with them. [Solution] An information management method according to one embodiment includes providing a conversational information management function to an information provider who intends to provide content to users of a search service, facilitating a conversation between the information provider and artificial intelligence based on Large Language Models (LLM) using the conversational information management function, and analyzing the conversation to manage the information provider's campaign.

Description

[Technical Field]

[0001] The following description relates to a method and system for managing information of an information provider based on a conversation with the information provider. [Background Art]

[0002] Large Language Models (LLM) are a type of artificial intelligence trained on large-scale text data to enable response in human language to input natural language, and are language models configured by an artificial neural network having a large number of parameters (usually billions or more). Such LLMs are trained on a large amount of unlabeled text using self-supervised learning or semi-self-supervised learning. [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Korean Registered Patent No. 10-2551531 [Summary of Invention] [Problem to be Solved by Invention]

[0004] To provide a method and system for managing information of an information provider based on a conversation with the information provider. [Means for Solving the Problem]

[0005] An information management method for a computer device including at least one processor, comprising: providing a conversational information management function to an information provider who intends to provide content to users of a search service using the at least one processor; facilitating a conversation between the information provider and artificial intelligence based on large language models (LLMs) using the conversational information management function using the at least one processor; and analyzing the conversation to manage the information provider's campaign.

[0006] According to one embodiment, providing the conversational information management function may be characterized by including a function for registering assets for each campaign of the information provider through the conversational information management function.

[0007] In another embodiment, the advancement of the conversation may be characterized by the artificial intelligence generating conversation content to be provided to the information provider by utilizing at least two of the following: the information provider's campaigns, the assets of each of the information provider's campaigns, the prompts of each of the information provider's campaigns, information collected from external sources, and the content of the conversation.

[0008] In another embodiment, the asset may be characterized by including at least one of the following: a URL (Uniform Resource Locator) associated with the content that the information provider intends to provide, the title of the content, an identifier for the content, a category for the content, multimedia associated with the content, the content of the content, and the content of an article associated with the content.

[0009] In another embodiment, the prompt may be characterized by including at least one of the following: a phrase entered to be emphasized in relation to the content that the information provider intends to provide; keywords entered to be emphasized in relation to the content that the information provider intends to provide; the tone of the informational message contained in the content; and the format of the informational message.

[0010] In another embodiment, the campaign may be generated for each purpose for which the information provider intends to provide content, and may include assets and prompts for dynamically generating the content for the corresponding purpose at the time of search.

[0011] In another embodiment, managing the campaign may be characterized by including creating a new campaign using at least one of the assets included in the information provider's pre-created campaign and information collected externally in connection with the information provider.

[0012] In another embodiment, managing the campaign may include modifying the information provider's prompts registered in the information provider's pre-generated campaign based on the content of the conversation.

[0013] In another embodiment, managing the campaign may be characterized by including registering a new prompt in the information provider's pre-generated campaign based on the content of the conversation.

[0014] In yet another embodiment, the content provided to the user through the search service may be characterized by being dynamically generated at the time of the user's search and included in the search results, utilizing the information provider's assets and prompts registered for the corresponding campaign.

[0015] The present invention provides a computer program for causing a computer device to execute the aforementioned method.

[0016] The present invention provides a computer-readable recording medium on which a program for causing a computer device to execute the aforementioned method is recorded.

[0017] The present invention provides a computer device comprising at least one processor implemented to execute instructions readable by the computer device, wherein the at least one processor provides a conversational information management function to an information provider who intends to provide content to users of a search service, the conversational information management function facilitates a conversation between the information provider and artificial intelligence based on large language models (LLMs), and analyzes the conversation to manage the information provider's campaign. [Effects of the Invention]

[0018] We can provide methods and systems for managing information about information providers based on conversations with them. [Brief explanation of the drawing]

[0019] [Figure 1] This diagram shows an example of a network environment in one embodiment of the present invention. [Figure 2] This is a block diagram showing an example of a computer device in one embodiment of the present invention. [Figure 3] This is an illustrative diagram showing an overview of an information management system in one embodiment of the present invention. [Figure 4] This is a flowchart illustrating an example of an information management method in one embodiment of the present invention. [Figure 5] This figure shows an example of a conversational information management center in one embodiment of the present invention. [Figure 6] This figure shows an example of a conversational information management center in one embodiment of the present invention. [Figure 7]It is a diagram illustrating an example of a conversational information management center according to an embodiment of the present invention. [Figure 8] It is a diagram illustrating an example of a conversational information management center according to an embodiment of the present invention. [Figure 9] It is a diagram illustrating an example of a conversational information management center according to an embodiment of the present invention. [Figure 10] It is a diagram illustrating an example of a conversational information management center according to an embodiment of the present invention. [Figure 11] It is an exemplary diagram for explaining a process of providing a response to a user prompt according to an embodiment of the present invention. [Figure 12] It is a diagram showing an example of providing search results according to an embodiment of the present invention. DETAILED DESCRIPTION OF EMBODIMENTS

[0020] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.

[0021] The information management system according to an embodiment of the present invention may be implemented by at least one computer device. In this case, in the computer device that implements the information management system, a computer program according to an embodiment of the present invention may be installed and executed, and the computer device may execute the information management method according to the embodiment under the control of the executed computer program. The above-described computer program may be recorded on a computer-readable recording medium, to be combined with a computer device and cause the computer to execute the information management method.

[0022] Figure 1 is a diagram showing an example of a network environment according to an embodiment of the present invention. The network environment in Figure 1 is shown as an example including a plurality of electronic devices 110, 120, 130, 140, a plurality of servers 150, 160, and a network 170. Such Figure 1 is merely an example for describing the invention, and the number of electronic devices and the number of servers are not limited to those shown in Figure 1.

[0023] The multiple electronic devices 110, 120, 130, and 140 may be fixed or mobile terminals implemented by a computer system. 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), tablets, game consoles, wearable devices, IoT (Internet of Things) devices, VR (virtual reality) devices, and AR (augmented reality) devices. 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 systems that can communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 via a network 170 using substantially wireless or wired communication methods.

[0024] The communication method is not limited, and it may include not only communication methods that utilize communication networks that can be included in network 170 (for example, mobile communication networks, wired internet, wireless internet, broadcasting networks, phase networks, etc.), but also short-range wireless communication between devices. For example, network 170 may include one or more arbitrary networks such as PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet. Furthermore, network 170 may include, but is not limited to, one or more network topologies, including bus networks, star networks, ring networks, mesh networks, star-bus networks, tree or hierarchical networks.

[0025] Servers 150 and 160 may each be implemented by one or more computer devices that communicate with multiple electronic devices 110, 120, 130, and 140 via a network 170 to provide commands, code, files, content, services, etc. For example, server 150 may be a system that provides a first service to multiple electronic devices 110, 120, 130, and 140 connected via the network 170, and server 160 may also be a system that provides a second service to multiple electronic devices 110, 120, 130, and 140 connected via the network 170. As a more specific example, server 150 may provide the multiple electronic devices 110, 120, 130, and 140 as a first service through an application, which is a computer program installed and executed on the multiple electronic devices 110, 120, 130, and 140, with the service targeted by that application (for example, a search service). As another example, server 160 may provide a second service that distributes files for installing and running the aforementioned application to multiple electronic devices 110, 120, 130, and 140.

[0026] 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, may be implemented by the computer device 200 shown in Figure 2.

[0027] 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 persistent mass storage devices such as disk drives. Here, persistent mass storage devices such as ROM and disk drives may be included in the computer device 200 as separate persistent 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 computer-readable recording media such as floppy disks, disks, tapes, DVD / CD-ROM drives, and memory cards. In other embodiments, the software components may be loaded into the memory 210 through a communication interface 230 which is not a computer-readable recording medium. For example, software components may be loaded into the memory 210 of the computer device 200 based on a computer program installed by a file received via the network 170.

[0028] The processor 220 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor 220 by memory 210 or a communication interface 230. For example, the processor 220 may be configured to execute instructions received according to program code stored in a recording device such as memory 210.

[0029] The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (for example, the recording device described above) via the network 170. For example, requests, instructions, data, files, etc., generated by the processor 220 of the computer device 200 according to program code recorded in a recording device such as memory 210 may be transmitted to other devices via the network 170 under the control of the communication interface 230. Conversely, signals, instructions, data, files, etc., from other devices may be received by the computer device 200 via the network 170 through the communication interface 230 of the computer device 200. Signals, instructions, data, etc., received via the communication interface 230 may be transmitted to the processor 220 or memory 210, and files, etc., may be recorded on a recording medium (the persistent recording device described above) that the computer device 200 may further include.

[0030] 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.

[0031] In other embodiments, the computer device 200 may include fewer or more components than those shown in Figure 2. However, it is not necessary to explicitly show most of the conventional components in the figure. For example, the computer device 200 may be implemented to include at least some of the input / output devices 250 described above, and may further include other components such as transceivers and databases.

[0032] Figure 3 is a schematic diagram illustrating an information management system in one embodiment of the present invention. Figure 3 shows an information management system 310, a search system 320, multiple users 330, multiple information providers 340, and a conversational information management center 350.

[0033] The search system 320 may correspond to a server (for example, server 150) that provides search services to multiple users 330, and may be implemented by at least one computer device 200. Here, each of the multiple users 330 may be a physical device of a user that connects to the search system 320 via the network 170 to receive search services. Each of the multiple information providers 340 may be a physical device of an information provider that registers the information it intends to provide in the information management system 310. Here, the physical device may be implemented by the computer device 200 described above.

[0034] The information management system 310 according to this embodiment may be included in the search system 320, or it may be implemented in a manner that is linked with the search system 320 via the network 170. The embodiment in Figure 3 shows an example in which the information management system 310 is implemented in a manner that is included in the search system 320. In this case, the information management system 310 may be implemented on at least one physical device that implements the search system 320. Depending on the embodiment, the information management system 310 may be implemented on a physical device separate from the physical device that implements the search system 320, and may be implemented in a manner that communicates with the search system 320 via the network 170.

[0035] The search service provided by the search system 320 to multiple users 330 may include search results corresponding to user input. The search results may, in principle, be generated based on information searchable on the web. Furthermore, the search system 320 may include information provided by multiple information providers 340 in the search results. Here, the information provided by the multiple information providers 340 may, but is not limited to, advertising information. Since the search service itself that provides such search results is well-known, a detailed explanation will be omitted.

[0036] On the other hand, the search system 320 according to this embodiment may provide a search service that includes answers based on artificial intelligence, such as Large Language Models (LLMs), in the search results. For example, suppose the search system 320 receives a natural language-based prompt from a specific user among a group of users 330. In this case, the search system 320 may input the received prompt into the LLM, generate a first answer suitable for the prompt as an LLM result, and provide the user with search results including the first answer. In this case, the search results may include at least a portion of existing diverse search results in addition to the first answer. The search system 320 may also provide a search service based on a conversation between the LLM-based artificial intelligence and the user. The search service may be provided to the user by switching between a first mode that provides a first answer as an LLM result based on a general search service and a second mode that provides a first answer as an LLM result based on a conversation between the LLM-based artificial intelligence and the user. In this case, in both the first and second modes, at least a portion of the first answer may be further provided as a second answer, which is an instance for the information provider's content.

[0037] Furthermore, the search results may include a second response generated from at least some of the information registered by multiple information providers 340. For example, suppose the search system 320 dynamically generates a second response based on artificial intelligence, onto which the message of a selected information provider 340 is projected. In this case, the search system 320 can provide the user with search results that include not only the first response generated using LLM, but also the second response based on artificial intelligence.

[0038] In this case, when the search system 320 generates a second response based on artificial intelligence, it may not simply provide the information provided by the information provider as is, but may dynamically generate the second response based on artificial intelligence by using the user's prompt, the first response generated using LLM, assets registered by the information provider, and / or prompts registered by the information provider. Here, assets may include, as an example, a URL (Uniform Resource Locator) related to the first information that the information provider intends to provide, the title or identifier of the first information, the category of the first information, the content of the first information, and the content of articles related to the first information. For example, if the information provider intends to advertise a specific product or service, the assets may include a URL related to the product or service, the product or service name, the category of the product or service, product or service information, and the content of articles related to the product or service. In addition, prompts registered by the information provider may include phrases or keywords that the information provider intends to emphasize in relation to the first information, and information regarding the tone and format of the information message provided as the second response. Thus, the search system 320 can dynamically generate a second response that takes into account not only the first response generated using LLM in response to the user's natural language-based prompt, but also the registered assets and prompts of information providers offering their own information, as well as the first response. Furthermore, depending on the embodiment, the search system 320 may generate the second response by further utilizing information about the user. Here, information about the user may include the user's demos, interests, purchase information, etc., and may be used to customize the second response for the user.

[0039] In addition, since there may be multiple information providers 340 who wish to disclose their own information, the search system 320 may dynamically determine which of the multiple information providers 340's assets and prompts to use to generate the second answer. For example, the search system 320 may initially select an information provider associated with the first answer, i.e., the LLM result, from among the multiple information providers 340 based on the first answer. Depending on the embodiment, the search system 320 may use at least one of the user's prompt, the LLM result, and the recommendation query generated by LLM when initially selecting an information provider. After this, the search system 320 may dynamically conduct an auction among the initially selected information providers and select the first information provider as the information provider for generating the second answer. One of the well-known auction methods may be used. For example, the GSP (Generalized Second Price) auction method may be used.

[0040] Thus, in providing a response to a natural language-based prompt from a user, the search system 320 can dynamically generate a response based on the information provider's assets and the prompt, i.e., a second artificial intelligence-based response onto which the information provider's message is projected. Therefore, the search system 320 can provide the user with a response that is dynamically generated so as to project the information provider's message, in relation to a natural language-based prompt received from the user.

[0041] In this case, the information management system 310 may provide a conversational information management center 350 for managing information necessary for generating content that each of the multiple information providers 340 intends to provide to multiple users 330 through a search service. Such a conversational information management center 350 may, for example, be created in the form of a web page provided to the information provider, but is not limited to this.

[0042] The information management system 310 may manage information for generating content that an information provider intends to provide through the search system 320, while interacting with the information provider in a conversational manner via the network 170 to the conversational information management center 350. For example, the information provider may generate campaigns for each purpose for which the information provider intends to provide content through a conversation with the artificial intelligence provided by the conversational information management center 350, and the assets and prompts described above may be registered for each campaign. For example, the information provider can generate campaigns for various purposes desired by the information provider, such as generating campaigns related to a specific event or campaigns related to the download of a specific app, and can register the assets and prompts associated with each generated campaign for each campaign. For this reason, the conversational information management center 350 may provide the information provider with a list of generated campaigns and a function for the information provider to upload assets for each campaign. On the other hand, the information provider's prompts may be automatically registered by analyzing the conversation between the artificial intelligence provided by the conversational information management center 350 and the information provider.

[0043] For example, the information management system 310 can manage the information provider's campaigns, such as improving existing campaigns or creating new campaigns, by interacting with the information provider in a conversational format using artificial intelligence at the conversational information management center 350. In this case, the artificial intelligence may include conversational artificial intelligence based on LLM. Such conversational artificial intelligence can access campaigns pre-registered with the information provider, assets and prompts for each campaign, and information that can be collected from external sources, such as information on the internet, and may process the conversation with the information provider based on the accessed information and the content of the conversation exchanged with the information provider in the current conversation session.

[0044] Figure 4 is a flowchart showing an example of an information management method in one embodiment of the present invention. The information management method according to this embodiment may be executed by a computer device 200 that implements the information management system 310 described above. In this case, the processor 220 of the computer device 200 may be implemented to execute control instructions from the operating system code contained in the memory 210 and the code of at least one computer program. Here, the processor 220 may control the computer device 200 so that it executes steps 410 to 440 included in the method of Figure 4 in accordance with the control instructions provided by the code recorded in the computer device 200.

[0045] In step 410, the computer device 200 may provide a conversational information management function to information providers who intend to provide content to users of the search service. Here, the conversational information management function may correspond to the conversational information management center 350 described with reference to Figure 3. At this time, the computer device 200 may provide a function for registering assets for each campaign of the information provider through the conversational information management function. Such a function may include a function for the information provider to select a specific campaign and upload related assets in various formats to the information management system 310.

[0046] In step 420, the computer device 200 may use a conversational information management function to facilitate a conversation between the information provider and artificial intelligence based on Large Language Models (LLMs). For example, the computer device 200 may use artificial intelligence to generate conversational content to provide to the information provider, utilizing at least two of the following: the information provider's campaigns, the assets of each of the information provider's campaigns, the prompts of each of the information provider's campaigns, information collected from external sources, and the content of the conversation. Here, campaigns are generated for each purpose for which the information provider intends to provide content and may include assets and prompts for dynamically generating content for the corresponding purpose at the time of search. In this case, assets may include at least one of the following: a URL (Uniform Resource Locator) associated with the content the information provider intends to provide, the title of the content, the identifier of the content, the category of the content, multimedia associated with the content, the content of the content, and the content of articles associated with the content. Here, multimedia associated with the content may include images, videos, etc. associated with the content. The prompt may also include at least one of the following: a phrase entered by the informant to emphasize in relation to the content they intend to provide; keywords entered by the informant to emphasize in relation to the content they intend to provide; the tone of the informational message contained in the content; and the format of the informational message.

[0047] In step 430, the computer device 200 may analyze the conversation and manage the information provider's campaign. For example, the computer device 200 may generate a new campaign using at least one of the assets included in the information provider's pre-generated campaign and information collected externally in relation to the information provider. Another example is that the computer device 200 may modify the information provider's prompts registered in the information provider's pre-generated campaign based on the content of the conversation. Yet another example is that the computer device 200 may register a new prompt in the information provider's pre-generated campaign based on the content of the conversation.

[0048] Content provided to users through the search service may be dynamically generated at the time of the user's search using the assets and prompts of information providers registered for the corresponding campaign, and included in the search results.

[0049] Figures 5-10 show an example of a conversational information management center according to one embodiment of the present invention.

[0050] Figure 5 shows an example of the functionality of a conversational information management center 350 that allows information providers to register assets and manage the registered assets. The parent folders of the assets may correspond to campaigns, and each parent folder may contain subfolders. The first dotted box 510 shows a list of folders for the registered assets, and the second dotted box 520 shows a list of folders and files that are assets for the registered assets. Information providers can use the functions shown in Figure 5 to check and delete registered assets, and can also register new assets using buttons such as the "Upload" button. At this time, the functions shown in Figure 5 may include a user interface 540 for transmitting prompts to artificial intelligence, and conversations with the artificial intelligence can proceed through such a user interface 540. In the embodiment of Figure 5, an example is shown in which an information provider requests the artificial intelligence to organize folders and files. In this way, the information management system 310 can provide a variety of functions for managing the information provider's information, such as organizing the folders and files associated with the information provider's assets, based on conversations between the artificial intelligence of the conversational information management center 350 and the information provider.

[0051] Figure 6 shows an example of the functionality of a conversational information management center 350, which receives URLs as assets from an information provider and has a robot crawl and collect content corresponding to those URLs. For example, suppose an information provider enters URLs in the first area 610 of Figure 6. When the information provider selects the archive button 620, the robot crawls for each entered URL and collects information corresponding to that URL. In Figure 6, an example is shown where information regarding the number of URLs entered by the user is displayed on the button 620. URLs and the information collected through them may also be managed as assets of the information provider. In the embodiment of Figure 6, an example is shown where the information provider requests the artificial intelligence to classify URLs via the user interface 540. In this way, the information management system 310 can provide a variety of functions for managing the information provider's information, such as classifying similar URLs entered by the information provider into folders, based on the conversation between the artificial intelligence of the conversational information management center 350 and the information provider.

[0052] Figure 7 illustrates an example where artificial intelligence proactively communicates suggestions to an information provider. That is, the artificial intelligence of the conversational information management center 350 can not only provide responses to the information provider's prompts, but also proactively communicate campaign management and related suggestions to the information provider. Such suggestions may be generated based on the information provider's existing campaigns and the assets and / or prompts registered to those campaigns. The embodiment in Figure 7 shows an example where the information provider rejects the artificial intelligence's suggestion and requests the generation of a new campaign.

[0053] Figures 8-10 illustrate an example of the process by which artificial intelligence generates new campaigns based on conversations with information providers. The information management system 310 can generate conversation content to be provided to information providers by utilizing information collected from external sources (for example, the internet) in relation to the information provider's prompts (e.g., search results for the AAA brand SNKRS app), or by utilizing assets pre-registered by the information provider (e.g., information collected through URL-formatted assets, images in specific asset folders). The information management system 310 can also acquire and register the information provider's prompts, including phrases and keywords to be emphasized (for example, "AAA brand SNKRS," "community," "style") and / or the wording used when generating responses (for example, the information provider's content provided to users through the search service).

[0054] Figure 11 is an illustrative diagram illustrating the process of providing a response to a user prompt in one embodiment of the present invention. The embodiment in Figure 11 describes an example in which the information provider intends to publish an advertisement for an advertiser's product or service as the content to be provided.

[0055] The search system 320 may receive input from a user's terminal connected via the network 170 as a user prompt 1101. For example, the prompt may correspond to a natural language-based search term entered by the user. The user may enter the search term into the user interface of the search service provided through the user's terminal, and the search system 320 may receive the search term entered into the user interface as a user prompt 1101.

[0056] In this case, the search system 320 may select the prompt to actually use by analyzing the user prompts 1101, extracting and summarizing the user intent during the User Intent Extracting & Summarizing 1102 process.

[0057] On the other hand, the search system 320 may guide the user to provide sufficient information to provide an answer that reflects the advertiser's marketing message. For example, the content of the user prompt 1101 may be insufficient to match the marketing message of a particular advertiser. In this case, the search system 320 may generate a question to guide the user to provide additional information to select a particular advertiser, and may provide the generated question to the user. After the user provides an answer to the question, the system may use the content of this answer to supplement the prompt. The Question Specification Prompt 1103 may include a prompt derived from the user's answer.

[0058] At this time, the search system 320 may select a Specified User Prompt 1104 that has been designated as a prompt for providing a marketing message. That is, the designated user prompt 1104 may be specified based on the prompt obtained from the extraction and summarization of user intent 1102 for the user prompt 1101 and the question specification prompt 1103.

[0059] A Prompt Ads Safe Check 1105 may be an example of a process for verifying whether a given user prompt 1104 is a prompt that may disclose an advertiser's marketing message to the user. For example, the search system 320 may generate and provide a response if the given user prompt 1104 is not a prompt that requests pre-configured illegal information or pre-configured non-advertising information.

[0060] The search system 320 may also input the specified user prompt 1104 into the LLM to generate LLM results. Figure 11 shows an example of an Organic LLM Result Memory 1106 that records such LLM results.

[0061] The search system 320 may primarily select advertisers associated with LLM results based on the LLM results recorded in the organic LLM result memory 1106. In this case, advertisers associated with LLM results may be advertisers who have registered marketing messages that may be published together with the LLM results. Marketing messages that may be published together with the LLM results may be selected based on the relevance between the information registered by the advertiser and the LLM results. Depending on the embodiment, the search system 320 may also utilize at least one of the user prompt 1104, LLM results, and recommendation queries generated by the large language model when primarily selecting advertisers. In this case, the search system 320 may primarily select advertisers based on the relevance between the user prompt 1104, LLM results, and recommendation queries and the information registered by the advertiser. In this case, the search system 320 may select a specific advertiser from among the advertisers primarily selected by the Ad Prompt Auction 1107.

[0062] Once an advertiser is selected, the search system 320 retrieves advertising assets 1108 and advertiser prompts 1109 registered by the selected advertiser. Here, advertising assets 1108 and advertiser prompts 1109 may correspond to assets and prompts registered in the conversational information management center 350 for a particular campaign. In this case, the search system 320 may use user prompts 1101 and at least one LLM result recorded in the organic LLM result memory 1106, along with at least one of the advertising assets 1108 and advertiser prompts 1109, to generate an Answer Prompt 1110 that reflects the advertiser's marketing message. Depending on the embodiment, the advertiser may want to provide answers in a specific format depending on the user's characteristics. For this purpose, the search system 320 may generate the Answer Prompt 1110 by further reflecting information about the user. For example, information about the user may include at least one of the user's demos, interests, and purchase information. For example, suppose the search system 320 analyzes the advertiser prompt 1109 and understands that the advertiser wants female users to be provided with more detailed answers than male users. In this case, the search system 320 may determine the user's gender from the user demo and then generate the response prompt 1110 taking the determined user gender into consideration.

[0063] After the response prompt 1110 is generated, the search system 320 may verify whether the generated response prompt 1110 is generated in a manner that conforms to the tone and / or format confirmed from the advertiser prompt 1109. If the generated response prompt 1110 does not conform to the tone and / or format desired by the advertiser, the search system 320 may modify the response prompt 1110 to conform to the tone and / or format desired by the advertiser. Depending on the embodiment, the search system 320 may also perform additional verifications, such as whether the generated response prompt 1110 is safe to publish.

[0064] Subsequently, the search system 320 may add the finally generated answer 1112 to the search results and provide it to the user through the search service. Depending on the embodiment, user information recorded in the Data Management Platform (DMP) 1113 (e.g., gender, age, interests, etc.) may also be used when generating the answer prompt 1110. By utilizing such user information, the search system 320 can generate an answer 1112 optimized for the user.

[0065] Figure 12 is a diagram illustrating an example of providing search results in one embodiment of the present invention. Figure 12 shows an example of a search page 1200 screen provided to a user through a search service. The search page 1200 may include a user interface 1210 for entering user prompts. Furthermore, the search page 1200 may include a search results area 1220 for displaying search results. In this case, the search results area 1220 may include an LLM results area 1230 for displaying LLM results generated based on LLM in response to user prompts.

[0066] Furthermore, the search results area 1220 shows an example of an answer area 1240 that displays the answers generated by the search system 320 in response to the user prompt. In this embodiment, an example is shown in which multiple answers are displayed in the answer area 1240. Thus, it is possible for multiple answers to be generated and displayed in response to a single prompt. It is also possible for answers to be generated and displayed for two or more information providers. For this reason, the search system 320 may select two or more information providers.

[0067] On the other hand, the embodiment of Figure 12 shows an example in which the responses of an information provider selected based on user prompts entered into the user interface 1210 and / or LLM results displayed in the LLM results area 1230 are displayed in the extended area 1250. For example, the extended area 1250 may further display the responses of an information provider selected based on at least one of the user prompts, LLM results, and recommendation queries generated by the large language model. If the information provider is an advertiser, the extended area 1250 may further display advertisements from the advertiser selected based on at least one of the user prompts, LLM results, and recommendation queries generated by the large language model.

[0068] Furthermore, the dotted frame 1260 displays a question to request additional user prompts in relation to the answer displayed in the extended area 1250. If the user selects a specific question, this question may be recognized as an additional user prompt. When providing a conversational search service, the additional user prompt may be recognized as the user's next conversation. In this case, the search system 320 may generate LLM results and / or answers considering the entire conversation with the user.

[0069] Thus, according to embodiments of the present invention, a method and system for managing information of an information provider based on conversations with the information provider can be provided.

[0070] The systems or devices described above may be implemented by hardware components, or by a combination of hardware and software components. For example, the devices 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.

[0071] 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, virtual equipment, computer recording medium, or device for interpretation based on the processing unit or for providing instructions or data to the processing unit. Software may be distributed across a network of computer systems, and may be recorded or executed in a distributed manner. Software and data may be recorded on one or more computer-readable recording media.

[0072] The methods according to the embodiment may be implemented in the form of program instructions executable by various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., individually or in combination. The medium may continuously record computer-executable programs or may temporarily record them for execution or download. The medium may also be a variety of recording or storage means in the form of a combination of one or more hardware components, and may be a medium directly connected to a computer system or distributed on a network. Examples of media 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 media configured to record program instructions such as ROMs, RAMs, and flash memories. Other examples of media include recording media and storage media managed by app stores that distribute applications, and sites and servers that supply and distribute various other software. Examples of program instructions include not only machine code such as that generated by a compiler, but also high-level language code that is executed by a computer using an interpreter or the like.

[0073] 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.

[0074] Therefore, even if the embodiment is different, it falls within the scope of the attached claims if it is equivalent to the claims. [Explanation of Symbols]

[0075] 310: Information Management System 320: Search System 330: User 340:Informant 350: Conversational Information Management Center

Claims

1. A method for managing information in a computer device including at least one processor, The aforementioned at least one processor provides conversational information management functionality to information providers who intend to provide content to users of the search service, The at least one processor facilitates a conversation between the information provider and the artificial intelligence based on a Large Language Model (LLM) through the conversational information management function, This includes analyzing the aforementioned conversation and managing the information provider's campaign, Providing the aforementioned conversational information management function means The aforementioned conversational information management function provides a function for registering assets for each campaign of the information provider, An information management method comprising organizing folders or files associated with registered assets based on a request from the information provider to organize the registered assets during a conversation between the artificial intelligence and the information provider.

2. To continue the aforementioned conversation, The information management method according to claim 1, comprising using the artificial intelligence to generate conversation content to be provided to the information provider, using at least two of the following: the information provider's campaigns, the assets of each of the information provider's campaigns, the prompts of each of the information provider's campaigns, information collected from external sources, and the conversation content.

3. The information management method according to claim 2, wherein the asset includes at least one of the following: a URL (Uniform Resource Locator) associated with the content that the information provider intends to provide, the title of the content, the identifier name of the content, the category of the content, multimedia associated with the content, the content of the content, and the content of an article associated with the content.

4. The information management method according to claim 2, wherein the prompt includes at least one of a phrase entered to be emphasized in relation to the content that the information provider intends to provide, a keyword entered to be emphasized in relation to the content that the information provider intends to provide, the tone of an information message contained in the content, and the format of the information message.

5. The information management method according to claim 1, wherein the campaign is generated for each purpose for which the information provider intends to provide content, and includes assets and prompts for dynamically generating the content for the corresponding purpose at the time of search.

6. Managing the aforementioned campaign is The information management method according to claim 1, comprising generating a new campaign using at least one of the assets included in a pre-generated campaign of the information provider and information collected from external sources related to the information provider.

7. Managing the aforementioned campaign is The information management method according to claim 1, comprising modifying the information provider's prompt registered in the information provider's pre-generated campaign based on the content of the conversation.

8. Managing the aforementioned campaign is The information management method according to claim 1, comprising registering a new prompt in a pre-generated campaign of the information provider based on the content of the conversation.

9. The information management method according to claim 1, wherein the content provided to the user through the search service is dynamically generated at the time of the user's search and included in the search results, using the assets and prompts of the information provider registered for the corresponding campaign.

10. A computer program for causing the computer device to perform the method described in any one of claims 1 to 9.

11. It includes at least one processor implemented to execute instructions readable by a computer device, With the aforementioned at least one processor, To provide conversational information management functions to information providers who wish to provide content to users of the search service, The aforementioned conversational information management function facilitates a conversation between the information provider and the artificial intelligence based on Large Language Models (LLM), The following actions are taken: Analyze the aforementioned conversation and manage the information provider's campaign; Providing the aforementioned conversational information management function means The aforementioned conversational information management function provides a function for registering assets for each campaign of the information provider, A computer device comprising: organizing folders or files associated with registered assets based on a request from the information provider to organize the registered assets during a conversation between the artificial intelligence and the information provider.

12. In order to advance the aforementioned conversation, at least one processor, The computer device according to claim 11, wherein the artificial intelligence generates conversation content to be provided to the information provider, using at least two of the following: the information provider's campaigns, the assets of each of the information provider's campaigns, the prompts of each of the information provider's campaigns, information collected from external sources, and the conversation content.

13. To manage the campaign, at least one processor is used: To generate a new campaign using at least one of the pre-generated campaign assets of the aforementioned information provider and information collected externally in connection with the aforementioned information provider, Based on the content of the aforementioned conversation, modify the prompts registered in the information provider's pre-generated campaign, or The computer device according to claim 12, which registers a new prompt to the pre-generated campaign based on the content of the conversation.

Images