Method and system for managing information of information provider based on conversation with information provider

Abstract

This invention discloses a method and system for managing information provider information based on dialogue with the information provider. One embodiment of the information management method may include the following steps: providing a conversational information management function to an information provider that provides content to users of a search service; enabling dialogue between the information provider and an artificial intelligence based on Large Language Models (LLM) through the conversational information management function; and analyzing the dialogue to manage the activities of the information provider.

Description

Method and System for Managing Information of an Information Provider Based on a Conversation with the Information Provider The following description relates to a method and system for managing information of an information provider based on a conversation with the information provider. A large language model or large language model (LLM) is an artificial intelligence trained in a large-scale text dataset to generate human-like responses to natural language inputs. It is a language model composed of an artificial neural network with numerous parameters (usually more than billions of weights). Such large language models can be trained on large amounts of unlabeled text using self-supervised learning or semi-self-supervised learning. Prior Art Documents Korean Patent No. 10-2551531 The present invention provides a method and system for managing information of an information provider based on a conversation with the information provider. The present invention provides an information management method. The information management method is an information management method of a computer device including at least one processor. The information management method includes the following steps: providing, through at least one of the processors, a conversational information management function to an information provider who provides content to a user of a search service; enabling, through at least one of the processors, a conversation between an artificial intelligence based on a large language model (LLM) and the information provider through the conversational information management function; and analyzing the conversation to manage the activities of the information provider. According to one embodiment, the present invention is characterized in that the step of providing the conversational information management function may include the step of providing, through the conversational information management function, a function for registering each activity asset of the information provider. According to another embodiment, the present invention is characterized in that, in the step of conducting the conversation, the artificial intelligence may use at least two of the activities of the information provider, each activity asset of the information provider, each activity prompt of the information provider, information received from the outside, and the content of the conversation to generate the content of the conversation provided to the information provider. According to another embodiment, the present invention is characterized in that the asset may include at least one of a uniform resource locator (URL) related to the content provided by the information provider, a title of the content, an identifier of the content, a category of the content, multimedia related to the content, the content of the content, and the content of a report related to the content. According to yet another embodiment, the present invention is characterized in that the above prompt includes at least one of a sentence emphasizing the input related to the content provided by the above information provider, a keyword emphasizing the input related to the content provided by the above information provider, the tone of the information message included in the above content, and the format of the above information message. According to yet another embodiment, the present invention is characterized in that the above activity may include generating assets and prompts for the corresponding purpose at the search time point for the purpose of the content provided by the above information provider and used to dynamically generate the above content for the corresponding purpose. According to yet another embodiment, the present invention is characterized in that the step of managing the above activity may include the step of generating a new activity by using at least one of the assets of the generated activity of the above information provider and the information received from the outside related to the above information provider. According to yet another embodiment, the present invention is characterized in that the step of managing the above activity may include the step of modifying the prompt of the above information provider registered in the generated activity of the above information provider based on the content of the above conversation. According to yet another embodiment, the present invention is characterized in that the step of managing the above activity may include the step of registering a new prompt in the generated activity of the above information provider based on the content of the above conversation. According to yet another embodiment, the present invention is characterized in that the above content provided to the above user through the above search service can be dynamically generated at the search time point of the above user by using the assets and prompts of the above information provider registered for the corresponding activity and included in the search results. The present invention provides a computer-readable recording medium recording a program useful for running the above method in a computer device. The present invention provides a computer device, which is characterized in that it includes at least one processor for running computer device-readable instructions, and through at least one of the above processors, provides a dialog-type information management function to an information provider, the above information provider provides content to a user of a search service, and through the above dialog-type information management function, a dialog is carried out between artificial intelligence based on a large language model and the above information provider, and the above dialog is analyzed to manage the activity of the above information provider. The present invention can provide a method and a system for managing information of an information provider based on a conversation with the information provider. Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. The information management system according to an embodiment of the present invention can be implemented by at least one computer device. In this case, a computer program according to an embodiment of the present invention can be set and driven in the computer device that implements the information management system, and the computer device can execute the information management method according to an embodiment of the present invention under the control of the driven computer program. The above computer program can be combined with the computer device and can be stored in a computer-readable recording medium in order to run the information management method on the computer. FIG. 1 is a diagram showing an example of a network environment according to an embodiment of the present invention. The network environment of FIG. 1 shows an example including a plurality of electronic devices 110, 120, 130, 140, a plurality of servers 150, 160, and a network 170. The above FIG. 1 is an example for explaining the present invention, and the number of electronic devices or the number of servers is not limited to FIG. 1. The plurality of electronic devices 110, 120, 130, 140 can be fixed terminals or mobile terminals embodied by a computer system. For example, the plurality of electronic devices 110, 120, 130, 140 include smart phones, mobile phones, navigators, computers, laptop computers, digital broadcast terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), tablet computers, game consoles, wearable devices, Internet of Things (IoT) devices, virtual reality (VR) devices, augmented reality (AR) devices, etc. As an example, the shape of a smart phone is shown as an example of the electronic device 110 in FIG. 1, but in an embodiment of the present invention, the electronic device 110 can substantially be one of various physical computer systems that communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 through the network 170 using wireless or wired communication methods. The communication method is not limited and may include communication methods using communication networks that the network 170 may include (for example, mobile communication networks, wired networks, wireless networks, broadcast networks, satellite networks, etc.) and wireless communication between multiple devices. For example, the network 170 may include any one or more of networks such as a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), and the Internet. Also, the network 170 may include any one or more of network topologies such as a bus network, a star network, a ring network, a mesh network, a star bus network, a tree network, and a hierarchical network, but is not limited thereto. The servers 150 and 160 may be computer devices or multiple computer devices that communicate with the multiple electronic devices 110, 120, 130, and 140 through the network 170 to provide instructions, codes, files, content, services, etc. For example, the server 150 may be a system that provides a first service to the multiple electronic devices 110, 120, 130, and 140 accessing through the network 170, and the server 160 may also be a system that provides a second service to the multiple electronic devices 110, 120, 130, and 140 accessing through the network 170. As a more specific example, the server 150 may provide, as the first service, services (such as a search service, for example) required by an application, which is a computer program installed on the multiple electronic devices 110, 120, 130, and 140, to the multiple electronic devices 110, 120, 130, and 140. As another example, the server 160 may provide, as the second service, a service of distributing files for setting up and driving the above application to the multiple electronic devices 110, 120, 130, and 140. FIG. 2 is a block diagram for explaining an example of a computer device according to an embodiment of the present invention. The multiple electronic devices 110, 120, 130, and 140 or the multiple servers 150 and 160 described above may be respectively implemented by the computer device 200 shown in FIG. 2. As shown in FIG. 2, such a computer device 200 may include a storage 210, a processor 220, a communication interface 230, and an input / output interface 240. The storage 210, as a computer-readable recording medium, may include non-volatile mass storage devices such as random access memory (RAM), read only memory (ROM), and hard disk drives. Among them, non-volatile mass storage devices such as read only memory and hard disk drives are separate permanent storage devices distinguished from the storage 210 and may be formed in the computer device 200. Also, the storage 210 may store an operating system and at least one program code. The above software components may be loaded into the storage 210 from a separate computer-readable recording medium separated from the storage 210. The above separate computer-readable recording medium may include computer-readable recording media such as floppy disk drives, magnetic disks, magnetic tapes, DVD / CD-ROM drives, and memory cards. In another embodiment, the software components are loaded into the storage 210 not through a computer-readable recording medium but through the communication module 230. For example, the software components may be loaded into the storage 210 of the computer device 200 based on a computer program set by a file received through the network 170. The processor 220 may perform basic calculations, logic, and input / output calculations, thereby processing the instructions of a computer program. The instructions may be provided to the processor 220 through the storage 210 or the communication interface 230. For example, the processor 220 may execute the received instructions according to the program code stored in a storage device such as the storage 210. The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (as an example, the storage device described above) through the network 170. As an example, the processor 220 of the computer device 200 may cause requests or instructions, data, files, etc. generated according to the program code stored in a recording device such as the storage 210 to be transmitted to other devices through the network 170 under the control of the communication interface 230. Conversely, signals, instructions, data, files, etc. from other devices may pass through the network 170 and be transmitted to the computer device 200 through the communication interface 230 of the computer device 200. Signals, instructions, data, etc. received through the communication interface 230 may be transmitted to the processor 220 or the storage 210, and files, etc. may be stored in the storage medium (the above permanent storage device) that the computer device 200 may also include. The input / output interface 240 may be a unit for an interface with an input / output device 250. For example, the input device may include devices such as a microphone, a keyboard, or a mouse, and the output device may include devices such as a display or a speaker. As another example, the input / output interface 240 may also be a unit for an interface with a device in which functions for input and output, such as a touch screen, are integrated. The input / output device 250 may be configured as one device with the computer device 200. Moreover, in another embodiment, the computer device 200 may include more components than those in FIG. 2. However, most of the components of the prior art do not need to be explicitly shown. For example, the computer device 200 includes at least a part of the above-described input / output device 250, or may further include other components such as a transceiver and a database. FIG. 3 is a diagram showing an example of a brief state of an information management system according to an embodiment of the present invention. FIG. 3 shows an information management system 310, a search system 320, a plurality of users 330, a plurality of information providers 340, and a dialog-type information management center 350. The search system 320 may correspond to a server that provides a search service to a plurality of users 330 (as an example, the server 150), and may be implemented as at least one computer device 200. Among them, each user 330 may be a physical device of a user who can access the search system 320 through the network 170 in order to receive the search service. The plurality of information providers 340 may be physical devices of information providers who respectively register the information they provide with the information management system 310. Among them, the physical device may be implemented as the computer device 200 described above. The information management system 310 of the present embodiment may be included in the search system 320 or may be linked with the search system 320 through the network 170. An example of a form in which the information management system 310 is included in the search system 320 is shown in the embodiment of FIG. 3. In this case, the information management system 310 may be formed on at least one physical device for implementing the search system 320. According to an embodiment, the information management system 310 is a separate physical device separated from the physical device implementing the search system 320, and thus may communicate with the search system 320 through the network 170. The search service provided by the search system 320 to the plurality of users 330 may include search results corresponding to user input. The search results may be basically generated based on information that can be searched on the network. Moreover, the search system 320 may include the information provided by the plurality of information providers 340 in the search results to provide the search service. Among them, the information provided by the plurality of information providers 340 may be advertising information, but is not limited thereto. Since the search service itself that provides such search results is known, a detailed description thereof will be omitted. On the other hand, the search system 320 of this embodiment can include answers based on artificial intelligence such as large language models or large-scale language models in the search results to provide search services. For example, the search system 320 can receive a natural language-based prompt from a specific user among multiple users 330. In this case, the search system 320 can input the received prompt into a large language model to generate a first answer that conforms to the prompt as the result of the large language model, and can provide the search results including the first answer to the user. In this case, the search results can include at least a part of the existing various search results other than the first answer. Also, the search system 320 can provide a search service through a dialogue between artificial intelligence based on a large language model and the user. The first mode of providing the first answer as the result of the large language model through general search services and the second mode of providing the first answer as the result of the large language model through a dialogue between artificial intelligence based on the large language model and the user can be converted into each other and provide search services to the user. In this case, in the first mode and the second mode, at least a part of the first answer can also provide an example of the content for the information provider as the second answer. Also, the search results can include a second answer generated from at least a part of the information registered by multiple information providers 340. For example, the search system 320 can dynamically generate an artificial intelligence-based second answer that projects the information provider message selected from multiple information providers 340. In this case, the search system 320 can provide the search results including the first answer generated using a large language model and the artificial intelligence-based second answer to the user. In this case, in the process of generating the AI-based second answer, the search system 320 does not simply directly provide the information provided by the information provider, but can dynamically form the AI-based second answer by using user prompts, the first answer generated by using a large language model, the assets registered by the information provider, and / or the prompts registered by the information provider. Among them, as an example, the assets may include a uniform resource locator related to the first information provided by the information provider, the title or identifier of the first information, the category of the first information, the content of the first information, the content of the report related to the first information, etc. For example, when the information provider is an advertiser advertising a specific product or service, the assets may include a uniform resource locator related to the product or service, the product name or service name, the category of the product or service, the product information or service information, the content of the report related to the product or service, etc. And the prompts registered by the information provider may include sentences or keywords emphasized by the information provider in relation to the first information, information related to the tone or format of the information message provided as the second answer, etc. As described above, the search system 320 can dynamically generate a second answer that takes into account the first answer generated by using a large language model for a user's natural language-based prompt, the assets and prompts registered by the information provider providing its own information, and the first answer. And according to an embodiment, the search system 320 can also use information related to the user to generate the second answer. Among them, the information related to the user may include the user's profile, interests, purchase information, etc., and can be used to customize the second answer for the user. Moreover, there may be multiple information providers 340 that need to display their own information. Therefore, the search system 320 can dynamically determine which information provider's assets and prompts among the multiple information providers 340 to use to generate the second answer. As an example, the search system 320 can first select, based on the first answer among the multiple information providers 340, in other words, the multiple information providers related to the large language model results. According to an embodiment, in the process of first selecting an information provider, the search system 320 can use at least one of user prompts, large language model results, and recommended questions generated by using the large language model. After that, the search system 320 can dynamically conduct an auction among the multiple information providers selected for the first time to select the first information provider as the information provider used to generate the second answer. The auction method can use one of the known methods. For example, the generalized second price (GSP) auction method can be used. As described above, in the process of the search system 320 providing an answer related to a natural language prompt from a user, it can dynamically generate an answer based on the assets and prompts of the information provider. In other words, it dynamically generates an AI-based second answer that projects the information provider's message. Therefore, the search system 320 can provide the user with a dynamically generated answer to project the information provider's message in relation to the natural language prompt received from the user. In this case, the information management system 310 can provide a conversational information management center 350 for managing information used to generate content provided by multiple information providers 340 to multiple users 330 through search services respectively. As an example, such a conversational information management center 350 can be in the form of a web page provided to the information provider, but is not limited thereto. The information management system 310 interacts with the information provider accessing the conversational information management center 350 through the network 170 in a conversational form and manages the information used to generate the content provided by the corresponding information provider through the search system 320. As an example, through a conversation with the AI provided by the conversational information management center 350, the information provider can generate activities for the purpose of providing content. Each activity can register the assets and prompts described above. For example, the information provider can generate activities for various purposes required by the information provider. For example, generate activities related to a specific event, or generate activities related to the download of a specific application, etc., and can register the assets and prompts related to each generated activity according to the activity. For this purpose, the conversational information management center 350 can provide a list of multiple activities generated by the information provider and the function for the information provider to register assets for each activity. On the other hand, the prompts of the information provider can be automatically registered by analyzing the conversation between the AI and the information provider through the conversational information management center 350. For example, the information management system 310 can interact with the information provider in a conversational form using AI through the conversational information management center 350 and manage the activities of the information provider, such as improving existing activities or generating new activities. Among them, the AI can include a conversational AI based on a large language model. Such a conversational AI can access information that can be received from the outside, such as activities pre-registered for the information provider, the assets and prompts of each activity, and information on the network, and can process the conversation with the information provider based on the accessed information and the conversation content exchanged with the information provider through the current conversation session. FIG. 4 is a flowchart showing an example of the information management method according to an embodiment of the present invention. The information management method of this embodiment can be executed by the computer device 200 that implements the information management system 310 described above. In this case, the processor 220 of the computer device 200 can run the code of the operating system or control instructions (instructions) based on at least one computer program code. Among them, the processor 220 can control the computer device 200 according to the control instructions provided by the code stored in the computer device 200, so that the computer device 200 executes multiple steps (steps 410 to step 430) included in the method of FIG. 4. In step 410, the computer device 200 can provide a conversational information management function to the information provider, and the above information provider can provide content to the user of the search service. Among them, the conversational information management function can correspond to the conversational information management center 350 described in FIG. 3 above. In this case, the computer device 200 can provide a function of registering each active asset of the information provider through the conversational information management function. Such a function can include the function that the information provider selects a specific activity to upload various forms of related assets to the information management system 310. In step 420, the computer device 200 can enable a conversation between the artificial intelligence based on the large language model and the information provider through the conversational information management function. As an embodiment, the computer device 200 can use at least two of the activities of the information provider, each active asset of the information provider, each active prompt of the information provider, the information collected from the outside, and the content of the conversation to generate the content of the conversation provided to the information provider through artificial intelligence. Among them, the activity can include generating according to the purpose of the content provided by the information provider, and dynamically generating assets and prompts corresponding to the purpose at the search time point. In this case, the asset can include at least one of a uniform resource locator related to the content that the information provider needs to provide, the title of the content, the identifier of the content, the category of the content, the multimedia related to the content, the content of the content, and the content of the report related to the content. Among them, the multimedia related to the content can include images, videos, etc. related to the content. And the prompt can include at least one of a sentence emphasizing the input related to the content provided by the information provider, a keyword emphasizing the input related to the content provided by the information provider, the tone of the information message included in the content, and the format of the information message. In step 430, the computer device 200 may analyze the conversation to manage the activities of the information provider. As an example, the computer device 200 may include at least one of the assets of the information provider's generated activities and the information received from the outside related to the information provider to generate new activities. As another embodiment, the computer device 200 may modify the prompts of the information provider registered in the information provider's generated activities based on the content of the conversation. As another example, the computer device 200 may register new prompts in the information provider's generated activities based on the content of the conversation. The content provided to the user through the search service can be dynamically generated and included in the search results at the user's search time point by using the assets and prompts of the information provider registered for the corresponding activity. FIGS. 5 to 10 are diagrams showing examples of a dialogue-type information management center in an embodiment of the present invention. FIG. 5 shows an example of the functions of a dialogue-type information management center 350 where an information provider registers assets and can manage the registered assets. The upper-level folder of the assets may correspond to an activity, and each upper-level folder may also include lower-level folders. The first dashed box 510 represents a list of multiple folders related to the registered assets, and the second dashed box 520 represents a list of multiple folders related to the registered assets and multiple folders as assets. The information provider can use the functions shown in FIG. 5 to confirm or delete the registered assets, and can also register new assets through a "upload" button 530 or the like. In this case, the functions shown in FIG. 5 may include a user interface 540 for transmitting prompts to the artificial intelligence, and a conversation with the artificial intelligence can be carried out through such a user interface 540. An example where the information provider requests the artificial intelligence to organize folders and files is shown in the embodiment of FIG. 5. As described above, the information management system 310 can provide various functions for managing the information of the information provider, such as organizing folders and files related to the assets of the information provider based on the conversation between the artificial intelligence and the information provider in the dialogue-type information management center 350. FIG. 6 shows an example of the functions of the conversational information management center 350 that receives a uniform resource locator as an asset from an information provider and collects content corresponding to the uniform resource locator through robot crawling. For example, the first area 610 in FIG. 6 shows examples of multiple uniform resource locators input by the information provider. In this case, when the information provider selects the button 620 for archiving, robot crawling is performed for each of the multiple input uniform resource locators to collect information corresponding to the uniform resource locator. On the other hand, FIG. 6 shows an example of information related to the quantity related to the uniform resource locator input by the user being displayed on the button 620. The uniform resource locator and the information collected through the uniform resource locator can also be managed as the assets of the information provider. In the embodiment of FIG. 6, an example is shown in which the information provider requests classification of multiple uniform resource locators from the artificial intelligence through the user interface 540. As described above, the information management system 310 can provide various functions for managing the information of the information provider, such as classifying multiple uniform resource locators input by the information provider according to similar uniform resource locators based on the conversation between the artificial intelligence of the conversational information management center 350 and the information provider. FIG. 7 shows an example in which the artificial intelligence preferentially delivers proposals to the information provider. That is, the artificial intelligence of the conversational information management center 350 does not simply provide answers to the prompts of the information provider. Instead, first, it can also deliver proposals related to the management of activities to the information provider. Such proposals can be generated based on the existing activities of the information provider and the assets registered in the activities and / or prompts. In the embodiment of FIG. 7, an example is shown in which the information provider rejects the proposal of the artificial intelligence and requests the generation of a new activity. FIGS. 8 to 10 are diagrams showing examples of the process in which the artificial intelligence generates a new activity through a conversation with the information provider. The information management system 310 can use information collected from the outside (as an example, the Internet) related to the prompts of the artificial intelligence and the information provider (search results of the AAA brand SNKRS application) or the assets registered by the information provider (information collected through assets in the form of uniform resource locators, multiple images in a specific asset folder) to generate the conversation content provided to the information provider. And the information management system 310 can also obtain the prompts of the information provider related to the tone, etc. when generating sentences or keywords that need to be emphasized (as an example, "AAA brand SNKRS", "community", "style") and / or answers (as an example, the content of the information provider provided to the user through the search service) for registration. FIG. 11 is a diagram for explaining an example of the process of providing an answer to a user prompt in an embodiment of the present invention. In the embodiment of FIG. 11, an example is described in which an advertisement related to the goods or services of an advertiser is displayed as the information to be provided by multiple information providers. The search system 320 can receive a user prompt 1101 from a user terminal accessed via the network 170. As an example, the prompt can correspond to a search term based on the natural language input by the user. The user can input a search term through the user interface of the search service provided by the user terminal, and the search system 320 can receive the search term input through the user interface as the user prompt 1101. In this case, the search system 320 can analyze the user prompt 1101 through the user intent extracting & summarizing 1102 process to extract and summarize the user intent, thereby selecting the actually used prompt. On the other hand, the search system 320 can guide the user to provide sufficient information for providing an answer that reflects the marketer's marketing message. As an example, the content of the user prompt 1101 may not be sufficient to match the marketing message of a specific advertiser. In this case, the search system 320 can generate a question that guides additional information, where the additional information is used to select a specific advertiser, and can provide the generated question to the user. After that, when receiving the user's answer to the question, the content of the received answer can be used to supplement the prompt. The question specification prompt 1103 can include the prompt obtained through the user's answer. In this case, the search system 320 can select a specified user prompt 1104 as the prompt for providing the marketing message. In other words, the specified user prompt 1104 can be specified based on the prompt obtained through the user intent extracting & summarizing 1102 of the user prompt 1101 and the question specification prompt 1103. The prompt ads safe check 1105 can be an example of a process for verifying whether the specified user prompt 1104 is a prompt suitable for displaying the marketer's marketing message to the user. As an example, when the specified user prompt 1104 is not a prompt that requests preset illegal information or preset non - advertising information, the search system 320 can generate and provide an answer. Moreover, the search system 320 can input the specified user prompt 1104 to a large language model to generate a large language model result. An example of an organic large language model result memory 1106 for storing such large language model results is shown in FIG. 11. The search system 320 can first select an advertiser related to the large language model results based on the large language model results stored in the organic large language model result storage 1106. In this case, the advertiser related to the large language model results can be an advertiser who registers a marketing message to be displayed together with the large language model results. The marketing message to be displayed together with the large language model results can be selected based on the relevance between the information registered by the advertiser and the large language model results. And, according to an embodiment, during the process of the search system 320 first selecting an advertiser, at least one of the specified user prompt 1104, the large language model results, and the recommended questions generated by the large language model can be utilized. In this case, the search system 320 can first select an advertiser based on the relevance between at least one of the specified user prompt 1104, the large language model results, and the recommended questions and the information registered by the advertiser. In this case, the search system 320 can select a specific advertiser from the advertisers first selected through the ad prompt auction 1107. When selecting an advertiser, the search system 320 can obtain the advertising assets 1108 registered by the selected advertiser and the advertiser prompts 1109 registered by the selected advertiser. Among them, the advertising assets 1108 and the advertiser prompts 1109 can correspond to the assets and prompts registered through the dialog information management center 350 for a specific activity. In this case, the search system 320 can utilize at least one of the user prompt 1101 and the large language model results stored in the organic large language model result storage 1106 and at least one of the advertising assets 1108 and the advertiser prompts 1109 to generate an answer prompt 1110 that reflects the advertiser's marketing message. According to an embodiment, the advertiser may expect to provide an answer in a specific format based on user characteristics. For this purpose, the search system 320 can also reflect information related to the user to generate the answer prompt 1110. As an example, the information related to the user can include at least one of the user's demographics, interests, and purchase information. For example, the search system 320 can analyze the advertiser prompt 1109 to grasp that the advertiser hopes to provide a relatively more detailed content answer to female users than male users. In this case, after the search system 320 grasps the user's gender through the user demographics, it can consider the grasped user gender to generate the answer prompt 1110. After generating the answer prompt 1110, the search system 320 can confirm whether the generated answer prompt 1110 conforms to the confirmed tone and / or format 1111 through the advertiser prompt 1109. When the generated answer prompt 1110 does not match the tone and / or format required by the advertiser, the answer prompt 1110 can be processed to conform to the tone and / or format required by the advertiser. Also, according to an embodiment, the search system 320 can additionally confirm, for example, whether the generated answer prompt 1110 is safe for display. After that, the search system 320 can add the finally generated answer 1112 (Answer) to the search results and provide it to the user through the search service. Also, according to an embodiment, the generation of the answer prompt 1110 can also utilize user information (as an example, gender, age, interests, etc.) stored in the data management platform 1113 (DMP, Data Management Platform). By using such user information, the search system 320 can generate an answer 1112 optimized for the user. FIG. 12 is a diagram showing an example of providing search results according to an embodiment of the present invention. FIG. 12 shows a screen example of a search page 1200 provided to the user through the search service. The search page 1200 may include a user interface 1210 for receiving user prompts. Also, the search page 1200 may include a search result area 1220 for displaying search results. In this case, the search result area 1220 may include a large language model result area 1230 for displaying large language model results generated for the user prompt based on the large language model. Also, the search result area 1220 represents an example of an answer area 1240 where answers generated by the search system 320 are displayed for the user prompt. An example of displaying multiple answers through the answer area 1240 is shown in this embodiment. As described above, multiple answers can also be generated and displayed for one prompt. Also, multiple answers can be generated and displayed for two or more information providers. To this end, the search system 320 can select two or more information providers. On the other hand, in the embodiment of FIG. 12, an example is shown in which answers from information providers selected based on the user prompt input to the user interface 1210 and / or the large language model results displayed in the large language model result area 1230 are displayed through the expansion area 1250. For example, answers from information providers selected based on at least one of the user prompt, the large language model result, and the recommended questions generated by the large language model can also be displayed through the expansion area 1250. When the information provider is an advertiser, advertisements from the advertiser selected based on at least one of the user prompt, the large language model result, and the recommended questions generated by the large language model can also be displayed in the expansion area 1250. Also, the dashed box 1260 may display multiple questions of additional prompts for the user in need related to the answers displayed in the extended area 1250. When the user selects a specific question, the corresponding question can be identified as the user's additional prompt. When providing a conversational search service, the user's additional prompt can be identified as the user's next conversation. In this case, the search system 320 may generate large language model results and / or answers considering the user's entire conversation. As described above, according to an embodiment of the present invention, the present invention can provide a method and system for managing messages of an information provider based on a conversation with the information provider. The systems or devices described above may be implemented as hardware components, software components, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device that can execute and respond to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the above operating system. Also, the processing device may also access, store, operate, process, and generate data in response to the execution of software. For ease of understanding, the processing device may be described as using one element, but those of ordinary skill in the art can understand that the processing device includes multiple processing elements and / or various types of processing elements. For example, the processing device may include multiple processors or include one processor and one controller. Also, other processing configurations such as a parallel processor are also feasible. Software may include a computer program, code, instructions, or a combination of more than one of them, and may configure a processing device to operate as needed, or independently or collectively command the processing device. Software and / or data may be embodied as any type of machine, component, physical device, virtual equipment, computer storage medium or device, so as to be interpreted by the processing device or provide instructions or data to the processing device. Software may be distributed on a networked computer system and stored or executed in a distributed manner. Software and data may be stored in more than one computer-readable recording medium. The method according to an embodiment can be implemented in the form of program instructions executable by various computer devices and recorded in a computer-readable medium. The above computer-readable medium may include one or more program instructions, digital files, data structures, etc. The medium may continue to store a computer-executable program or may temporarily store it for running or downloading. And the medium may be various technical units or storage units in the form of a single or multiple software combinations, and is not limited to the medium directly connected to the computer system, and may also be distributed on the network. Examples of the medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices such as ROM, RAM, and flash memory dedicated to storing and executing program instructions. And other examples of the medium may include an application store that distributes application programs or a website that supplies or distributes other various software, a recording medium managed by a server, or a magnetic storage medium. The form of program instructions includes not only machine language code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter, etc. As described above, although the description is made with reference to limited embodiments and drawings, those skilled in the art can make various modifications and improvements based on the above description. For example, performing the technology in a sequence different from the described method, and / or combining or assembling the components of the system, structure, device, circuit, etc. in a form different from the described method, or other components or even being replaced or substituted by equivalent technical solutions can also achieve appropriate results. Therefore, other embodiments, other examples, and content equivalent to the scope of the patent application of the present invention also fall within the protection scope of the present invention. 110, 120, 130, 140: Electronic devices 150, 160: Servers 170: Network 200: Computer device 210: Storage 220: Processor 230: Communication interface 240: Input / output interface 250: Input / output device 310: Information management system 320: Search system 330: User 340: Information provider 350: Dialog-based information management center 410, 420, 430: Steps 510: First dashed box 520: Second dashed box 530: Button 540: User interface 610: First area 620: Button 1101: User prompt 1102: User intention extraction and summary 1103: Problem specification prompt 1104: Specified user prompt 1105: Prompt advertisement security confirmation 1106: Organic large language model result storage 1107: Advertisement prompt auction 1108: Advertisement asset 1109: Advertiser prompt 1110: Answer prompt 1111: Confirm tone and / or format 1112: Answer 1113: Data management platform 1200: Search page 1210: User interface 1220: Search result area 1230: Large language model result area 1240: Answer area 1250: Expansion area 1260: Dashed box FIG. 1 is a diagram showing an example of a network environment according to an embodiment of the present invention. FIG. 2 is a block diagram showing an example of a computer device according to an embodiment of the present invention. FIG. 3 is a diagram showing an example of a brief state of an information management system according to an embodiment of the present invention. FIG. 4 is a flowchart showing an example of an information management method according to an embodiment of the present invention. FIGS. 5 to 10 are diagrams showing an example of a dialog-based information management center according to an embodiment of the present invention. FIG. 11 is a diagram for explaining an example of a process of providing an answer to a user prompt according to an embodiment of the present invention. FIG. 12 is a diagram showing an example of providing search results according to an embodiment of the present invention. 410, 420, 430: Steps

Claims

1. An information management method, comprising a computer device with at least one processor, wherein, The aforementioned information management method includes the following steps: providing a conversational information management function to an information provider through at least one processor, the information provider providing content to users of the search service; enabling a dialogue between artificial intelligence based on a large language model and the information provider through the conversational information management function via the at least one processor; and analyzing the dialogue to manage the activities of the information provider through the at least one processor; wherein providing the conversational information management function includes the following steps: providing a function for registering each activity asset of the information provider through the conversational information management function; wherein managing the activities of the information provider includes modifying the prompts input by the information provider for the activity based on the dialogue between the conversational information management function and the large language model, and registering the modified prompts to the activity; wherein the content provided to the user through the search service is dynamically generated at the user's search time using the information provider's registered assets, the modified prompts, and a first answer, and included in the search results, wherein the first answer is generated using a large language model for the user's natural language prompts; The prompts provided by the information provider for the above-mentioned activities include at least one of the following: sentences that emphasize input related to the content provided by the information provider, keywords that emphasize input related to the content provided by the information provider, the tone of the information message included in the above-mentioned content, and the format of the information message.

2. The information management method as described in request item 1, wherein, In the steps of conducting the above dialogue, the dialogue content provided to the information provider is generated by using at least two of the following: the information provider's activities, each of the information provider's activity assets, each of the information provider's activity prompts, information received from external sources, and the dialogue content.

3. The information management method as described in request item 1, wherein, The aforementioned assets include at least one of the following: Uniform Resource Locator (URL) relating to the content provided by the aforementioned information provider, the title of the aforementioned content, the identifier of the aforementioned content, the category of the aforementioned content, the multimedia relating to the aforementioned content, the content items relating to the aforementioned content, and the content items of reports relating to the aforementioned content.

4. The information management method as described in request item 1, wherein, The aforementioned activities include assets and prompts that are generated for the purpose of the content provided by the aforementioned information providers and used to dynamically generate the aforementioned content for the corresponding purpose at the time of the search.

5. The information management method as described in request item 1, wherein, The steps for managing the above activities include generating new activities using at least one of the assets of the activities already generated by the information provider and information received from external sources in relation to the information provider.

6. The information management method as described in claim 1, wherein, The steps for managing the above activities include the following steps: based on the content of the above dialogue, modifying the prompts from the above information provider for the generated activities registered with the above information provider.

7. The information management method as described in Request 1, wherein, The steps for managing the above activities include the following: based on the content of the above dialogue, registering new prompts for the activities already generated by the above information provider.

8. A computer-readable recording medium, wherein, The computer program is recorded for running the information management method as described in claim 1 in the aforementioned computer device.

9. A computer device, wherein, The system includes at least one processor for executing computer-readable instructions, wherein the at least one processor is configured to: provide a conversational information management function to an information provider that provides content to a user of a search service; enable a dialogue between the information provider and an artificial intelligence based on a large language model through the conversational information management function; and analyze the dialogue to manage the activities of the information provider; wherein, in order to provide the conversational information management function, the at least one processor provides a function for registering each activity asset of the information provider through the conversational information management function; wherein managing the activities of the information provider includes modifying the prompts entered by the information provider for the activity based on the dialogue between the conversational information management function and the large language model, and registering the modified prompts to the activity; and wherein the content provided to the user through the search service is dynamically generated at the user's search time using the assets registered by the information provider, the modified prompts, and a first answer, and included in the search results, wherein the first answer is generated using the large language model for the user's natural language prompts; The prompts provided by the information provider for the above-mentioned activities include at least one of the following: sentences that emphasize input related to the content provided by the information provider, keywords that emphasize input related to the content provided by the information provider, the tone of the information message included in the above-mentioned content, and the format of the information message.

10. The computer apparatus as described in claim 9, wherein, In order to conduct the above dialogue, at least one of the above processors uses artificial intelligence to generate dialogue content to be provided to the information provider, utilizing at least two of the information provider's activities, each of the information provider's activity assets, each of the information provider's activity prompts, information received from the outside, and the content of the above dialogue.

11. The computer apparatus as described in claim 9, wherein, In order to manage the above activities, at least one of the processors may generate new activities by using at least one of the assets of the information provider’s generated activities and information received from external sources related to the information provider, or modify the prompts of the generated activities registered with the information provider based on the content of the dialogue, or register new prompts in the generated activities based on the content of the dialogue.

Images