Method and system for dynamically generating artificial intelligence-based answer in which message of information provider is projected

Abstract

Disclosed are a method and a system for dynamically generating an artificial intelligence-based answer in which a message of an information provider is projected. An answer generation method according to an embodiment may comprise the steps of: selecting a first information provider from among a plurality of information providers on the basis of a large language model (LLM) result generated based on an LLM with respect to a user's prompt; dynamically generating an answer reflecting information registered in association with the selected first information provider; and providing the generated answer.

Description

Method and system for dynamically generating artificial intelligence-based responses reflecting messages from information providers

[0001] The following description relates to a method and system for dynamically generating artificial intelligence-based responses that reflect messages from information providers.

[0002] Large language models (LLMs) are a type of artificial intelligence (AI) trained on large corpora of text data to generate human-like responses to natural language input. These models consist of artificial neural networks with numerous parameters (typically billions of weights or more). These LLMs can be trained on large amounts of unlabeled text using self-supervised or semi-self-supervised learning.

[0003] A method and system are provided for dynamically generating artificial intelligence-based responses projected from an information provider's message.

[0004] A method for generating an answer in a computer device including at least one processor, the method comprising: selecting a first information provider from among a plurality of information providers based on a Large Language Model (LLM) result generated based on an LLM for a user's prompt by the at least one processor; dynamically generating an answer reflecting information registered in association with the selected first information provider by the at least one processor; and providing the generated answer by the at least one processor.

[0005] According to one aspect, the step of selecting the first information provider may include the step of first selecting information providers related to at least one of the user's prompt, the LLM result, and the recommendation query generated by the large language model among the plurality of information providers; and the step of dynamically conducting an auction among the first selected information providers to select the first information provider.

[0006] According to another aspect, the step of dynamically generating the answer may be characterized by dynamically generating the answer using at least one of an asset registered by the first information provider and a prompt registered by the first information provider.

[0007] According to another aspect, the asset may be characterized by including at least one of a Uniform Resource Locator (URL) related to the content that the first information provider intends to provide, a title of the content, an identifier of the content, a category of the content, multimedia related to the content, content of the content, and content of an article related to the content.

[0008] According to another aspect, the prompt registered by the first information provider may be characterized by including at least one of a phrase or keyword entered to be emphasized in relation to the content the first information provider intends to provide, and a tone or format of an information message to be provided as the answer.

[0009] According to another aspect, the step of dynamically generating the answer may be characterized in that the answer is generated by further reflecting at least one of the user's prompt and the LLM result.

[0010] According to another aspect, the step of dynamically generating the answer may be characterized in that the answer is generated by further reflecting information about the user, and the information about the user includes at least one of the user's demo, interests, and purchase information.

[0011] According to another aspect, the user's prompt may be input through a search service, and the dynamically generated answer may be included in a search result for the user's prompt and provided to the user through the search service.

[0012] According to another aspect, the search results may be characterized in that they further include the LLM results.

[0013] According to another aspect, the user's prompt may be input through a conversation between the user and artificial intelligence using the large language model, and the dynamically generated answer may be provided to the user as included in the answer result for the user's prompt.

[0014] According to another aspect, the method for generating an answer may further include a step of generating, by the at least one processor, a question for inducing additional information for selection of the first information provider; and a step of providing, by the at least one processor, the generated question.

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

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

[0017] A computer device is provided, comprising at least one processor implemented to execute instructions readable by a computer device, characterized in that the computer device selects a first information provider from among a plurality of information providers based on an LLM result generated based on Large Language Models (LLM) for a user's prompt by the at least one processor, dynamically generates an answer reflecting registered information associated with the selected first information provider, and provides the generated answer.

[0018] A method and system for dynamically generating an artificial intelligence-based response projected with a message from an information provider can be provided.

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

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

[0021] FIG. 3 is a drawing illustrating an example of a general appearance of an answer generation system according to one embodiment of the present invention.

[0022] Figure 4 is a flowchart illustrating an example of a method for generating an answer according to one embodiment of the present invention.

[0023] FIG. 5 is a flowchart illustrating an example of a process for supplementing a user's prompt in one embodiment of the present invention.

[0024] FIG. 6 is a drawing illustrating an example for explaining a process of providing a response to a user's prompt in one embodiment of the present invention.

[0025] FIG. 7 is a drawing illustrating an example of providing search results in one embodiment of the present invention.

[0026] Hereinafter, the detailed description will be given with reference to the attached drawings.

[0027] The answer generation system according to embodiments of the present invention may be implemented by at least one computer device. In this case, a computer program according to an embodiment of the present invention may be installed and run on the computer device implementing the answer generation system, and the computer device may perform the answer generation method according to embodiments of the present invention under the control of the run computer program. The above-described computer program may be stored on a computer-readable recording medium, which may be coupled to the computer device to cause the computer to execute the answer generation method.

[0028] FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention. The network environment of FIG. 1 represents an example including multiple electronic devices (110, 120, 130, 140), multiple servers (150, 160), and a network (170). FIG. 1 is merely an example for explaining the invention, and the number of electronic devices or servers is not limited to that of FIG. 1.

[0029] The plurality of electronic devices (110, 120, 130, 140) may be fixed terminals or mobile terminals implemented as computer systems. Examples of the plurality of electronic devices (110, 120, 130, 140) include smart phones, mobile phones, navigation systems, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, game consoles, wearable devices, IoT (Internet of Things) devices, VR (Virtual Reality) devices, AR (Augmented Reality) devices, etc. For example, in FIG. 1, the shape of a smartphone is shown as an example of an electronic device (110), but in embodiments of the present invention, the electronic device (110) may actually mean one of various physical computer systems that can communicate with other electronic devices (120, 130, 140) and / or servers (150, 160) through a network (170) using a wireless or wired communication method.

[0030] The communication method is not limited, and may include not only a communication method utilizing a communication network (e.g., a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network, a satellite network, etc.) that the network (170) may include, but also short-range wireless communication between devices. For example, the network (170) may include any one or more of a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), the Internet, etc. In addition, the network (170) may include any one or more of a network topology including, but not limited to, a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree, or a hierarchical network.

[0031] Each of the servers (150, 160) may be implemented as a computer device or multiple computer devices that communicate with multiple electronic devices (110, 120, 130, 140) via a network (170) to provide commands, codes, files, contents, services, etc. For example, the server (150) may be a system that provides a first service to multiple electronic devices (110, 120, 130, 140) connected via a network (170), and the server (160) may also be a system that provides a second service to multiple electronic devices (110, 120, 130, 140) connected via a network (170). As a more specific example, the server (150) may provide a service (e.g., a search service, etc.) intended by the application as a first service to the plurality of electronic devices (110, 120, 130, 140) through an application as a computer program installed and run on the plurality of electronic devices (110, 120, 130, 140). As another example, the server (160) may provide a service of distributing a file for installing and running the above-described application to the plurality of electronic devices (110, 120, 130, 140) as a second service.

[0032] FIG. 2 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. Each of the plurality of electronic devices (110, 120, 130, 140) or servers (150, 160) described above can be implemented by the computer device (200) illustrated in FIG. 2.

[0033] Such a computer device (200) may include a memory (210), a processor (220), a communication interface (230), and an input / output interface (240), as illustrated in FIG. 2. The memory (210) may be a computer-readable recording medium, and may include a random access memory (RAM), a read only memory (ROM), and a non-permanent mass storage device such as a disk drive. Here, the non-permanent mass storage device such as a ROM and a disk drive may be included in the computer device (200) as a separate permanent storage device distinct from the memory (210). In addition, an operating system and at least one program code may be stored in the memory (210). These software components may be loaded into the memory (210) from a computer-readable recording medium separate from the memory (210). Such a separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, a memory card, etc. In another embodiment, the software components may be loaded into the memory (210) via a communication interface (230) other than a computer-readable recording medium. For example, the software components may be loaded into the memory (210) of the computer device (200) based on a computer program installed by files received over a network (170).

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

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

[0036] The input / output interface (240) may be a means for interfacing with an input / output device (250). For example, the input device may include a device such as a microphone, keyboard, or mouse, and the output device may include a device such as a display or speaker. As another example, the input / output interface (240) may be a means for interfacing with a device that integrates input and output functions, such as a touchscreen. The input / output device (250) may also be configured as a single device with the computer device (200).

[0037] Additionally, in other embodiments, the computer device (200) may include fewer or more components than those illustrated in FIG. 2. However, it is not necessary to explicitly illustrate most conventional components. For example, the computer device (200) may be implemented to include at least some of the input / output devices (250) described above, or may further include other components such as a transceiver, a database, etc.

[0038] FIG. 3 is a schematic diagram illustrating an example of an answer generation system according to one embodiment of the present invention. FIG. 3 illustrates an answer generation system (310), a search system (320), multiple users (330), and multiple information providers (340).

[0039] The search system (320) may correspond to a server (e.g., server (150)) that provides search services to a plurality of users (330), and may be implemented with at least one computer device (200). Here, each of the plurality of users (330) may be a physical device of a user that connects to the search system (320) using a network (170) to receive search services, and such physical device may be implemented with the computer device (200) described above.

[0040] The answer generation system (310) according to the present embodiment may be implemented in a form that is included in the search system (320) or is linked to the search system (320) via a network (170). The embodiment of FIG. 3 shows an example in which the answer generation system (310) is implemented in a form that is included in the search system (320). In this case, the answer generation system (310) may be implemented on at least one physical device for implementing the search system (320). Depending on the embodiment, the answer generation system (310) may be implemented as a physical device separate from the physical device for implementing the search system (320) and may be implemented in a form that communicates with the search system (320) via a network (170).

[0041] The search service provided by the search system (320) to multiple users (330) may include search results corresponding to the user's input. The search results may be generated based on information searchable on the web. Furthermore, the search system (320) may also provide the search service by including information provided by multiple information providers (340) in the search results. Here, the information provided by the multiple information providers (340) may be advertising information, but is not limited thereto. Since the search service itself, which provides such search results, is already well known, a detailed description thereof will be omitted.

[0042] Meanwhile, the search system (320) according to the present embodiment may provide a search service by including answers based on artificial intelligence, such as large language models (LLMs), in the search results. For example, the search system (320) may receive a natural language-based prompt from a specific user among a plurality of users (330). In this case, the search system (320) may input the received prompt into the LLM, generate a first answer appropriate to the prompt as an LLM result, and provide a search result including the first answer to the user. At this time, the search result may include at least some of various existing search results in addition to the first answer. In addition, the search system (320) may provide a search service through a conversation between an LLM-based artificial intelligence and a user. The first mode, which provides the first answer as an LLM result through a general search service, and the second mode, which provides the first answer as an LLM result through a conversation between an LLM-based artificial intelligence and a user, may be switched to provide a search service to the user. At this time, in each of the first mode and the second mode, at least some of the first answers may further provide instances of the information provider's content as second answers.

[0043] In some embodiments, the search system (320) may verify whether a natural language-based prompt received from the user is a user prompt that may provide information from the information provider. For example, an advertiser may not want their advertisements to be displayed in response to prompts requesting pre-defined illegal information or pre-defined non-advertising information. Therefore, the search system (320) may first verify whether the user's prompt is a safe prompt for providing information from the information provider. In this case, if the user's prompt does not request pre-defined illegal information or pre-defined non-advertising information, the search system (320) may request the answer generation system (310) to generate and provide a second answer.

[0044] The answer generation system (310) can dynamically generate an AI-based second answer that reflects a message from an information provider selected from among multiple information providers (340). In this case, the search system (320) can provide the user with search results that include not only the first answer generated using LLM, but also the AI-based second answer generated by the answer generation system (310).

[0045] At this time, the answer generation system (310) may not simply provide the information provided by the information provider as is when generating the AI-based second answer, but may dynamically generate the AI-based second answer using the user's prompt, the first answer generated using LLM, the asset registered by the information provider, and / or the prompt registered by the information provider. Here, the asset may include, for example, a URL (Uniform Resource Locator) related to the content that the information provider intends to provide, the title or identifier of the content, the category of the content, multimedia related to the content, content of the content, content of an article related to the content, etc. Here, the multimedia related to the content may include images, videos, etc. related to the content. For example, if the information provider is advertising a specific product or service, the asset may include a URL related to the product or service, the product or service name, the category of the product or service, product information or service information, article content related to the product or service, etc. Additionally, the prompt registered by the information provider may include information such as phrases or keywords that the information provider wishes to emphasize in relation to the content they wish to provide, and the tone or format of the information message to be provided as a second response. In this way, the response generation system (310) 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 prompt of the information provider seeking to provide their information, as well as the first response.

[0046] Additionally, depending on the embodiment, the answer generation system (310) may further utilize information about the user to generate a second answer. This information about the user may include the user's demo, interests, purchase information, etc., and may be used to customize the second answer for the user.

[0047] Moreover, since there may be multiple information providers who wish to expose their information, the answer generation system (310) can dynamically determine which of the multiple information providers' assets and prompts will be used to generate the second answer. For example, the answer generation system (310) can initially select information providers related to the first answer, i.e., the LLM result, based on the first answer among the multiple information providers. In some embodiments, the answer generation system (310) may utilize at least one of the user's prompt, the LLM result, and the recommended query generated by the LLM to initially select the information providers. Thereafter, the answer generation system (310) can dynamically conduct an auction among the initially selected information providers to select the first information provider as the information provider for generating the second answer. The auction method can utilize one of the well-known methods. For example, the GSP (Generalized Second Price) auction method can be used.

[0048] In this way, when the search system (320) provides a response to a natural language-based prompt from a user, the response generation system (310) can dynamically generate a response based on the information provider's assets and prompt, i.e., a second AI-based response that reflects the information provider's message. Accordingly, the search system (320) can provide the user with a dynamically generated response that reflects the information provider's message in relation to the natural language-based prompt received from the user.

[0049] Additionally, depending on the embodiment, the content of the user's prompt may be insufficient to match the information of a specific information provider. In this case, the answer generation system (310) may provide the user with a question via the search system (320) to guide the user to include sufficient information in the user's prompt for the matching. Information obtained through the user's response to this question may also be included in the user's prompt.

[0050] FIG. 4 is a flowchart illustrating an example of a method for generating an answer according to an embodiment of the present invention. The method for generating an answer according to the present embodiment can be performed by a computer device (200) that implements the answer generation system (310) described above. At this time, the processor (220) of the computer device (200) can be implemented to execute control instructions according to the code of the operating system included in the memory (210) or the code of at least one computer program. Here, the processor (220) can control the computer device (200) so that the computer device (200) performs steps (410 to 430) included in the method of FIG. 4 according to the control instructions provided by the code stored in the computer device (200).

[0051] In step (410), the computer device (200) may select a first information provider among a plurality of information providers based on the LLM results generated based on Large Language Models (LLM) in response to the user's prompt. The plurality of information providers may correspond to the plurality of information providers (340) described above with reference to FIG. 3 . For example, the LLM results may be generated by the search system (320) described above. In this case, the computer device (200) may select the first information provider based on the generated LLM results. This may be a process for selecting a first information provider that provides information related to the LLM results. Depending on the embodiment, step (410) may include steps (411) and (412).

[0052] In step (411), the computer device (200) may first select information providers among a plurality of information providers that are related to at least one of the user's prompt, the LLM result, and the recommended query generated by the large language model. As described above, the first-selected information providers may include information providers that provide information related to at least one of the user's prompt, the LLM result, and the recommended query. For example, the computer device (200) may first select information providers that have registered information related to at least one of the user's prompt, the LLM result, and the recommended query by comparing each of the registered information associated with the plurality of information providers with at least one of the user's prompt, the LLM result, and the recommended query.

[0053] In step (412), the computer device (200) can dynamically conduct an auction among the initially selected information providers to select the first information provider. For example, the computer device (200) can select the first information provider by conducting a dynamic auction among the initially selected information providers using a well-known auction method, such as the GSP auction method.

[0054] In step (420), the computer device (200) can dynamically generate a response reflecting information registered in association with the selected first information provider. For example, the computer device (200) can dynamically generate a response using at least one of an asset registered by the first information provider and a prompt registered by the first information provider. Here, the asset may include at least one of a Uniform Resource Locator (URL) related to content that the first information provider intends to provide, a title of the content, an identifier of the content, a category of the content, multimedia related to the content, content of the content, and content of an article related to the content. In addition, the prompt registered by the first information provider may include at least one of a phrase or keyword entered to be emphasized in relation to the content that the first information provider intends to provide, and the tone and format of an information message to be provided as a response.

[0055] In some embodiments, the computer device (200) may generate an answer by further reflecting the user's prompt and / or the LLM result. In other words, the computer device (200) may generate an answer by reflecting the user's prompt, at least one of the LLM results generated based on a large language model in response to the user's prompt, and information registered in association with the selected first information provider.

[0056] In another embodiment, the computer device (200) may generate a response by further incorporating information about the user. The information about the user may include at least one of the user's demographics, interests, and purchase information. In other words, the computer device (200) may generate a response by incorporating both information registered with the first information provider and information about the user.

[0057] In another embodiment, the computer device (200) can generate an answer by reflecting at least one of a user prompt and an LLM result generated based on a giant language model for the user prompt, information registered in association with the first information provider, and information about the user.

[0058] In step (430), the computer device (200) may provide the generated answer. For example, the user's prompt may be input through a search service provided by the search system (320). In this case, the search system (320) may generate an LLM result for the user's prompt, and if the user's prompt is verified and determined not to be a prompt requesting preset illegal information or preset non-advertising information, the LLM result may be transmitted to the computer device (200) to request generation of an answer. After generating the answer through steps (410) and (420), the computer device (200) may provide the generated answer to the search system (320) in step (430). In this case, the search system (320) may generate a search result including the answer generated by the computer device (200) and the LLM result and provide the generated search result to the user. At this time, the search result may further include search results based on existing search terms.

[0059] Depending on the embodiment, the user's prompt may be input through a conversation between the user and the AI ​​using a large language model. In this case, the dynamically generated response may be included in the response to the user's prompt (the AI's response in the user-AI conversation) and provided to the user.

[0060] FIG. 5 is a flowchart illustrating an example of a process for supplementing a user's prompt according to one embodiment of the present invention. Depending on the embodiment, the answer generation system (310) may perform steps (510) and (520) to supplement the user's prompt prior to step (410) of FIG. 4.

[0061] In step (510), the computer device (200) may generate a question to elicit additional information for selecting the first information provider. As previously described, the content of the user's prompt may be insufficient to match the information of a specific information provider. In this case, the computer device (200) may generate a question to ensure that the user's prompt includes sufficient information to match the information of the information provider. This question generation may also be based on the LLM.

[0062] In step (520), the computer device (200) may provide the generated question. For example, the generated question may be provided to the user through the search service of the search system (320). If the user enters an answer to the provided question, the user's answer may be included in the user's prompt, supplementing the content of the user's prompt. This process of generating and providing questions may be repeated until the content of the user's prompt satisfactorily matches the information of a specific information provider. Information providers whose registered information matches the content of the user's prompt may correspond to the initially selected information providers. As described above, the first information provider may be selected in step (410) through an auction among the initially selected information providers.

[0063] Figure 6 is a diagram illustrating an example of a process for providing a response to a user's prompt, according to one embodiment of the present invention. The embodiment of Figure 6 illustrates an example in which information providers wish to display advertisements for advertisers' products or services as information they wish to provide.

[0064] The search system (320) can receive a user prompt (User Prompt, 601) from a user's terminal connected via the network (170). For example, the prompt can correspond to a natural language-based search term entered by the user. The user can input a search term through the user interface of a search service provided via the user's terminal, and the search system (320) can receive the search term entered through the user interface as a user prompt (601).

[0065] At this time, the search system (320) can analyze the user prompt (601) through the process of user intent extraction and summarization (User Intent Extracting & Summarizing, 602) to extract and summarize the user intent, thereby selecting a prompt to be actually used.

[0066] Meanwhile, the search system (320) and / or the answer generation system (310) may prompt 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 (601) may be insufficient to match a specific advertiser's marketing message. In this case, the answer generation system (310) may generate a question to elicit additional information for selecting a specific advertiser and provide the question generated through the search system (320) to the user. Thereafter, when the user's answer to the question is received, the content of the received answer may be used to supplement the prompt. The question specification prompt (603) may include a prompt obtained through the user's answer.

[0067] At this time, the search system (320) and / or the answer generation system (310) may select a specified user prompt (604) as a prompt for providing a marketing message. In other words, the specified user prompt (604) may be specified based on a prompt obtained through user intent extraction and summary (602) for the user prompt (601) and a question specification prompt (603).

[0068] Prompt Ads Safe Check (605) may be an example of a process for verifying whether a designated user prompt (604) is a prompt that may be appropriate for displaying an advertiser's marketing message to the user. For example, if the designated user prompt (604) is not a prompt requesting pre-determined illegal information or pre-determined non-advertising information, the search system (320) may request the response generation system (310) to generate and provide a response.

[0069] Additionally, the search system (320) can generate LLM results by inputting a designated user prompt (604) into the LLM. FIG. 5 illustrates an example of an Organic LLM Result Memory (606) storing such LLM results.

[0070] The answer generation system (310) may initially select advertisers related to the LLM results based on the LLM results stored in the Organic LLM Result Memory (606). At this time, the advertisers related to the LLM results may be advertisers who have registered marketing messages to be displayed together with the LLM results. The marketing messages to be displayed together with the LLM results may be selected based on the relevance between the information registered by the advertisers and the LLM results. In addition, according to an embodiment, the answer generation system (310) may utilize at least one of the user prompt (604), the LLM results, and the recommendation query generated by the large language model when initially selecting the advertisers. In this case, the answer generation system (310) may initially select the advertisers based on the relevance between at least one of the user prompt (604), the LLM results, and the recommendation query and the information registered by the advertisers. At this time, the response generation system (310) can select a specific advertiser from among the advertisers selected in the first round through an ad prompt auction (Ad Prompt Auction, 607).

[0071] Once an advertiser is selected, the answer generation system (310) can obtain an advertising asset (608) registered by the selected advertiser and an advertiser prompt (609) registered by the selected advertiser. In this case, the answer generation system (310) can generate an answer prompt (610) that reflects the advertiser's marketing message by using at least one of the user prompt (601) and the LLM result stored in the organic LLM result memory (606) and at least one of the advertising asset (608) and the advertiser prompt (609). In some embodiments, the advertiser may want to provide an answer in a specific format based on the user's characteristics. To this end, the answer generation system (310) can generate the answer prompt (610) by further reflecting information about the user. For example, the information about the user may include at least one of the user's demo, interests, and purchase information. For example, the response generation system (310) may analyze the advertiser prompt (609) to determine that the advertiser wants to provide relatively more detailed answers to female users than to male users. In this case, the response generation system (310) may determine the user's gender through the user's demo, and then generate the response prompt (610) considering the determined user's gender.

[0072] Once the response prompt (610) is generated, the response generation system (310) can check (611) whether the generated response prompt (610) is generated in accordance with the tone and / or format confirmed through the advertiser prompt (609). If the generated response prompt (610) does not match the tone and / or format desired by the advertiser, the response prompt (610) can be processed to match the tone and / or format desired by the advertiser. In addition, depending on the embodiment, the response generation system (310) can additionally perform a check to determine whether the generated response prompt (610) is safe to be exposed, etc.

[0073] Thereafter, the answer generation system (310) can provide the finally generated answer (Answer, 612) to the user through the search system (320). For example, the search system (320) can add the answer (612) provided by the answer generation system (310) to the search results and provide it to the user through a search service. Additionally, depending on the embodiment, user information (e.g., gender, age, interests, etc.) stored in the DMP (Data Management Platform, 613) may be further utilized in generating the answer prompt (610). By utilizing such user information, the answer generation system (310) can generate an answer (612) optimized for the user.

[0074] FIG. 7 is a diagram illustrating an example of providing search results according to an embodiment of the present invention. FIG. 7 illustrates an example screen of a search page (700) provided to a user through a search service. The search page (700) may include a user interface (710) for receiving a user's prompt. In addition, the search page (700) may include a search results area (720) for displaying search results. In this case, the search results area (720) may include an LLM results area (730) for displaying LLM results generated based on Large Language Models (LLM) in response to the user's prompt.

[0075] Additionally, the search results area (720) illustrates an example of a response area (740) that displays responses generated by the response generation system (310) in response to a user's prompt. In this embodiment, an example of multiple responses being displayed is illustrated through the response area (740). In this manner, multiple responses may be generated and displayed for a single prompt. Furthermore, responses may be generated and displayed for each of two or more information providers. To this end, the response generation system (310) may select two or more information providers.

[0076] Meanwhile, the embodiment of FIG. 7 illustrates an example in which an answer from an information provider selected based on a user's prompt input into the user interface (710) and / or an LLM result displayed in the LLM result area (730) is displayed through an expansion area (750). For example, an answer from an information provider selected based on at least one of the user's prompt, the LLM result, and the recommended query generated by the large language model may be further displayed through the expansion area (750). If the information provider is an advertiser, an advertisement from an advertiser selected based on at least one of the user's prompt, the LLM result, and the recommended query generated by the large language model may be further displayed in the expansion area (750).

[0077] Additionally, the dotted box (760) displays questions that request additional prompts from the user in relation to the answers displayed in the expanded area (750). If the user selects a specific question, that question may be recognized as an additional prompt from the user. If a conversational search service is provided, the user's additional prompt may be recognized as the user's next conversation. In this case, the search system (320) and / or the answer generation system (310) may generate LLM results and / or answers by considering the entire conversation with the user.

[0078] In addition, although the embodiment of FIG. 7 described an example of dynamically generating an answer by receiving a user's prompt through the user interface (710) of the search service, an interface for generating and providing dynamic answers may also be included in the search results, depending on the embodiment. For example, a function for dynamically generating and providing an answer by receiving a user's prompt may be provided to the user through each and / or some of various vertical services provided in the existing search ecosystem. Here, the vertical service may refer to a service for each of various collections that classify search results, such as shopping search, knowledge search, local search, UGC (User Generated Contents) search, language search, image search, video search, and news search. For example, if a shopping search service is provided as a separate vertical service of an integrated search service, a function for dynamically generating and providing an answer by receiving a user's prompt may also be provided to the user through the shopping search service. If multiple different advertising services are provided as vertical services of the integrated search service, a function for dynamically generating and providing an answer by receiving a user's prompt may also be provided to the user through each of these multiple advertising services.

[0079] In this way, according to embodiments of the present invention, a method and system for dynamically generating an artificial intelligence-based answer projected with a message from an information provider can be provided.

[0080] The systems or devices described above may be implemented as hardware components, or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0081] Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may independently or collectively command the processing device. The software and / or data may be embodied in any type of machine, component, physical device, virtual equipment, computer storage medium, or device for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

[0082] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., singly or in combination. The medium may continuously store a computer-executable program, or may temporarily store it for execution or download. In addition, the medium may be various recording means or storage means in the form of a single or multiple hardware combinations, and is not limited to a medium directly connected to a computer system, but may also be distributed over a network. Examples of the medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and those configured to store program commands, including ROM, RAM, and flash memory. In addition, examples of other media may include recording media or storage media managed by app stores that distribute applications, sites that supply or distribute various software, servers, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0083] Although the embodiments described above have been described by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above description. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0084] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

1. A method for generating an answer in a computer device including at least one processor, A step of selecting a first information provider among a plurality of information providers based on an LLM result generated based on Large Language Models (LLM) for a user's prompt by at least one processor; A step of dynamically generating an answer reflecting information registered in association with the selected first information provider by at least one processor; and A step of providing the generated answer by at least one processor How to generate an answer that includes .

2. In paragraph 1, The step of selecting the first information provider is: A step of first selecting information providers among the plurality of information providers related to at least one of the user's prompt, the LLM result, and the recommendation query generated by the large language model; and A step of dynamically conducting an auction among the first selected information providers to select the first information provider. A method for generating an answer, characterized in that it includes:

3. In paragraph 1, The steps to dynamically generate the above answers are: An answer generation method characterized in that the answer is dynamically generated using at least one of an asset registered by the first information provider and a prompt registered by the first information provider.

4. In paragraph 3, A method for generating an answer, wherein the above asset includes at least one of a Uniform Resource Locator (URL) related to the content that the first information provider intends to provide, a title of the content, an identifier of the content, a category of the content, multimedia related to the content, content of the content, and content of an article related to the content.

5. In paragraph 3, A method for generating an answer, characterized in that the prompt registered by the first information provider includes at least one of a phrase or keyword entered to be emphasized in relation to the content to be provided by the first information provider, and a tone or format of an information message to be provided as the answer.

6. In paragraph 1, The steps to dynamically generate the above answers are: An answer generation method characterized in that the answer is generated by further reflecting at least one of the user's prompt and the LLM result.

7. In paragraph 1, The steps to dynamically generate the above answers are: Generate the above answer by further reflecting information about the above user, Information about the user includes at least one of the user's demo, interests, and purchase information. A method for generating answers characterized by .

8. In paragraph 1, The above user's prompt is entered through a search service, The above dynamically generated answer is included in the search results for the user's prompt and provided to the user through the search service. A method for generating answers characterized by .

9. In paragraph 8, A method for generating an answer, characterized in that the search result further includes the LLM result.

10. In paragraph 1, The above user's prompt is input through a conversation between the user and artificial intelligence using the above large language model, The above dynamically generated answer is included in the answer result for the user's prompt and provided to the user. A method for generating answers characterized by .

11. In paragraph 1, generating a question for inducing additional information for selection of the first information provider by at least one processor; and A step of providing the generated question by at least one processor How to generate an answer that includes more.

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

13. At least one processor implemented to execute instructions readable by a computer device. Including, By at least one processor, Select the first information provider among multiple information providers based on the LLM results generated based on Large Language Models (LLM) for the user's prompt, Dynamically generates a response reflecting the information registered in connection with the first information provider selected above, Providing the above generated answers A computer device characterized by:

14. In paragraph 13, To select the first information provider, by the at least one processor, First, among the plurality of information providers, information providers related to at least one of the user's prompt, the LLM result, and the recommendation query generated by the large language model are selected, Selecting the first information provider by dynamically conducting an auction among the first-selected information providers A computer device characterized by:

15. In paragraph 13, To dynamically generate the above answer, by at least one processor, Dynamically generating the answer using at least one of the assets registered by the first information provider and the prompt registered by the first information provider A computer device characterized by:

16. In paragraph 13, To dynamically generate the above answer, by at least one processor, Generating said answer by further reflecting at least one of said user's prompt and said LLM result. A computer device characterized by:

17. In paragraph 13, To dynamically generate the above answer, by at least one processor, Generate the above answer by further reflecting information about the above user, Information about the user includes at least one of the user's demo, interests, and purchase information. A computer device characterized by:

Images