A method and system for dynamically generating AI-based responses that reflect the information provider's message.

Abstract

The present invention discloses a method and system for dynamically generating artificial intelligence-based responses that reflect messages from information providers. One embodiment of the response generation method may include the steps of: selecting a first information provider from a plurality of information providers based on LLM results generated using Large Language Models (LLM) in response to a user prompt; dynamically generating a response that reflects information registered in association with the selected first information provider; and providing the generated response to the user.

Description

Technical Field

[0001] The following description relates to a method and system for dynamically generating an AI-based answer reflecting a message from an information provider.

Background Art

[0002] Large Language Models (LLMs, also referred to as "giant language models") are one type of artificial intelligence trained with a large-scale text dataset to generate human-like natural answers for input natural language, and are language models composed of neural networks having hundreds of millions or more parameters (usually weights of tens of billions or more). Such large language models (LLMs) learn a large amount of unlabeled text through supervised learning or semi-supervised learning.

Summary of the Invention

Problems to be Solved by the Invention

[0003] Provided are a method and system for dynamically generating an AI-based answer reflecting a message from an information provider.

Means for Solving the Problems

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

[0005] According to one embodiment, the step of selecting the first information provider may include: provisionally selecting an information provider from the plurality of information providers that is related to at least one of the user prompt, the LLM results, and the recommendation queries generated by the large-scale language model; and selecting the first information provider by conducting an auction among the provisionally selected information providers.

[0006] According to another embodiment, the step of dynamically generating the response may be to dynamically generate the response using at least one of the assets registered by the first information provider and the prompts registered by the first information provider.

[0007] In other embodiments, the assets registered by the first information provider may include at least one of the following: a URL (Uniform Resource Locator) related to the content that the first information provider intends 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 article content related to the content.

[0008] In another embodiment, the prompt registered by the first information provider may include at least one of the following: a phrase entered to emphasize in relation to the content that the first information provider intends to provide; keywords entered by the first information provider to emphasize in relation to the content; the tone of the information message to be provided as a response; and the format of the information message.

[0009] In another embodiment, the step of dynamically generating the response may generate a response that further reflects at least one of the user prompts and the LLM results.

[0010] In another embodiment, the step of dynamically generating the response may further reflect information about the user, which may include at least one of the user's demos, interests, and purchase information.

[0011] In another embodiment, the user prompt may be entered through a search service, and the dynamically generated response may be included in the search results for the user prompt and provided to the user through the search service.

[0012] In other embodiments, the search results may further include the LLM results.

[0013] In another embodiment, the user prompt may be input through a dialogue between the user and the artificial intelligence utilizing the large-scale language model, and the dynamically generated response may be provided to the user as part of the response result to the user prompt.

[0014] In further embodiments, the response generation method may further include the steps of generating questions using the at least one processor to elicit additional information that would be useful in selecting the first information provider, and providing the generated questions to the user using the at least one processor.

[0015] The present invention provides a program, which is combined with a computer device and recorded on a computer-readable recording medium to cause the computer device to execute the response generation method.

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

[0017] A computer device including at least one processor configured to execute instructions readable by the computer device, wherein the at least one processor selects a first information provider from a plurality of information providers based on an LLM result generated using a large language model in response to a user prompt, dynamically generates an answer reflecting information registered in association with the selected first information provider, and provides the generated answer to the user.

Advantages of the Invention

[0018] It is possible to provide a method and system for dynamically generating an AI-based answer reflecting a message from an information provider.

Brief Description of the Drawings

[0019] [Figure 1] A diagram showing an example of a network environment in an embodiment of the present invention. [Figure 2] A block diagram showing an example of a computer device according to an embodiment of the present invention. [Figure 3] A schematic diagram showing a configuration example of an answer generation system according to an embodiment of the present invention. [Figure 4] A flowchart showing an example of an answer generation method according to an embodiment of the present invention. [Figure 5] A flowchart showing an example of a process for supplementing a user prompt in an embodiment of the present invention. [Figure 6] A diagram showing an example of a process for providing an answer to a user prompt in an embodiment of the present invention. [Figure 7] A diagram showing an example of providing search results in an embodiment of the present invention.

Modes for Carrying Out the Invention

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

[0021] The answer generation system according to an embodiment of the present invention may be realized by at least one computer device. At this time, in the computer device constituting the answer generation system, a computer program according to an embodiment of the present invention may be installed and executed, and the computer device may execute the answer generation method according to the embodiment of the present invention according to the control of the executed computer program. The above-described computer program may be recorded on a computer-readable recording medium in order to be combined with the computer device to cause the computer to execute the answer generation method.

[0022] FIG. 1 is a diagram showing an example of a network environment in 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. Such a FIG. 1 is merely an example for explaining the invention, and the number of electronic devices and the number of servers are not limited as in FIG. 1.

[0023] The plurality of electronic devices 110, 120, 130, 140 may be fixed terminals or mobile terminals realized by a computer system. Examples of the plurality of electronic devices 110, 120, 130, 140 include smartphones, mobile phones, navigation devices, PCs (personal computers), notebook PCs, digital broadcast terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablets, and the like. As an example, in FIG. 1, a smartphone is shown as an example of the electronic device 110. However, in the embodiment of the present invention, the electronic device 110 may mean one of various physical computer systems that can communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 via the network 170 using substantially wireless or wired communication methods.

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

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

[0026] Figure 2 is a block diagram showing an example of a computer device according to one embodiment of the present invention. Each of the above-mentioned electronic devices 110, 120, 130, and 140, as well as each of the servers 150 and 160, may be composed of the computer device 200 shown in Figure 2.

[0027] Such a computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input / output interface 240, as shown in Figure 2. The memory 210 is a computer-readable recording medium and may include RAM (random access memory), ROM (read-only memory), and a permanent mass storage device such as a disk drive. Here, the permanent mass storage device such as ROM or a disk drive may be included in the computer device 200 as a separate permanent storage device distinct from the memory 210. The memory 210 may also contain an operating system and at least one program code. Such software components may be loaded into the memory 210 from a computer-readable recording medium separate from the memory 210. Such a separate computer-readable recording medium may include a floppy disk drive, disk, tape, DVD / CD-ROM drive, memory card, and other computer-readable recording media. In other embodiments, the software components may be loaded into the memory 210 through a communication interface 230, which is not a computer-readable recording medium. For example, software components may be loaded into the memory 210 of the computer device 200 based on a computer program installed by a file received via the network 170.

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

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

[0030] The input / output interface 240 may be a means for interface with the input / output device 250. For example, the input device may include a microphone, keyboard, or mouse, and the output device may include a display or speaker. In another example, the input / output interface 240 may be a means for interface with a device that integrates input and output functions into one, such as a touchscreen. The input / output device 250 may consist of the computer device 200 and one other device.

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

[0032] Figure 3 is a schematic diagram showing an example configuration of a response generation system according to one embodiment of the present invention. Figure 3 shows a response generation system 310, a search system 320, multiple users 330, and multiple information providers 340.

[0033] The search system 320 may correspond to a server (for example, server 150) that provides search services to multiple users 330, and may be implemented by at least one computer device 200. Here, each of the multiple users 330 may be a physical device of a user that connects to the search system 320 using the network 170 to receive search services, and such a physical device may be implemented by the computer device 200 described above.

[0034] The answer generation system 310 according to this embodiment may be implemented either as part of the search system 320 or in conjunction with the search system 320 via the network 170. The embodiment in Figure 3 shows an example in which the answer generation system 310 is implemented as part of 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 on a physical device separate from the physical device for implementing the search system 320 and communicate with the search system 320 via the network 170.

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

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

[0037] Depending on the embodiment, the search system 320 may verify whether a natural language-based prompt received from a user is a user prompt that may provide information from an information provider. For example, an advertiser may not want their advertisements to be published in response to prompts that request pre-configured illegal information or pre-configured non-advertising information. Therefore, the search system 320 may first verify whether the user's prompt is a prompt that is safe for providing information from an information provider. In this case, if the user's prompt is not a prompt that requests pre-configured illegal information or pre-configured non-advertising information, the search system 320 may request the response generation system 310 to generate and provide a second response.

[0038] The response generation system 310 may dynamically generate an artificial intelligence-based second response that reflects the message of an information provider selected from among multiple information providers 340. In this case, the search system 320 may provide the user with search results that include not only the first response generated using LLM, but also the artificial intelligence-based second response generated by the response generation system 310.

[0039] In this case, when generating an artificial intelligence-based second response, the response generation system 310 may not simply provide the information provided by the information provider as is, but may dynamically generate an artificial intelligence-based second response using the user's prompt, the first response generated using LLM, assets registered by the information provider, and / or prompts registered by the information provider. Here, assets may include, as an example, a URL (Uniform Resource Locator) related to the 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, the content of the content, and the content of articles related to the content. Here, multimedia related to the content may include images, videos, etc. related to the content. For example, if the information provider is an advertiser intending to advertise a specific product or service, the assets may include a URL related to the product or service, the product or service name, the category of the product or service, product or service information, and the content of articles related to the product or service. In addition, prompts registered by the information provider may include phrases or keywords that the information provider wants to emphasize in relation to the content that the information provider intends to provide, and information regarding the tone and format of the information message to be provided as the second response. Thus, the response generation system 310 can dynamically generate not only a first response generated using LLM in response to a user's natural language-based prompt, but also a second response that takes into account the registered assets and prompts of the information provider offering their own information, as well as the first response.

[0040] Furthermore, depending on the embodiment, the response generation system 310 may generate a second response by further utilizing information about the user. Here, the information about the user may include the user's demo, interests, purchase information, etc., and may be used to customize the second response for the user.

[0041] In addition, since there may be multiple information providers who wish to disclose their own information, the response generation system 310 may dynamically determine which of the multiple information providers' assets and prompts to use to generate the second response. For example, the response generation system 310 may provisionally select an information provider related to the first response, i.e., the LLM result, from among the multiple information providers based on the first response. Depending on the embodiment, the response generation system 310 may use at least one of the user's prompt, the LLM result, and the recommendation query generated by LLM when provisionally selecting an information provider. Subsequently, the response generation system 310 may conduct an auction among the provisionally selected information providers and select the first information provider as the information provider for generating the second response. One of the well-known methods may be used for the auction. For example, the GSP (Generalized Second Price) auction method may be used.

[0042] Thus, 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 the prompt, in other words, a second AI-based response that reflects the information provider's message. Therefore, the search system 320 can provide the user with a dynamically generated response that reflects the information provider's message in relation to a natural language-based prompt received from the user.

[0043] Furthermore, depending on the embodiment, the content of the user prompt may be insufficient to match it with information from a specific information provider. In this case, the response generation system 310 may provide the user, via the search system 320, with questions to guide the user so that the user prompt contains sufficient information for the matching. Information obtained from the user's answers to such questions may also be included in the user prompt.

[0044] Figure 4 is a flowchart showing an example of a response generation method according to one embodiment of the present invention. The response generation method according to this embodiment may be executed by a computer device 200 that constitutes the response generation system 310 described above. In this case, the processor 220 of the computer device 200 may be configured to execute control instructions from the operating system code contained in the memory 210 and the code of at least one computer program. Here, the processor 220 may control the computer device 200 so that the computer device 200 executes steps 410 to 430 included in the method of Figure 4 in accordance with the control instructions provided by the code stored in the computer device 200.

[0045] In step 410, the computer device 200 may select a first information provider from among multiple information providers based on the LLM results generated using Large Language Models (LLM) in response to a user prompt. The multiple information providers may correspond to the multiple information providers 340 described with reference to Figure 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 a 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.

[0046] In step 411, the computer device 200 may tentatively select information providers from among multiple information providers that are relevant to at least one of the user prompts, the LLM results, and the recommendation queries generated by the large-scale language model. As described above, the tentatively selected information providers may include information providers who intend to provide information relevant to at least one of the user prompts, the LLM results, and the recommendation queries. As an example, the computer device 200 may tentatively select information providers who have registered information relevant to at least one of the user prompts, the LLM results, and the recommendation queries by comparing at least one of them with the information registered in association with multiple information providers.

[0047] In step 412, the computer device 200 may select a first information provider by conducting an auction among the provisionally selected information providers. For example, the computer device 200 may select a first information provider by conducting an auction among the provisionally selected information providers using a well-known auction method such as the GSP auction method.

[0048] In step 420, the computer device 200 may dynamically generate a response that reflects the information registered in association with the selected first information provider. For example, the computer device 200 may dynamically generate a response using at least one of the assets and prompts registered by the first information provider. Here, the assets may include at least one of the following: a URL (Uniform Resource Locator) related to the content that the first information provider intends 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 itself, and the article content related to the content. The prompts registered by the first information provider may include at least one of the phrases, keywords, and the tone and format of the information message provided as a response that the first information provider has entered to emphasize in relation to the content that they intend to provide.

[0049] Depending on the embodiment, the computer device 200 may generate a response that further reflects the user's prompt and / or LLM results. In other words, the computer device 200 may generate a response that reflects the user's prompt and, in response to the user's prompt, at least one of the LLM results generated using a large-scale language model, and further information registered in association with a selected first information provider.

[0050] In other embodiments, the computer device 200 may generate responses that further reflect information about the user, including at least one of the user's demos, interests, and purchase information. In other words, the computer device 200 may generate responses that reflect both information registered in association with the first information provider and information about the user.

[0051] In yet another embodiment, the computer device 200 may generate a response that reflects at least one of a user prompt, an LLM result generated using a large-scale language model in response to the user prompt, information registered in association with the first information provider, and information about the user.

[0052] In step 430, the computer device 200 may provide the generated response. For example, the user prompt may be entered through a search service provided by the search system 320. In this case, the search system 320 may generate an LLM result in response to the user prompt, verify the user prompt, and if it determines that the user prompt is not a prompt requesting pre-configured illegal information or pre-configured non-advertising information, it may send the LLM result to the computer device 200 to request the generation of a response. After generating the response in steps 410 and 420, the computer device 200 may provide the generated response to the search system 320 in step 430. In this case, the search system 320 may generate search results including the response and LLM result generated by the computer device 200, and provide the generated search results to the user. In this case, the search results may further include search results based on existing search terms.

[0053] Depending on the embodiment, user prompts may be input through interaction between the user and artificial intelligence utilizing a large-scale language model. In this case, dynamically generated responses may be included in the response results to the user prompts (the AI's response in the interaction between the user and the AI) and provided to the user.

[0054] Figure 5 is a flowchart showing an example of a process for complementing user prompts in one embodiment of the present invention. Depending on the embodiment, the response generation system 310 may perform steps 510 and 520 to complement user prompts prior to step 410 in Figure 4.

[0055] In step 510, the computer device 200 may generate questions to elicit additional information that may help in the selection of the first information provider. As described above, the content of the user's prompt may be insufficient to match the information of a particular information provider. In this case, the computer device 200 may generate questions to guide the user's prompt to include sufficient information in order to match the user's prompt with the information provider's information. Such questions may also be generated using LLM.

[0056] In step 520, the computer device 200 may provide a 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, completing the content of the user's prompt. Such generation and provision of questions may be repeated until the content of the user's prompt matches the information of a specific information provider. Information providers whose registered information matches the content of the user's prompt correspond to the provisionally selected information providers, and as described above, the first information provider may be selected in step 410 through an auction targeting the provisionally selected information providers.

[0057] Figure 6 shows an example of a process for providing responses to user prompts in one embodiment of the present invention. In the embodiment of Figure 6, an example is described in which the information provider intends to publish an advertisement for an advertiser's product or service as the information to be provided.

[0058] The search system 320 may receive input to a user prompt 601 from a user's terminal connected via the network 170. For example, the prompt may correspond to a natural language-based search term entered by the user. The user may enter the search term via the user interface of the search service provided through the terminal, and the search system 320 may receive the search term entered via the user interface as a user prompt 601.

[0059] In this case, the search system 320 may analyze the user prompt 601 through the process of User Intent Extracting & Summarizing 602 to extract and summarize the user intent, thereby calculating the prompt that will actually be used.

[0060] On the other hand, the search system 320 and / or the response generation system 310 may guide the user to provide sufficient information to help provide a response that reflects the advertiser's marketing message. For example, the content of the user prompt 601 may be insufficient to match the marketing message of a particular advertiser. In this case, the response generation system 310 may generate a question to guide the user to provide additional information that helps select a particular advertiser, and may provide the generated question to the user via the search system 320. After this, when the user's response to the question is received, the prompt may be supplemented using the content of the received response. The Question Specification Prompt 603 may include a prompt derived from the user's response.

[0061] At this time, the search system 320 and / or the response generation system 310 may select a Specified User Prompt 604 that has been designated as a prompt for providing a marketing message. In other words, the specified user prompt 604 may be determined based on a prompt obtained through user intent extraction and summarization 602 for a user prompt 601 and a question specification prompt 603.

[0062] A Prompt Ads Safe Check 605 may be an example of a process for verifying whether a specified user prompt 604 is a prompt that does not pose a problem in disclosing an advertiser's marketing message to a user. For example, if the search system 320 is not a prompt that requests pre-configured illegal or non-advertising information, it may request the response generation system 310 to generate and provide a response.

[0063] The search system 320 may also input the specified user prompt 604 into the LLM to generate LLM results. Figure 5 shows an example of an Organic LLM Result Memory 606 that stores such LLM results.

[0064] The response generation system 310 may provisionally select advertisers associated with the LLM results based on the LLM results stored in the Organic LLM Result Memory 606. In this case, advertisers associated with the LLM results may be advertisers who have registered marketing messages that can be publicly displayed together with the LLM results without any issues. Marketing messages that can be displayed together with the LLM results without any issues may be selected based on the relationship between the information registered by the advertiser and the LLM results. Depending on the embodiment, the response generation system 310 may also use at least one of the user prompts 604, the LLM results, and recommendation queries generated by the large-scale language model when provisionally selecting advertisers. In this case, the response generation system 310 may provisionally select advertisers based on the relationship between at least one of the user prompts 604, the LLM results, and recommendation queries and the information registered by the advertiser. In this case, the response generation system 310 may select a specific advertiser from the provisionally selected advertisers through an Ad Prompt Auction 607.

[0065] Once an advertiser is selected, the answer generation system 310 may obtain advertising assets 608 and advertiser prompts 609 registered by the selected advertiser. In this case, the answer generation system 310 may use at least one of the user prompts 601 and LLM results stored in the organic LLM result memory 606, along with at least one of the advertising assets 608 and advertiser prompts 609, to generate an answer prompt 610 that reflects the advertiser's marketing message. Depending on the embodiment, the advertiser may want to provide answers in a specific format depending on the user's characteristics. For this purpose, the answer generation system 310 may generate an answer prompt 610 that further reflects information about the user. For example, the information about the user may include at least one of the user's demos, interests, and purchase information. For example, suppose the answer generation system 310 analyzes the advertiser prompt 609 and finds 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 demonstration and then generate the response prompt 610 taking into account the determined user's gender.

[0066] Once a response prompt 610 is generated, the response generation system 310 may verify 611 whether the generated response prompt 610 is generated to match the tone and / or format to be confirmed through the advertiser's prompt 609. If the generated response prompt 610 does not match the tone and / or format desired by the advertiser, the response prompt 610 may be modified to match the tone and / or format desired by the advertiser. Alternatively, depending on the embodiment, the response generation system 310 may perform additional verifications, such as whether the generated response prompt 610 is safe to publish.

[0067] Subsequently, the answer generation system 310 may provide the finally generated answer 612 to the user via the search system 320. For example, the search system 320 may add the answer 612 provided by the answer generation system 310 to the search results and provide it to the user through the search service. Alternatively, depending on the embodiment, user information recorded in the Data Management Platform (DMP) 613 (for example, gender, age, interests, etc.) may be further used 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.

[0068] Figure 7 shows an example of providing search results in one embodiment of the present invention. Figure 7 shows 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 user prompt input. The search page 700 may also 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 using Large Language Models (LLM) in response to user prompts.

[0069] Furthermore, the search results area 720 shows an example of an answer area 740 that displays the answer generated by the answer generation system 310 in response to the user prompt. In this embodiment, an example is shown in which multiple answers are displayed in the answer area 740. In this way, multiple answers may be generated and displayed for a single prompt. Moreover, answers may be generated and displayed for each of two or more information providers. For this purpose, the answer generation system 310 may select two or more information providers.

[0070] On the other hand, the embodiment of Figure 7 shows an example in which the responses of an information provider selected based on user prompts entered into the user interface 710 and / or LLM results displayed in the LLM results area 730 are displayed in the extended area 750. For example, the extended area 750 may further display the responses of an information provider selected based on at least one of the user prompts, LLM results, and recommendation queries generated by the large language model. If the information provider is an advertiser, the extended area 750 may further display advertisements from the advertiser selected based on at least one of the user prompts, LLM results, and recommendation queries generated by the large language model.

[0071] Furthermore, the dashed frame 760 displays a question to request additional user prompts related to the answer displayed in the extended area 750. If the user selects a particular question, that question may be recognized as an additional user prompt. When an interactive search service is provided, the additional user prompt may be recognized as the user's next interaction. In this case, the search system 320 and / or the answer generation system 310 may generate LLM results and / or answers after considering the overall interaction with the user.

[0072] Furthermore, while the embodiment in Figure 7 describes an example of dynamically generating answers by receiving user prompt input via the user interface 710 of the search service, depending on the embodiment, the search results may also include an interface for generating and providing dynamic answers. For example, the user may be provided with a function that dynamically generates and provides answers by receiving user prompt input through various vertical services and / or parts thereof provided in the existing search ecosystem. Here, vertical services may mean services for 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 vertical service of the integrated search service, the user may be provided with a function that dynamically generates and displays answers by receiving user prompt input through the shopping search service. If multiple different advertising services are provided as vertical services of the integrated search service, the user may be provided with a function that dynamically generates and provides answers by receiving user input through each of these multiple advertising services.

[0073] Thus, according to embodiments of the present invention, it is possible to provide a method and system for dynamically generating artificial intelligence-based responses that reflect the information provider's message.

[0074] The apparatus described above may be implemented by hardware components, software components, and / or combinations of hardware and software components. For example, the apparatus and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as processors, controllers, ALUs (arithmetic logic units), digital signal processors, microcomputers, FPGAs (field programmable gate arrays), PLUs (programmable logic units), microprocessors, or various devices capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications running on the OS. The processing unit may also respond to software execution, access data, record, manipulate, process, and generate data. For convenience of understanding, it may be described as if a single processing unit is used, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Other processing configurations, such as parallel processors, are also possible.

[0075] Software may include computer programs, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or which may instruct the processing unit independently or collectively. Software and / or data may be embodied in any kind of machine, component, physical device, virtual equipment, computer recording medium, or device for interpretation based on the processing unit or for providing instructions or data to the processing unit. Software may be distributed across a network of computer systems, and may be recorded or executed in a distributed manner. Software and data may be recorded on one or more computer-readable recording media.

[0076] The methods according to the embodiment may be implemented in the form of program instructions executable by various computer means and may be recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., individually or in combination. The medium may continuously record computer-executable programs or may temporarily record them for execution or download. The medium may also be a variety of recording or storage means in the form of a combination of one or more hardware components, and may be a medium directly connected to a computer system or distributed on a network. Examples of media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and media configured to record program instructions such as ROMs, RAMs, and flash memories. Other examples of media include recording media and storage media managed by app stores that distribute applications, and sites and servers that supply and distribute various other software. Examples of program instructions include not only machine code such as that generated by a compiler, but also high-level language code that is executed by a computer using an interpreter or the like.

[0077] As described above, embodiments have been explained based on limited embodiments and drawings, but those skilled in the art will be able to make various modifications and variations from the above description. For example, the described technique may be performed in a different order than described, and / or the components of the described system, structure, apparatus, circuit, etc. may be combined or assembled in a different manner than described, or opposed or replaced by other components or equivalents, and still achieve suitable results.

[0078] Therefore, even if the embodiment is different, it falls within the scope of the attached claims if it is equivalent to the claims.

Claims

1. A method for generating answers for a computer device including at least one processor, The process involves at least one processor selecting a first information provider from among multiple information providers based on LLM results generated using a large-scale language model in response to a user prompt, The steps include: dynamically generating a response that reflects information registered in association with the selected first information provider using at least one processor; The steps include providing the user with the answer generated by the at least one processor, A method for generating answers, including the method itself.

2. The step of selecting the first information provider is: The steps include: provisionally selecting an information provider from the aforementioned multiple information providers that is relevant to at least one of the user prompts, the LLM results, and the recommendation queries generated by the large-scale language model; The first information provider is selected by dynamically conducting an auction among the provisionally selected information providers, The method for generating an answer according to claim 1, including the method described in claim 1.

3. The step of dynamically generating the aforementioned answer is: The response generation method according to claim 1, comprising dynamically generating the response using at least one of the assets registered by the first information provider and the prompts registered by the first information provider.

4. The response generation method according to claim 3, wherein the assets registered by the first information provider include at least one of the following: a URL related to the content that the first information provider intends to provide, the title of the content, the identifier name of the content, the category of the content, the multimedia related to the content, the content of the content, and the article content related to the content.

5. The response generation method according to claim 3, wherein the prompt registered by the first information provider includes at least one of the following: a phrase entered to emphasize in relation to the content that the first information provider intends to provide; keywords entered by the first information provider to emphasize in relation to the content; the tone of the information message to be provided as the response; and the format of the information message.

6. The step of dynamically generating the aforementioned answer is: The response generation method according to claim 1, which generates the response that further reflects at least one of the user prompts and the LLM results.

7. The step of dynamically generating the aforementioned answer is: The aforementioned response is generated, which further reflects information about the aforementioned user. The response generation method according to claim 1, wherein the information relating to the user includes at least one of the user's demo, interests, and purchase information.

8. The user prompt is entered through the search service, The method for generating an answer according to claim 1, wherein the dynamically generated answer is included in the search results for the user's prompt and provided to the user through the search service.

9. The response generation method according to claim 8, wherein the search results further include the LLM results.

10. The user prompt is input through interaction between the user and the artificial intelligence utilizing the large-scale language model. The method for generating an answer according to claim 1, wherein the dynamically generated answer is included in the answer result to the user's prompt and provided to the user.

11. The steps include: generating a question using at least one processor to elicit additional information that will help in the selection of the first information provider; The steps include providing the user with the question generated by the at least one processor, The method for generating an answer according to claim 1, further comprising:

12. A program recorded on a computer-readable recording medium for causing the computer device to execute the answer generation method according to any one of claims 1 to 11.

13. A computer device comprising at least one processor configured to execute instructions readable by the computer device, With the aforementioned at least one processor, In response to user prompts, a first information provider is selected from multiple information providers based on LLM results generated using a large-scale language model. Dynamically generate a response that reflects the information registered in association with the selected first information provider, A computer device that provides the generated response to the user.

14. In order to select the first information provider, the at least one processor performs the following: From the aforementioned multiple information providers, a provisional selection is made of information providers related to at least one of the user prompts, the LLM results, and the recommendation queries generated by the large-scale language model. The computer device according to claim 13, which selects the first information provider by conducting an auction among the provisionally selected information providers.

15. To dynamically generate the aforementioned answer, at least one processor is used: The computer device according to claim 13, which dynamically generates the response using at least one of the assets registered by the first information provider and the prompts registered by the first information provider.

16. To dynamically generate the aforementioned answer, at least one processor is used: The computer device according to claim 13, which generates the response that further reflects at least one of the user prompts and the LLM results.

17. To dynamically generate the aforementioned answer, at least one processor is used: The aforementioned response is generated, which further reflects information about the aforementioned user. The computer device according to claim 13, wherein the information relating to the user includes at least one of the user's demonstrations, interests, and purchase information.

Images