KR-20260064690-A - Configuration of an artificial intelligence (AI) bot with a simulated persona to participate in automated conversations

KR20260064690AKR 20260064690 AKR20260064690 AKR 20260064690AKR-20260064690-A

Abstract

Feedback on options can be generated using an artificial intelligence (AI) bot having a simulated persona. For example, the system may receive a selection of an option from a group of options by a selector. Based on a selector profile associated with the selector, the system may configure a first AI bot to simulate the selector. Based on an end-user profile, the system may also configure a second AI bot to simulate the end-user of the option. Subsequently, the system may initiate a conversation regarding the selected option between the first AI bot and the second AI bot. Based on the conversation, the system may generate feedback on the option. Subsequently, the system may provide the feedback on the option to the selector.

Inventors

알레스, 톰 엠.
베커, 스티븐
불로스, 조나단 디.
마해피, 클리어리 이.
패리스, 대런
레시오, 마크
타워, 시어도어 티.

Assignees

킴벌리-클라크 월드와이드, 인크.

Dates

Publication Date: 20260507
Application Date: 20240905
Priority Date: 20230906

Claims (20)

As a computer-implemented method, A step of receiving a selection of an option from a group of options through a user interface by a selector; A step of configuring a first artificial intelligence (AI) bot to simulate the selector based on a selector profile associated with the selector; A step of configuring a second AI bot to simulate the end user of the above option based on the end user profile; A step of initiating a conversation about options between the first AI bot and the second AI bot; A step of generating feedback on the above options based on the above conversation; and A computer-implemented method comprising the step of providing feedback on the option to the selector through the user interface.
A method according to claim 1, wherein the option is a physical object, and the group of options comprises a group of deployable objects at one or more physical locations associated with the selector.
A method according to claim 1, wherein the option is an object feature, and the group of options includes a group of object features.
In paragraph 1, A step of configuring a plurality of second AI bots to simulate a plurality of end users of the above options based on one or more end user profiles; A step of initiating a plurality of conversations regarding the option between the first AI bot and the plurality of second AI bots; and A method further comprising the step of generating the feedback based on the plurality of conversations above.
In paragraph 1, A step of configuring a plurality of first AI bots to simulate the selector based on the selector profile above; A step of configuring a plurality of second AI bots to simulate a plurality of end users of the above options based on one or more end user profiles; A step of initiating a plurality of conversations regarding the option between the plurality of first AI bots and the plurality of second AI bots; and A method further comprising the step of generating the feedback based on the plurality of conversations above.
In paragraph 1, A step of providing the conversation as input to an analyzer model different from the first AI bot and the second AI bot, wherein the analyzer model includes a machine learning model configured to output a metric based on the conversation, and the metric is different from the feedback; and A method further comprising the step of generating the feedback based on the above metric.
In paragraph 1, A step of receiving a selection of the selector profile by the selector through the user interface above—the selector profile is selected from a group of selector profiles available for selection in the user interface—; and A method further comprising the step of configuring the first AI bot to simulate the selector by providing the first AI bot with an input prompt having data from the selector profile based on receiving the selection and before initiating the conversation.
In paragraph 1, A step of receiving a selection of the end user profile by the selector through the user interface, wherein the end user profile is selected from a group of end user profiles available for selection in the user interface; and A method further comprising the step of configuring the second AI bot to simulate the end user by providing the second AI bot with an input prompt having data from the end user profile based on receiving the above selection and before initiating the above conversation.
A method according to claim 1, further comprising the step of generating a selector profile based on collected data regarding the selector.
The method according to claim 1 further comprises the step of generating the end user profile based on collected data regarding one or more end users, wherein the one or more end users are different from the selector.
A method according to claim 1, wherein the first AI bot and the second AI bot comprise a large-scale language model (LLM).
As a system, One or more processors; and The operation includes one or more memories containing program code executable by the one or more processors to enable the one or more processors to perform an operation, and the operation Receiving a selection of an option from a group of options through a user interface by a selector; Configuring a first artificial intelligence (AI) bot to simulate the selector based on a selector profile associated with the selector; Configuring a second AI bot to simulate the end user of the above option based on the end user profile; Initiating a conversation about options between the first AI bot and the second AI bot; Generating feedback on the above options based on the above conversation; and A system comprising providing feedback on the option to the selector through the user interface.
In Clause 12, the above operation is Configuring a plurality of second AI bots to simulate a plurality of end users of the above options based on one or more end user profiles; Initiating a plurality of conversations regarding the option between the first AI bot and the plurality of second AI bots; and A system further comprising generating the feedback based on the plurality of conversations above.
In Clause 12, the above operation is Configuring a plurality of first AI bots to simulate the selector based on the above selector profile; Configuring a plurality of second AI bots to simulate a plurality of end users of the above options based on one or more end user profiles; Initiating a plurality of conversations regarding the option between the plurality of first AI bots and the plurality of second AI bots; and A system further comprising generating the feedback based on the plurality of conversations above.
In Clause 12, the above operation is Providing the conversation as input to an analyzer model different from the first AI bot and the second AI bot—the analyzer model is a machine learning model configured to output a metric based on the conversation, and the metric is different from the feedback—; and A system further comprising generating the feedback based on the above metric.
In Clause 12, the above operation is Receiving a selection of the selector profile by the selector through the user interface above—the selector profile is selected from a group of selector profiles available for selection in the user interface—; and A system further comprising configuring the first AI bot to simulate the selector by providing the first AI bot with an input prompt having data from the selector profile based on receiving the above selection and before initiating the above conversation.
In Clause 12, the above operation is Receiving the selection of the end user profile by the selector through the above user interface—the end user profile is selected from a group of end user profiles available for selection in the above user interface—; and A system further comprising configuring the second AI bot to simulate the end user by providing the second AI bot with an input prompt having data from the end user profile based on receiving the above selection and before initiating the above conversation.
A system according to claim 12, wherein the operation further comprises generating a selector profile based on collected data regarding the selector.
In paragraph 12, the operation further comprises generating the end user profile based on collected data regarding one or more end users, wherein the one or more end users are different from the selector, the system.
A non-transient computer-readable medium comprising program code executable by one or more processors to enable one or more processors to perform an operation, wherein the operation is Receiving a selection of an option from a group of options through a user interface by a selector; Configuring a first artificial intelligence (AI) bot to simulate the selector based on a selector profile associated with the selector; Configuring a second AI bot to simulate the end user of the above option based on the end user profile - said end user is different from said selector -; Initiating a conversation about options between the first AI bot and the second AI bot; Generating feedback on the above options based on the above conversation; and A non-transient computer-readable medium comprising providing feedback on the option to the selector through the user interface.

Description

Configuration of an artificial intelligence (AI) bot with a simulated persona to participate in automated conversations Cross-reference regarding related applications This application claims priority to U.S. Provisional Application No. 63/580,989 filed on September 6, 2023, which is incorporated herein by reference. Technology field The present disclosure generally relates to artificial intelligence. More specifically, without limitation, the present disclosure relates to configuring an artificial intelligence (AI) bot with a simulated persona to engage in automated conversations. Machine learning and artificial intelligence are revolutionizing various industries by enabling machines to learn from data and make intelligent decisions. At the core of these technologies lies the neural network. Neural networks and other machine learning models are trained on vast datasets to optimize performance and accuracy. Furthermore, a model's hyperparameters can play a critical role in its performance, such as its ability to simulate complex patterns and make predictions. By carefully fine-tuning these hyperparameters, machine learning practitioners can enhance the capabilities of artificial neural networks, thereby enabling the implementation of more sophisticated and effective models capable of solving a wide range of tasks. New types of machine learning tools are continuously being developed. Among these, AI bots such as OpenAI®’s ChatGPT have recently gained popularity. These AI bots utilize natural language models, such as Large Language Models (LLMs), to process natural language input and provide natural language output. LLMs are advanced AI systems designed to understand and generate human language with remarkable accuracy. By leveraging Natural Language Processing (NLP) techniques, LLMs can analyze and interpret text to grasp the meaning, sentiment, and context of sentences. These models are useful for various applications as they can generate consistent and contextually relevant responses. For example, in the audio domain, LLMs can be integrated with speech recognition technology to convert spoken words into text, thereby bridging the gap between voice and text-based communication. This functionality is particularly beneficial for telephone-based interactions where accurately understanding and responding to voice queries is essential. One example of the present disclosure may include a computer-implemented method comprising providing a user interface that allows a chooser to select from a group of options. The method may also include the step of receiving a selection of an option from a group of options by the chooser through the user interface. The method may also include the step of configuring a first artificial intelligence (AI) bot to simulate the chooser based on a chooser profile associated with the chooser. The method may also include the step of configuring a second AI bot to simulate an end user of the option based on an end user profile. The method may also include the step of initiating a conversation about the option between the first AI bot and the second AI bot. The method may also include the step of generating feedback about the option based on the conversation. The method may also include the step of providing feedback about the option to the chooser through the user interface. Another example of the present disclosure comprises a system comprising one or more processors and one or more memories, wherein the one or more memories comprise program code executable by one or more processors to cause the one or more processors to perform an operation. The operation may include providing a user interface that allows a selector to select from a group of options. The operation may include receiving a selection of an option from a group of options by the selector through the user interface. The operation may include configuring a first artificial intelligence (AI) bot to simulate the selector based on a selector profile associated with the selector. The operation may include configuring a second AI bot to simulate an end user of the option based on an end user profile. The operation may include initiating a conversation about the option between the first AI bot and the second AI bot. The operation may include generating feedback about the option based on the conversation. The operation may include providing feedback about the option to the selector through the user interface. Another example of the present disclosure comprises a non-transient computer-readable medium comprising program code executable by one or more processors to cause one or more processors to perform an operation. The operation may include providing a user interface that allows a selector to select from a group of options. The operation may include receiving a selection of an option from a group of options by the selector through the user interface. The operation may include configuring a first artificial intelligence (AI) bot to simu