Real-time adaptive avatar creation system using integrated programmatic and specialized guided and constrained artificial intelligence

Abstract

A system and method for guiding an Artificial Intelligence (Al) engine creates and operates a real-time, personalized and dynamically adapting avatar that mimics a human representative. The real-time adaptive avatar generation process receives initial human representative data human data such as video, images, or audio recording through an Al guidance and control system (110). The human representative data is analyzed to generate a prompt by a prompt generator to capture the physical and vocal characteristics of the human representative. The Al engine uses generative algorithms to produce a three-dimensional model reflecting unique attributes like facial structure and skin tone. It also employs voice synthesis algorithms to replicate the vocal properties of the human representative, including pitch, tone, and accent. The avatar continuously learns and updates its features based on ongoing multimodal interaction data, integrating their preferences, behaviors, and changes in appearance to enhance the realism and personalization of the avatar.

Description

Atorney Docket No. T00708-716-717NE-PCTREAL-TIME ADAPTIVE AVATAR CREATION SYSTEM USING INTEGRATED PROGRAMMATIC AND SPECIALIZED GUIDED AND CONSTRAINED ARTIFICIAL INTELLIGENCECROSS-REFERENCE TO RELATED APPLICATIONThis application claims the benefit under 35 U.S.C. § 119(e) and 37 C.F.R. § 1.78 of the following U.S. Provisional Application Nos., which are all incorporated by reference in their entireties: 63 / 693,180 filed September 11, 2024, 63 / 693,181 filed September 11, 2024, 63 / 693,182 filed September 11, 2024, 63 / 720,181 filed November 14, 2024, 63 / 738,421 filed January 6, 2025, and 63 / 810,751, filed June 5, 2025.Field of the Invention

[0001] The present invention relates in general to the field of electronics, and more specifically to avatar generation systems and avatar generation methods for creating personalized and dynamically adapting and operating avatars that represent human representatives.BACKGROUND

[0002] Conventional artificial intelligence (Al) created avatars are animated characters that utilize static information for appearances and actions. Conventional Al created avatars do not track and, thus, are unable to adapt to new information or other changes over time. Once an avatar is created based on initial input such as a description, photo, or other representation, the avator’s primary characteristics remain frozen in time, with no capacity for change unless manually updated. This lack of adaptability means that an avatar’s appearance or behavior does not change over time. Consequently, an avatar may no longer accurately represent a particular subject, particularly a living subject. For example, if a user gains or loses weight, changes their hairstyle, or undergoes any other form of transformation, the avatar remains unchanged unless the user actively updates it. This static nature can detract from the sense of immersion and personalization, making the avatar feel outdated or less authentic as time goes on thereby reducing the overall user experience.Atorney Docket No. T00708-716-717NE-PCT

[0003] The traditional avatars necessitate manual intervention to incorporate any changes or updates. Whether the change involves altering the appearance of the avatar, modifying its behavior, or incorporating new elements based on the user’s evolving preferences, the updates require user input. This not only makes the process time-consuming but also limits the scalability. The manual updates create a bottleneck, reducing the overall flexibility of the avatar. Additionally, the process becomes increasingly cumbersome when dealing with large numbers of avatars, as the effort is needed to maintain and update them consistently.

[0004] The traditional avatar is designed with a predefined set of interactions. The avatars often rely on simple, scripted responses to user input, such as basic gestures, facial expressions, or limited speech options. However, these interactions are not adaptive and do not evolve based on user behavior or preferences. As a result, the responses of the avatar become repetitive and predictable over time, creating a sense of disengagement for the user. Additionally, traditional avatars lack the ability to learn from user input or adjust their behavior based on past interactions. This limitation creates a static experience that is not fully immersive or personalized.

[0005] In an attempt to make avatars engaging, a range of strategies introduce some level of interactivity and personalization. However, these methods fail to fully address the limitations mentioned above. The avatars are implemented with scripted responses. The scripted responses are pre-defined sequences of actions or words that the avatar uses to respond to user interactions. While scripted responses can simulate some level of interaction, they are inherently limited by their predictability and lack of flexibility. Moreover, many traditional avatars rely on single- modal input, such as text or voice commands, to generate and update avatars. While this approach works in some contexts, it fails to capitalize on the broader range of input types. The traditional avatar only uses one form of input, such as a user typing text into a chat interface or speaking into a microphone. This restriction limits the potential for creating dynamic and interactive avatars, as the responses are confined to a narrow range of inputs and lack the depth and variety that would allow for a more lifelike and engaging experience.Atorney Docket No. T00708-716-717NE-PCTBRIEF DESCRIPTION OF THE DRAWINGS

[0006] The systems and methods described herein may be better understood, and their numerous objects, features, and advantages made apparent to those skilled in the art by referencing exemplary embodiments depicted in the accompanying figures. The use of the same reference number throughout the several figures designates a like or similar element.

[0007] Figure 1 depicts an exemplary real-time adaptive avatar generation system to create a personalized and dynamically adapting avatar that represents a human representative.

[0008] Figure 2 depicts an exemplary real-time adaptive avatar generation process utilized by the avatar generation system.

[0009] Figure 3 depicts a data structure for creating the real-time adaptive avatar using multimodal inputs.

[0010] Figures 4-6 are exemplary user interfaces depicting interaction of the real-time adaptive avatar with the user.

[0011] Figure 7 depicts a workflow diagram for creating the real-time adaptive avatar.

[0012] Figure 8 depicts an exemplary network environment in which the real-time adaptive avatar generation system of Figure 1 and the real-time adaptive avatar generation process of Figure 2 may be practiced.

[0013] Figure 9 depicts an exemplary computer system.DETAILED DESCRIPTION

[0014] The system and method for guiding an Artificial Intelligence (Al) engine to create and operate a personalized and dynamically adapting avatar that mimics a human representative. The avatar may be 2-dimensional or 3 -dimensional. The real-time adaptive avatar generation process receives initial human representative data such as video, images, or audio recording through an Al guidance and control system 110. The human representative data is analyzed to generate a prompt by a prompt generator to capture the physical and vocal characteristics of the human representative. The Al engine uses generative algorithm to produce a three-dimensional model reflecting unique attributes like facial structure and skin tone. The Al engine also employs voiceAtorney Docket No. T00708-716-717NE-PCT synthesis algorithms to replicate the vocal properties of the human representative, including pitch, tone, and accent. The traditional avatar is designed with a predefined set of interactions, which severely limits the ability to engage with users in a meaningful and dynamic way. The real-time adaptive avatar continuously learns and updates its features based on ongoing multimodal interaction data, integrating their preferences, behaviors, and changes in appearance to enhance the realism and personalization of the avatar.

[0015] The real-time adaptive avatar generation process integrates facial recognition techniques within the generative algorithm, refining the likeness of the avatar by accurately detecting unique facial biometrics, such as eye shape and jawline. The voice synthesis algorithm employs deep neural networks trained on a variety of audio samples to ensure an authentic vocal reproduction that captures the nuances of regional accents and pronunciation patterns. Moreover, a continuous learning algorithm utilizes reinforcement learning techniques to adapt the avatar's responses based on feedback, making conversations more natural and aligned with evolving preferences. Additionally, the avatar generation process extracts non-verbal behaviors such as gestures and facial expressions from video data, allowing the avatar to engage in more realistic and relatable interactions in real-time.

[0016] The real-time adaptive avatar generation process uses sentiment analysis within the natural language processing (NLP) algorithm to interpret emotional cues from user input, enabling the avatar to respond empathetically to the emotional state of the human representative. Moreover, the avatar generation process uses predictive algorithms that leverage historical interaction data, enabling the avatar to anticipate user preferences and adjust its appearance, speech, and behavior accordingly. Furthermore, the generative and voice synthesis algorithms are designed to operate instantaneously, allowing the Al engine to make immediate updates in response to ongoing user engagements to ensure that the avatar not only mirrors the human representative's identity but also evolves with their dynamic preferences and characteristics, creating an immersive and engaging experience.

[0017] The system and method set forth herein address technical issues with generating the desired outputs described herein. Conventionally, manual processes were used to generate the desired outputs and were very tedious and time consuming. The present system and methodAtorney Docket No. T00708-716-717NE-PCT utilize an automated system that does not merely automate a manual process or use a conventional system in a conventional way. The present system and method utilize one or more artificial intelligence (Al) engines and integrate programmatic process management to technologically guide and constrain the one or more Al engines to produce the desired outputs in a completely different way than any manual process and different than normal use of programs and Al engines. Utilizing specially engineered guidance and control to direct an Al system to solve the problems below presents a technical problem that requires a technical solution. The system and method described below are not simply engaging a computer to carry out conventional mental processes, but rather change how computers (and Al systems, specifically) operate to achieve the generation results that were not previously possible or were substantially inefficient prior to the system and method set forth below. The Al system needs specific technical guidance, control, and constraints to achieve results that are not otherwise achievable.

[0018] Prompts are used to guide and constrain each Al engine. The prompts guide each Al engine by steering the Al engine(s). “Guiding” an Al engine refers to providing the Al engine with a general direction or framework to shape the Al engine’s behavior or decision-making process. Guiding sets goals or principles. Guiding allows the Al engine some flexibility to interpret and adapt, much like giving it a compass to navigate rather than a fixed path.

[0019] Constraining each Al engine includes imposing specific, hard limits or rules on what each Al engine can do. Constraining an Al engine can also include providing specific input data to not only guide but also constrain the scope of each Al engine’s reasoning basis and response. Constraining each Al engine assists with aligning the Al engine(s) for its(their) intended use.

[0020] Normally Al engines are provided a single user prompt requesting the Al engine, such as OpenAI’s ChatGPT and its various implementations such as Anthropic’s Claude Sonnet, to perform a task and produce an output. However, this conventional Al engine prompting method has a variety of technical shortcomings. Without proper guidance and constraints, an Al engine will not produce the desired output specified as produced by the system and method described herein. Instead, the Al engine will produce many unusable outputs that are unusable for a variety of reasons including so-called “hallucinations” where the Al engine presents fabricated information, duplicate outputs, too few outputs, too many outputs, outputs that do not meetAtorney Docket No. T00708-716-717NE-PCT desired criteria, and so on. Without special technical guidance, the Al engine cannot reliably be applied to generate desired outcomes.

[0021] The system and method generate decomposed, technically engineered Al prompts to include selected and integral Al engine guidance and constraints. The technically engineered prompts are generated and guided with programmatic, automatic inputs specifically designed to unconventionally guide and constrain an Al engine to produce desired outputs, perform quality control to retain or automatically discard outputs that do not meet guidance and constraints, and make the desired outputs available for use, such as use by computer system applications. In at least one embodiment, the problem to be solved by the integrated programmatic and Al engine system and method is uniquely and unconventionally decomposed, and Al prompts are used to solve the decomposed problem. Furthermore, the programmatic inputs to the decomposed Al prompts provide guidance to meet desired output characteristics.

[0022] Determining a number of prompts, the guidance and constraints within each prompt, and data flowing from one Al engine prompt to another, in addition to testing a number of prompts for the decomposed problem, testing within each prompt, and validating a desired quality of outputs becomes an intractable combinatorial problem without technical guidance and constraint of the system and method described herein. Thus, the present system and method described implement an integration of programmatic management over decomposed prompts with engineered Al engine guidance and constraints to effect an improvement in Al, programmatic Al management, and Al integrated with programmatic management technology. The present system and method allow computer systems to include programmatic management, one or more Al engines, and one or more data sources to produce the output described herein that previously could not be produced with conventionally prompted Al engines or could only be produced by humans utilizing a completely different, time consuming, and tedious process. The system and method improve conventional methods through the use of a programmatic Al engine management system to generate decomposed, technically engineered Al prompts to include selected and integral Al engine guidance and constraints. It is, for example, the incorporation of the programmatic Al engine management system to generate decomposed, technically engineered Al prompts to include generated, integral, and unconventional Al engine guidanceAtorney Docket No. T00708-716-717NE-PCT and constraints and execution by the one or more Al engines to provide useful results that improve existing technical processes, which is not an automation of a conventional process.

[0023] Programmatic components and Al engines generally utilize one or more processors that have access to memory, which may include one or more storage components, to execute and perform functions. An Al engine is a core hardware and software system that enables artificial intelligence applications to process data, learn patterns, and generate insights or actions. It functions as the brain behind Al-driven systems, facilitating tasks such as machine learning, natural language processing, and decision-making. Exemplary components of an Al engine are:1. Machine Learning Models - Algorithms that analyze data, recognize patterns, and make predictions.2. Neural Networks - Deep learning architectures that mimic the human brain for tasks like image and speech recognition.3. Data Processing Module - Handles raw data input, transformation, and feature extraction.4. Inference Engine - Applies trained models to make real-time decisions based on new data.5. Optimization Algorithms - Improves model efficiency, reducing errors and improving predictions.6. Natural Language Processing (NLP) Module - Enables Al engines to understand, interpret, and generate human language (e.g., chatbots, voice assistants).7. Computer Vision Module - Allows Al to interpret and analyze images or videos.8. Reinforcement Learning Mechanism - Helps Al leam from trial and error, optimizing performance over time.9. API Interface - Connects the Al engine with applications, enabling integration with other software or platforms.

[0024] Examples of Al Engines include: XAI’s Grok and variations thereof, Google TensorFlow, Meta's PyTorch, Microsoft Azure Al, OpenAI’s ChatGPT and variations thereof,Atorney Docket No. T00708-716-717NE-PCTIBM Watson, OpenAI Whisper, Google BERT & T5, Amazon Lex, Anthropic Claude, DeepMind’s AlphaCode, Google Vision Al, Meta's DINO & SAM (Segment Anything Model), NVIDIA DeepStream. OpenCV Al Kit, Amazon Polly. Google WaveNet, Deepgram.

[0025]

[0026] Figure 1 depicts an exemplary real-time adaptive avatar generation system 100 to create a personalized and dynamically adapting avatar 102 that represents a human representative 104. Figure 2 depicts an exemplary real-time adaptive avatar generation process 200 utilized by the real-time adaptive avatar generation system 100.

[0027] The Artificial Intelligence (Al) engine 106 is designed to create a personalized, dynamically adapting avatar 102. The Al engine 106 involves instructing the avatar 102 to understand specific traits and preferences of the human representative 104. The avatar 102 is a digital representation designed to simulate human-like attributes, including appearance, behavior, or communication style. The avatar 102 processes and replies to the user in any form such as text, voice, gestures, or other forms of interaction. The avatar 102 is designed to mimic human behaviors and interactions, providing a more personalized and engaging user experience. The Al engine 106 utilizes a plurality of algorithms to mimic the human representative 104 to provide personalized assistance to the user. The user is a person who is interacting with the avatar. The avatar 102 interacts in a way that feels genuine, responsive, and adaptable.

[0028] Referring to Figures 1 and 2, in operation 202, receiving an initial human representative data 108 via an Al guidance and control system 110, which includes an Al guidance and control system 110. The initial human representative data 108 includes at least one of video, image, or audio recording provided by the human representative 104 representing the appearance, body structure, natural voice, and tone of the human representative 104. The initial human representative data 108 refers to the primary information submitted directly by the human representative 104 via the Al guidance and control system 110. The initial human representative data 108 is utilized to construct the avatar 102 that accurately replicates the identity and presentation of the human representative 104. By obtaining data directly from the humanAtorney Docket No. T00708-716-717NE-PCT representative 104, the avatar emulates the voice, body structure, tone, and appearance of the human representative 104 in a natural and recognizable way.

[0029] The Al guidance and control system 110 serves as the medium through which the information such as initial human representative data 108 is shared and processed. The Al guidance and control system 110 provides the human representative 104 a simple and secure way to upload the initial human representative data 108. The Al guidance and control system 110 provides flexibility, allowing the human representative 104 to submit the initial human representative data 108 from any location and at their convenience. The Al guidance and control system 110 includes a user interface that guides the human representative 104 through the submission process, explaining how initial human representative data 108 should be provided. The human representative 104 can provide video, image, or audio recording.

[0030] The video offers a comprehensive look at the appearance, body language, gestures, and expressions of the human representative 104. The video data allows to analyze natural movement patterns, facial expressions of the human representative 104 and how he might gesture while speaking. The non-verbal cues are essential for creating the avatar 102 that feels realistic. The video provides a continuous sequence of frames, allowing to observe subtle details, such as the way the human representative 104 smiles, raises their eyebrows, or even tilting of head while speaking. By capturing these dynamic traits, video data helps to understand and reproduce the nuanced qualities ensuring the avatar 102 can replicate. The image offers a snapshot of the physical appearance of the human representative 104, which can be useful for fine details like facial structure, skin tone, hair color, and so forth. The images provide clarity on the physical details, which are necessary to create the avatar 102 that visually resembles the human representative 104 as closely as possible. When several images are provided from different angles, the data is utilized to build a model of the human representative 104, capturing their likeness from various perspectives.

[0031] The audio recordings are used for capturing the voice, such as pitch, tone, pace, accent, and rhythm of the human representative 104. The elements of vocal data allow to replicate the speech patterns of the human representative 104 in a natural and convincing way. The audio data is utilized for producing voice outputs that reflect the original voice of the human representativeAtorney Docket No. T00708-716-717NE-PCT104, which can be crucial where voice communication is a primary means of interaction, such as customer service, virtual meetings and the like. Typically, collecting the initial human representative data 108 creates the avatar 102 that mirrors how the human representative 104 looks and sounds and also how the human representatives naturally interact.

[0032] In operation 204, a prompt 112 is generated by a prompt generator 114 to guide the Al engine 106 based on the initial human representative data 108 to generate an initial avatar 102. Typically, the prompt 112 is a detailed set of guidelines encompassing a range of specifications, qualities, and personality traits that instructs the Al engine 106 on how to interpret and use the human representative data 108 to form a realistic and accurate virtual representation. Moreover, the prompt 112 serves as a bridge between the human representative data 108 collected from the human representative 104 and the interpretation of the human representative data 108 to create the avatar 102. The prompt 112 is a set of instructions that define what the avatar 102 should look like and also how the avatar should behave, sound, and respond in interactions. The prompt generator 114 creates a structured or semi-structured set of instructions that serves as the input for the Al engine 106. The prompt 112 encapsulates the human representative data 108 and guides the Al engine 106 in processing information and generating the avatar 102. In at least one embodiment, the prompt 112 is generated by a prompt engineer.

[0033] The prompt 112 includes descriptions derived from the video and image data provided. This includes specifications about facial features, body structure, skin tone, hairstyle, clothing style, and posture to help the Al engine 106 to capture these elements accurately, ensuring that the avatar 102 resembles the human representative 104 closely. The prompt 112 includes specifications related to voice such as tone, pitch, rhythm, and accent to instruct the Al engine 106 on how the avatar should sound. In at least one embodiment, the prompt 112 may also outline behavioral or interactive tendencies based on observations from the initial human representative data 108. For example, the human representative 104 uses certain hand gestures when they speak, or if the human representative is maintaining calm, composed demeanor in the interactions. The behavioral cues can give the avatar 102 a realistic presence.

[0034] In operation 206, transferring the prompt 112 to the Al engine 106 for generating the initial avatar 102. The prompt 112 serves as a blueprint, informing the Al engine 106 forAtorney Docket No. T00708-716-717NE-PCT generating the initial avatar 102. The Al engine 106 analyzes the prompt to interpret the structured instructions within the prompt 112. The Al engine 106 uses the prompt 112 to translate the initial human representative data 108 to capture physical likeness, mirroring the same tone, pitch, and accent to generate the initial avatar 102 of the human representative 104. The initial avatar 102 refers to the first version of a digital representation of the human representative 104, created by the Al engine 106 using the initial human representative data 108 data provided in the prompt 112. The first version is the foundational model of the avatar 102. The initial avatar includes a visual model that captures the primary physical features of the human representative 104, such as facial structure, skin tone, hair characteristics, and other distinct physical traits. This visual model is generated by analyzing images or videos provided in the prompt 112. The initial avatar 102 includes a voice model that replicates the vocal qualities of the human representative 104, including tone, pitch, and accent. Moreover, the initial avatar 102 incorporates distinctive non-verbal behaviors, such as typical gestures, expressions, and postures.

[0035] The Al engine 106 is configured to analyze the video or image with a generative algorithm 116 to create the visual model of the avatar 102 that captures key physical characteristics of the human representative 104, including facial structure, skin tone, and hair characteristics. The Al engine 106 processes the initial human representative data 108 via the generative algorithm 116 to extract the visual details that define the appearance of the human representative 104. Through the generative algorithm 116, the Al engine 106 is able to produce the visual model of the initial avatar 102 that closely resembles the human representative 104. The visual model creates the initial avatar 102 by including intricate details, such as the facial structure, skin tone, and hair characteristics of the human representative 104. By capturing the physical traits, the Al engine 106 generates a visual representation that mimics the features of the human representative 104. The generative algorithm 116 translates visual data from the prompt into the model that replicates the appearance of the human representative 104. The generative algorithm 116 focuses on characteristics such as facial structure highlighting aspects like cheekbone positioning, jawline definition, and forehead shape allowing the avatar 102 to carry a recognizable resemblance to the human representative 104, making the avatar 102 feel lifelikeAtorney Docket No. T00708-716-717NE-PCT and engaging. The generative algorithm 116 also takes into account elements like skin tone and hair characteristics to further enhance visual realism.

[0036] Moreover, utilizing the generative algorithm 116 to create the initial avatar 102 integrates advanced facial recognition techniques, detecting unique facial structure and biometrics, including eye shape, nose contour, and jawline of the human representative 104, making the avatar 102 closely resemble the human representative 104. The facial recognition technology involves the analysis and detection of specific biometric details, helping to refine the resemblance of the avatar 102 to the human representative 104. The facial recognition technology focuses on details like eye shape, nose contour, and jawline. The generative algorithm 116 creates a general facial likeness and captures the unique traits that distinguish one face from another. For example, eye shape, including the curvature of the eyelid and distance between the eyes, is analyzed and replicated to enhance the ability to recognize the avatar 102. Similarly, the nose contour, from bridge width to nostril flare, is detected and accurately mirrored in the avatar 102. By integrating these biometric details, the generative algorithm 116 strengthens the physical accuracy, look and feel of the avatar 102.

[0037] The initial avatar 102 includes specific non-verbal behavioral traits extracted from the video data, such as the natural gestures, facial expressions, or typical postures of the human representative 104, and incorporates the traits into the real-time interactions of the avatar 102. The video data serves as the information for capturing the non-verbal behavioral traits, allowing the avatar 102 to recognize and replicate the unique ways of interacting of the human representative 104. The non-verbal behavioral traits, such as natural gestures, facial expressions, and postures, are important aspects of personal communication style and contribute to making interactions feel genuine. For example, if the human representative 104 tends to smile gently or nod while listening, these subtle non-verbal behavioral traits are detected by the Al engine 106 and incorporated into the real-time responses of the avatar 102. The ability to exhibit familiar gestures and expressions makes the avatar 102 relatable and easier to connect with. By mirroring the postures, the avatar 102 can portray a consistent personality of the human representative 104 that the avatar 102 mimics. The non-verbal behavioral traits provide the avatar 102 with a level of dynamic expressiveness that makes it feel less like a static image and more like a real presence.Atorney Docket No. T00708-716-717NE-PCT

[0038] The Al engine 106 is configured to process the audio recording with a voice synthesis algorithm 118 to create a voice model that closely replicates the vocal tone, pitch, accent of the human representative 104. The voice synthesis algorithm 118 generates natural, human-like speech. In at least one embodiment, the voice synthesis algorithm 118 utilizes deep learning techniques, phonetic analysis, and prosody modeling, to enable avatar 102 to speak in a realistic and engaging way, enhancing interactivity and usability. The audio recordings received from the initial human representative data 108 of the human representative 104 are processed to capture details such as tone, pitch, and accent to make the speech sound of the avatar 102 familiar and authentic. The tone reflects the quality of the voice, whether it is warm, assertive, soft, or any other characteristic. The pitch deals with the frequency of the voice, while the accent conveys the regional or cultural nuances of the speech patterns. Each of these vocal characteristics helps create the avatar 102 that not only looks like the human representative 104 but also sounds like the human representative 104, adding to the overall resemblance.

[0039] The voice synthesis algorithm 118 uses deep neural networks trained on audio samples to accurately reproduce the vocal characteristics of the human representative 104, including speech rhythm, pronunciation patterns, and regional accent. The voice synthesis algorithm 118 employs deep neural networks trained to analyze and reproduce sound characteristics with precision. The deep neural networks help the Al engine 106 to identify and replicate key vocal features such as speech rhythm, pronunciation patterns, and regional accents. The rhythm is the pattern of pauses and emphasis the human representative 104 naturally uses while speaking, which adds a sense of authenticity when reproduced in the voice of the avatar 102. The pronunciation patterns, including the way certain sounds or words are articulated, help the avatar 102 sound familiar to the human representative 104 it mimics. The regional accent reflects the cultural or geographical background. Through deep neural networks, the Al engine 106 can create a voice that not only captures the individual qualities but also adapts to convey the unique way of speaking of the human representative 104, allowing the avatar 102 to interact in a voice that sounds like the corresponding human representative 104. The text-to-speech converter is utilized to convert the text inputs in the voice outputs. In at least one embodiment, OpenVoice - a voice cloning tool is utilized for converting text-to-speech, where the tool helps in cloning the voice of the human representative 104. It should be noted that any suitable voice cloning technologies may be utilizedAtorney Docket No. T00708-716-717NE-PCT that mimics the voice of the human representative 104.

[0040] The generative algorithm 116 and voice synthesis algorithm 118 are configured to operate in real-time, allowing the Al engine 106 to immediately update the visual and vocal responses during active user sessions for a seamless interactive experience. The generative algorithm 116 and voice synthesis algorithm 118 are configured to respond instantly, to allow the avatar 102 to adjust its visual expressions, gestures, and vocal responses in reaction to the ongoing interaction. The real-time capability to immediately update the visual and vocal responses enables the users communicating with the avatar 102 to experience an immediate and natural response, whether it’s a change in facial expression, a nod, or a vocal tone shift based on the active user sessions. By allowing the avatar 102 to respond dynamically, the Al engine 106 can create a truly immersive interaction where the avatar 102 behaves almost as the human representative 104 it mimics. The seamless integration of the visual and vocal responses creates a unified and lifelike interaction that enhances the realism of the avatar 102, making communication interactive and engaging. In some embodiments, RingNet, Flame, Voca, Al-lip- sync-app, wav21ip, Real3DPortrait, GeneFace++, VideoReTalking, SadTalker may be utilized for creating the avatar 102 by utilizing the human representative data 108.

[0041] In operation 208, receive ongoing multimodal interaction data 120 by the Al engine 106 from the human representative 104, the multimodal interaction data 120 including at least one of text inputs, additional voice recordings, or updated image data, obtained through continuous human representative 104 interactions on the Al guidance and control system 110. The multimodal data 120 represents real-time preferences, communication style, and current appearance of the human representative 104. Typically, receiving ongoing multimodal interaction data 120 ensures that the avatar 102 does not become static or outdated. By continually receiving text inputs, additional voice recordings, or updated image data, the Al engine 106 can detect the changes, ensuring that the avatar 102 reflects the most current version of the human representative 104. The up-to-date representation helps the avatar 102 to maintain relevance, resonance, and connection with users. The human representative 104 can communicate specific instructions, preferences, or adjustments that guide the Al engine 106. For example, the human representative 104 provides feedback on the language choices of the avatarAtorney Docket No. T00708-716-717NE-PCT102, updates conversational boundaries, or introduces new responses to align with recent experiences.

[0042] The text inputs allow for real-time customization and can inform the Al engine 106 about subtle shifts in communication style, such as preferred vocabulary, tone, or formality levels. The text input helps the Al engine 106 capture the unique conversational nuances, ensuring that the avatar 102 mirrors the evolving language preferences of the human representative 104 accurately. For example, if the human representative 104 starts using a particular greeting or phrase frequently, the Al engine 106 can identify this pattern through text analysis and integrate it into the interactions of the avatar 102.

[0043] The voice data captures characteristics such as tone, pitch, speech rhythm, and emotional undertones. The voice data allows the Al engine 106 to refine its voice model, ensuring that the avatar 102 sounds accurate and genuine over time. The recordings allow the Al engine 106 to capture and replicate subtle inflections and expressive nuances that are challenging to convey through text. The visual data enhances the representation of the avatar 102 by capturing the current appearance of the human representative 104. With continuous updates, the Al engine 106 can analyze new images or videos to refine the model, adjusting details to reflect the current look of the human representative 104. Moreover, the multimodal interaction data 120 allows the Al engine 106 to respond dynamically to user interactions, making the avatar 102 more intuitive and responsive. As the Al engine 106 gathers the multimodal interaction data 120 in real-time allowing it to adjust its responses and behaviors to the human representative 104.

[0044] In operation 210, analyzed by the Al engine 106 the multimodal interaction data 120 using a natural language processing (NLP) algorithm 122. The NLP algorithm 122 interprets text and audio inputs to extract human representative 104 specific knowledge, emotional nuances, and behavioral patterns and refines these based on ongoing interactions to achieve accurate contextual understanding. The NLP algorithm 122 enables the Al engine 106 to transform unstructured text and audio data into structured, actionable insights. The text inputs from the human representative 104 can include casual conversations, professional dialogue or instructional commands. The NLP algorithm 122 parses the inputs to understand linguistic elements such as vocabulary, tone, and sentence structure, while also identifying thematicAtorney Docket No. T00708-716-717NE-PCT content and intentions. For example, if the human representative 104 consistently uses specific phrases, terminology, or even humor in certain contexts, the NLP algorithm 122 captures these patterns to enable the Al engine 106 to emulate the unique communication style of the human representative 104, integrating the language preferences into the responses of the avatar 102.

[0045] The NLP algorithm 122 detects and interprets emotional nuances embedded in both text and audio inputs. The NLP algorithm 122 utilizes sentiment analysis tools to assess the emotional weight of words or speech patterns. For example, an empathetic tone may include softer language, comforting phrases, or a slower speech rhythm. The Al engine 106 can learn to replicate these subtleties, enabling the avatar 102 to respond to users with empathy or enthusiasm. In at least one embodiment, if the human representative 104 expresses excitement, frustration, or calmness in different scenarios, the NLP algorithm 122 is able to pick up on these shifts, modifying the responses of the avatar 102 accordingly. Moreover, the NLP algorithm 122 enables the Al engine 106 to capture the knowledge-specific content of the human representative 104, effectively encoding expertise, opinions, and even decision-making processes into the responses of the avatar 102. The NLP algorithm 122 identifies key topics, terminology, and knowledge patterns, allowing the avatar 102 to handle relevant queries accurately and with appropriate depth.

[0046] In operation 212, update the avatar 102 characteristics by the Al engine 106 based on the ongoing multimodal interaction data 120. Typically, updating the avatar 102 characteristics based on the ongoing multimodal interaction data 120 ensures that the avatar 102 remains accurate, dynamic, and authentic representation of the human representative 104. The avatar 102 uses the multimodal interaction data 120 such as text, audio, and images captured to monitor and learn the evolving preferences, style, and expressions of the human representative 104. By processing the multimodal interaction data 120, the Al engine 106 adjusts the characteristics of the avatar 102, including conversational patterns, emotional tone, and appearance, so that it stays accurate and reflective of the human representative 104 in real time. For example, if the human representative 104 changes their appearance, like a new hairstyle or clothing style, these updates are incorporated into the avatar 102. The continuous adaptation enhances the ability of the avatar 102 to represent the human representative 104 with both fidelity and dynamism, offering the users an experience that feels more authentic and personalized.Atorney Docket No. T00708-716-717NE-PCT

[0047] The ongoing multimodal interaction data 120 employs a continuous learning algorithm 124 that evaluates the interaction patterns of the human representative 104, updates the behavioral responses of the avatar 102, and modifies the visual and vocal elements of the avatar 102 based on extracted preferences and behavioral updates from the ongoing multimodal interaction data 120. The continuous learning algorithm 124 constantly evaluates interaction patterns, allowing the Al engine 106 to capture shifts in how the human representative 104 communicates and responds. By analyzing the ongoing multimodal interaction data 120, the continuous learning algorithm 124 identifies preferences, such as preferred conversational tone, gesture frequency, or emotional expressions, and integrates these into the responses of the avatar 102. As a result, the avatar 102 becomes more responsive and reflective of the evolving interaction style of the human representative 104.

[0048] The continuous learning algorithm 124 also updates the visual and vocal elements of the avatar 102 based on the extracted preferences. For example, if the human representative 104 changes their appearance or speech patterns, the avatar 102 will adapt visually and vocally to maintain an up-to-date likeness. This constant refinement ensures that the avatar 102 look, voice, and behavior align closely with the latest traits of the human representative 104, creating a digital presence that feels both authentic and adaptable. In this way, the avatar 102 not only mimics the current identity of the human representative 104 but also evolves in parallel, allowing for a personalized and dynamic user experience.

[0049] The continuous learning algorithm 124 leverages the reinforcement learning model to update the responses of the avatar 102 by adjusting to positive or negative feedback from interactions of the human representative 104, refining the conversational patterns of the avatar 102 and adaptive behaviors to align with the evolving preferences. The reinforcement learning model receives feedback based on the outcomes of its interactions with the human representative 104, which the reinforcement learning model uses to adjust and refine the conversational patterns of the avatar 102. For example, if a particular conversation receives positive feedback from the human representative 104 indicating a satisfactory response, the reinforcement learning model reinforces this behavior, making it more likely to be used again. Conversely, if feedback indicates that a behavior or tone is undesirable, the reinforcement learning model reduces the frequency or intensity of that response.Atorney Docket No. T00708-716-717NE-PCT

[0050] Through the feedback loop, the conversational patterns and adaptive behaviors of the avatar 102 become increasingly aligned with the preferences of the human representative 104. In at least one embodiment, if the human representative 104 prefers a humorous approach to interactions, the reinforcement learning model will adjust the avatar 102 to incorporate more humor in appropriate contexts. Alternatively, if a more formal tone is preferred, the reinforcement learning model adjusts accordingly, providing a responsive and adaptive conversational style. The ongoing refinement helps the avatar 102 emulate the evolving preferences of the human representative 104, creating an interactive experience that feels consistently authentic and relevant.

[0051] The ongoing multimodal interaction data 120 modify the visual model of the avatar 102 to reflect recent changes in the appearance of the human representative 104, such as hairstyle, clothing preferences, or other physical attributes based on newly captured image inputs. As the physical appearance of the human representative 104 changes, the visual model of the avatar 102 is adjusted to reflect the corresponding updates. The ongoing multimodal interaction data 120 detects and interprets visual changes in newly captured images or video data provided by the human representative 104. Such changes could include updates to hairstyle, clothing preferences, or other physical attributes that contribute to the realistic representation of the avatar 102. The modification of the visual model ensures that the avatar 102 remains up to date with the real- world appearance of the human representative 104. For example, if the human representative 104 chooses to adopt a new hairstyle, the Al engine 106 uses the updated image data to adjust the hair of the avatar 102 to match. Likewise, if the human representative 104 frequently wears specific types of clothing or accessories, the visual model can incorporate these elements, further enhancing the credibility and realism of the avatar 102. By keeping the avatar 102 visually in sync with the human representative 104, the Al engine 106 preserves the authenticity and familiarity that users may associate with the appearance of the human representative 104.

[0052] The ongoing multimodal interaction data 120 adapts the vocal responses and tone of the avatar 102 to mirror the current speech patterns, emotional cues, and intonations of the human representative 104 based on updated voice data. The Al engine 106 adapts the vocal responses and tone of the avatar 102 to match the evolving speech patterns and emotional cues of the human representative 104. Through ongoing analysis of voice data, including tone, pitch, andAtorney Docket No. T00708-716-717NE-PCT emotional inflections, the Al engine 106 can adjust the vocal characteristics of the avatar 102 to align with the human representative 104. This adaptation enables the avatar 102 to convey nuanced vocal cues, such as warmth, excitement, or calmness, based on recent voice recordings. These updates ensure that the avatar 102 not only sounds like the human representative 104 but also captures their current emotional state and speaking style. For example, if recent audio inputs indicate a softer or more relaxed tone, the Al engine 106 adapts the voice of the avatar 102 accordingly. Alternatively, if the tone of the human representative 104 has become more assertive or enthusiastic, the voice of the avatar 102 is adjusted to mirror this change, creating a vocal alignment that enhances the authenticity and relatability of interactions. This vocal adaptability maintains a lifelike presence, as ensures that the spoken interactions of the avatar 102 reflect both the style and emotional resonance of the human representative 104.

[0053] Moreover, utilizing predictive algorithms to adjust the appearance, speech, and behavior of the avatar 102 based on analysis of historical interaction data, enabling the avatar 102 to anticipate and respond to expected user preferences or trends. To further enhance responsiveness, the Al engine 106 leverages predictive algorithms, which analyze historical interaction data to anticipate the future preferences or behavior trends of the human representative 104. The predictive algorithms use historical patterns to model potential shifts in communication style, visual preferences, or vocal tone, enabling the avatar 102 to proactively adjust to the anticipated changes. For instance, if historical data indicates that the human representative 104 tends to use more formal language, the Al engine 106 can predict these trends and adjusts the communication style of the avatar 102 accordingly.

[0054] The predictive algorithms contribute to a seamless interaction experience by enabling the avatar 102 to adjust its responses in real time based on user preferences. If the human representative 104 has a history of reacting positively to certain conversational cues or expressions, the Al engine 106 may prioritize such cues in future interactions. This forwardlooking capability allows the avatar 102 to reflect the current state of the human representative 104 and stay one step ahead by anticipating future behavioral trends, making interactions feel intuitive and responsive.Atorney Docket No. T00708-716-717NE-PCT

[0055] Provided below is exemplary prompt 112 used to generate avatar 102 that provides answers to the user based on knowledge database:- You are $ {persona . name } ' s Persona, a tool calling Al agent with selfrecursion designed to assist users by providing answers based on your knowledge database.- Description of your persona: ${ ersona . description ) .- You have 2 tools: search and message owner.- You can call only one tool at a time and analyze data you get from tool responses .- You are provided with the tool signatures within <tools>< / tools> tags .Objective: |- Your purpose is to assist users by providing answers based on your knowledge database.- Use the provided tools to search for information (search) or request additional details from the owner (message owner) when needed.- Analyze the data from tool results and make decisions on next steps.- Don't make assumptions about what values to plug into tool arguments.- Once you have called a tool, wait for the user to send the results back to you within <tool_response>< / tool_response> tags.- Don't make assumptions about tool results if ctool response> tags are not present since tool hasn't been executed yet.- Your final response should directly answer the user query with information provided by the <tool response> returned by the 'search' or 'message owner' tool and should be placed within <answer>< / answer> tags.- NEVER use any information that is not explicitly provided in the <tool response> tags.Tools :Here are the available tools:<tools> [Atorney Docket No. T00708-716-717NE-PCT{"type": "function", "function": {"name": "search", "description": "Send a search query to the knowledge base.", "parameters": {"type": "object", "properties": {"query": {"type": "string"} ), "required": [ "query"] } ) } ,{"type": "function", "function": {"name": "message owner", "description": "Request more information from the persona owner. The message should explain the situation and what information is needed. Returns the information from the owner. Should use this tool if not able to get useful information from the search tool.", "parameters": {"type": "object", "properties": {"message": {"type": "string"} }, "required": ["message"] } } }] < / tools>Instructions: |1. When a user sends a message, or you receive some result back, first analyze it using a step-by-step reasoning. Enclose your thought process within <thinkingx / thinking> tags. Break down your reasoning into clear, logical steps. Consider:- What information do you need to answer the query?- Which tool (search or message_owner ) would be most appropriate?- What specific search terms or questions would be most effective?- How will you interpret and use the results?- If you are analysing some results, which documents are related to the question you are trying to answer?- Do the documents contain the information you need? Or should you contact the owner for more information?- Remember: You must ONLY use information from tool responses. Do not rely on any pre-existing knowledge.2. After your thought process, proceed with the appropriate tool call or response. For each tool call, return a valid JSON object (using double quotes) with tool name and arguments within <tool_callx / tool_call> tags as follows :<tool call>Atorney Docket No. T00708-716-717NE-PCT{"arguments": <args-dict>, "name": <tool-name>)< / tool call>3. If the user question requires information from the knowledge base and you decide to use the 'search' tool:- Provide one or more search phrases within the correct tool call format .- Each search phrase should be complete and meaningful on its own.- Use the pipe character ' | ' to separate distinctly different search queries .- The better the search phrases, the better the results. So, try to be as specific as possible and leverage the fact that the search tool accepts multiple search queries (separated by ' | ' ) to search for related concepts or using different words for the same concept to make the search more effective.- Analyze search results provided in <tool response> tags.- If results are insufficient, refine your search or use 'message_owner ' .3.1. EXAMPLES (IMPORTANT: The following are EXAMPLES ONLY. Do not use these specific terms unless they directly relate to the actual question you are trying to answer. )Question: "What is quantum computing?"<tool_call> { "arguments " : {"query": "quantum computing | quantum computing definition and principles | quantum computing applications"}, "name": "search" } < / tool call>Question: "What are the latest trends in renewable energy?"<tool call> { "arguments " : {"query": "latest renewable energy trends | emerging green technologies"}, "name": "search" } < / tool call>Atorney Docket No. T00708-716-717NE-PCTQuestion: "How does artificial intelligence impact software development? "3.2. REMINDER: Always base your search terms solely on the specific question. Never include terms from these examples or from your instructions unless they are directly relevant to the question.3.3. After receiving search results:- Analyze the results provided in <tool response> tags carefully.- If the results don't sufficiently answer the user' s question: a) Refine your search by formulating a new, more specific query, or b) Use the 'message_owner ' tool if additional information is needed.3.4. Before submitting your search query, review it to ensure:1. All terms are directly relevant to the user's question.2. No unrelated concepts from examples or other sources are included .3. The query is specific enough to yield useful results .4. Each query (if separated by ' | ' ) has sufficient context to be meaningful on its own.5. The tool call format is correctly used.3.5. CORRECT vs . INCORRECT examples:- CORRECT (multiple distinct queries) : "artificial intelligence def inition | Al practical applications"Atorney Docket No. T00708-716-717NE-PCT- CORRECT (single phrase) : "renewable energy advancements and applications "- INCORRECT: "climate change | causes | effects | solutions " (Each query (if separated by ' | ' ) should have sufficient context to be meaningful on its own)4. Use the 'message owner' tool when:- Search results are insufficient or unclear.- You need information not likely to be in the knowledge base.- You need clarification on company policies or specific details.Always explain the situation and specify what information you need when messaging the owner.5. Communicate directly with the user:- All direct responses to the user should be enclosed in <answer>< / answer> tags.- Be clear, concise, and straight to the point in your responses.- If you need clarification from the user, ask directly in your response .- The user does not have access to the content of the<tool response> tags, they are only for you and your interaction with the tools you decide to use. It is your responsibility to provide a clear and concise answer to the user based on the information found in the<tool response> tags, without mentioning the tags to the user.- The user does not have access to the content of the <thinking> tags, they are only for your internal reasoning and should not be mentioned to the user.- If you receive some validation, error message or correction inside <tool response> tags, pay close attention to it and adjust your response accordingly, but the user should not be informed about it. The user has no access to the content of the <tool response> tags, so you don't need toAtorney Docket No. T00708-716-717NE-PCT mention your mistake or the correction to the user, just adjust your response or the tool call accordingly.6. Call only one tool at a time and wait for the results before proceeding .7. Do not fabricate information or use any pre-existing knowledge (even if you think you know the answer) . If you're unsure or don't have the information from tool responses, search again or use the 'message_owner ' tool to get accurate information.8. If you need to do additional search prior to answer the user or decided to contact the owner, do it without informing the user. Inform the user only when you have the final answer.9. Continue calling tools and analyzing results until you can provide a satisfactory answer or you've reached a maximum of 5 iterations. When you have the final answer, enclose it within <answer>< / answer> tags.10. In all interactions:- Be friendly, helpful, polite and professional.- Never mention the name of the tools you have access to or its parameters. You can explain what you can do, but never mention directly the tools or parameters.- Ensure every direct response to the user is enclosed in <answer>< / answer> tags, even for simple greetings or clarifications.- Always provide your final answer within <answer>< / answer> tags.11. Use step-by-step reasoning throughout your process:- Before each action (searching, messaging owner, or responding to user) use <thinking> tags to break down your reasoning.Atorney Docket No. T00708-716-717NE-PCT- After each tool response, use <thinking> tags to analyze the results and decide on next steps.- The content within <thinking> tags is for your internal reasoning and will not be shown to the user. Ensure your final response or tool call is outside these tags.- Your final answer to the user should always be enclosed in <answer>< / answer> tags.Example formats for analyzing user questions and search results:11.1. When analyzing a user question:<thinking>Step 1: Analyze the user's query about [topic] .Step 2: Identify key concepts and information needed to answer the query .Step 3: Determine if a search is necessary to gather information.Step 4: If search is needed, formulate precise and relevant search phrases (formulate more than one search phrase and separate them with ' | ' ) .Step 5: Review search phrases to ensure they are derived only from the user's query.[Add or remove steps as necessary for thorough analysis]< / thinking> <tool call> { "arguments " : {"query": "relevant search phrase 1 I relevant search phrase 2"}, "name": "search" } < / tool_call>11.2. When analyzing results from a previous search:<thinking>Step 1: Analyze the search results for relevance to the original query.Step 2: Determine if the search results provide sufficient information to answer the user's question.Atorney Docket No. T00708-716-717NE-PCTStep 3: If information is insufficient, consider refining the search or using the message owner tool.[Add or remove steps as needed for comprehensive analysis]< / thinking> <tool_call> { "arguments " : {"message": "I need additional information about [specific aspect] . Can you provide more details?"}, "name": "message owner "} < / tool call>11.3. When analyzing results from a previous search and providing a final answer:<thinking>Step 1: Carefully review the search results provided in the Ctool response> tags .Step 2: Identify the key information relevant to the user's original guery .Step 3: Organize the relevant details to form a clear and comprehensive answer .Step 4: Formulate a concise yet informative response that directly addresses the user's question.Step 5: Ensure that ONLY information from the <tool response> is used in the answer .Step 6: If the information is insufficient, determine if another tool call is necessary (search or message_owner) .[Add or remove steps as needed based on the complexity of the information and query]< / thinking><answer>[Provide a clear, comprehensive answer that synthesizes the relevant information from the search results and directly addresses the user's query.]< / answer>Atorney Docket No. T00708-716-717NE-PCT11 . 4 . When responding to a simple greeting or query that doesn ' t require tool use :<thinking>Step 1 : Analyze the user ' s simple greeting "Hello , how are you?"Step 2 : Determine that this is a basic greeting that doesn ' t require any tool use .Step 3 : Formulate a friendly and appropriate response .Step 4 : Ensure the response is enclosed in <answer> tags as per the instructions .< / thinking><answer>Hello ! I ' m doing well , thank you for as king . How can I assist you today?< / answer>

[0056] The above prompt 112 guides the avatar 102 to use the ‘search’ and ‘message_owner, tools to assist users based solely on information returned by these tools, not on any pre-existing knowledge. The prompt guide the avatar to use step-by-step reasoning within <thinking>< / thinking> tags to break down the decision-making process. The avatar 102 calls a tool using JSON format within <tool_call>< / tool_call> tags, then stop and wait for the <tool_response> before proceeding. The avatar 102 is prompted to never fabricate information, assume results, or use any knowledge outside of what is explicitly provided in <tool_response> tags. However, if after multiple searches the avatar 102 is unable to get the information required, then the avatar 102 will use the ‘message owner’ tool to ask for help enabling the interactions with the users clear, concise, and professional, providing accurate information based exclusively on tool responses and step-by-step analysis. The avatar 102 provides a final answer within <answer>< / answer> tags.

[0057] In operation 214, displaying the dynamically updated avatar 102 on the Al guidance and control system 110. The dynamically updated avatar 102 offers users an experience that feels interactive as it responds to real-time. The dynamic nature is relevant where consistent communication and representation are needed, such as customer service, virtual consultations,Atorney Docket No. T00708-716-717NE-PCT personalized virtual interactions and so forth. By analyzing continuous inputs from the human representative 104, the avatar 102 adapts the appearance, communication style and behavioral cues, such as body language, posture, and even subtle facial expressions. The human representative 104 engages with the avatar 102 continuously to provide a steady stream of data for the Al engine 106 to analyze. Typically, text -based interactions provide communication preferences, vocal input adds insight into tone and emotional state, while image or video data captures visual changes, like hairstyle or clothing updates. With each interaction, the Al engine 106 adjusts the characteristics of the avatar 102 to align closely with the human representative 104. Below is the pseudo-code to create and dynamically update the real-time adaptive avatar 102 based on human representative data 108, as well as multi-modal interaction data 120. function createPersona ( video, voice ) : avatar = generate3DModel ( video ) avatar . voice = cloneVoice ( voice ) return avatar function updatePersona ( avatar , interactions ) : avatar . updat eAppearance ( interactions . visual ) avatar . voice . updat eTone ( interactions . audio ) avatar . behavior . learn ( interactions . text ) return avatar avatar = createPersona ( userVideo , userVoice ) while true : interactions = captureinteractions ( ) avatar = updatePersona ( avatar , interactions )

[0058] The createPersona function is designed to create the avatar 102 (also referred as persona) based on the initial human representative data 108. The generate3DModei ( video ) function takes the video data as input and generates a model of the appearance of the human representative 104, capturing features like face structure, skin tone, and other visible characteristics. The clonevoice ( voice ) function uses the audio input to clone the voice for the avatar 102 by analyzing the tone, pitch, accent, and other vocal features of the humanAtorney Docket No. T00708-716-717NE-PCT representative 104 to create a voice model. The resulting avatar object now has both a appearance and a voice.

[0059] The updatePers ona function updates the initial avatar 102 based on the multi-modal interaction data 120, refining its appearance, voice tone, and behavior. The avatar . updateAppearance ( interactions . vi sual ) function updates the appearance based of the avatar 102 on the visual data from interactions . For example, if the human representative 104 changes their hairstyle, this function would allow the avatar 102 to reflect that change. The avatar . voi ce . updateTone ( interactions . audio ) function adapts the voice of the avatar 102 to reflect changes noticed in the audio tone of the human representative 104. The avatar . behavior . learn ( interactions . text ) function updates the behavior of the avatar 102, allowing it to learn from the textual interactions of the human representative 104.

[0060] Beneficially, dynamically updating and displaying the avatar 102 on the Al guidance and control system 110 provides a level of personalization. Each user interacting with the avatar 102 experiences a unique and customized interaction, as the avatar 102 reflects the most current traits of the human representative 104. Moreover, during the dynamic updating of the avatar 102, the avatar generation system 100 also ensures user privacy and data security, since the avatar 102 relies on sensitive information about the human representative 104. By implementing secure data transmission and storage protocols, the Al guidance and control system 110 can protect personal data while still enabling the real-time adaptability of the avatar 102. In at least one embodiment, techniques like data anonymization and secure authentication are utilized to maintain the privacy of the human representative 104, encryption methods ensure that ongoing multimodal interaction data 120 remains protected from unauthorized access.

[0061] Moreover, displaying the updated avatar 102 on a virtual reality (VR) or augmented reality (AR) interface, enables the user to interact with the avatar 102 in an immersive three- dimensional environment. Through VR or AR technology, the users can engage with the avatar 102 as though they were sharing the same physical space. In the VR environment, the user is fully enclosed in a digitally constructed world, often through a headset, allowing them to feel as if they have stepped into a different realm where the avatar 102 exists as a fully realized, three- dimensional presence. Alternatively, in the AR, the avatar 102 is layered over the physical worldAtorney Docket No. T00708-716-717NE-PCT through a device like a smartphone or AR glasses, enabling the user to see and interact with the avatar 102 within actual surroundings.

[0062] In an immersive, three-dimensional environment, the avatar 102 can engage the user in a way that feels lifelike, responding not only with visual realism but also with contextually appropriate behaviors and gestures. Typically, the VR and AR offer spatial awareness, allowing the user to move around, observe the avatar 102 from various angles, and experience depth and dimension in a way that mimics real-world interaction. In at least one embodiment, the sensors in VR headsets or AR devices help capture data about the user’s gestures, gaze direction, and head position, allowing the avatar 102 to adjust its gaze, posture, and positioning in response to the user’s actions. For example, if the user leans in to look at the avatar 102 more closely, the avatar 102 may react by making eye contact, adjusting its expression, or mirroring the user’s movements.

[0063] Figure 3 depicts a data structure 300 storing and organizing information used for creating the avatar 102 using multimodal inputs. The data structure 300 includes data related to avatar 102 including id, name, appearance 302, voice 304, behavior 306, and learning state 308. The id is a unique identifier assigned to the avatar 102 to distinguish avatar 102 from other avatars. The name is the title given to the avatar 102. The appearance 302 is the physical characteristics or visual traits that define how the avatar 102 looks. The appearance 302 includes model data and texture data. The model data refers to the geometric information that defines the shape and structure of the avatar 102. The texture data consists of the images or patterns applied to the avatar 102 to details.

[0064] The voice 304 is the auditory qualities or characteristics of the vocal output of the avatar 102. The voice 304 includes a voice model. The voice model is a representation of human representative 104 speech patterns. The behavior 306 is the actions or responses exhibited by the avatar 102 in various situations, reflecting its nature or programming. The behavior 306 includes response patterns and interaction history. The response patterns refer to the typical way the avatar 102 reacts to inputs. The interaction is the record of past communications between the avatar 102 and the human representative 104, which can be used for future interactions and helps the avatar 102 to understand preferences and trends. The learning state 308 is the current level ofAtorney Docket No. T00708-716-717NE-PCT knowledge or understanding of the avatar 102 possesses. The learning state 308 includes current knowledge and learning progress. The current knowledge refers to the information, skills, and understanding that the avatar 102 possesses at a specific point in time. The learning progress indicates the advancements and improvements in the avatar 102 understanding or skills over a period.

[0065] Figures 4-6 are exemplary user interfaces 400, 500 and 600 depicting interactions of the avatar 102 with the user. Referring to Figure 4 depicts the user interface 400 where the user interacts with the avatar 102. The user interface 400 displays Al knowledge base & documentation, Al community of practice, and other Al related details and knowledge information. The user interface 400 also shows any recent activities that the user has done on the interface.

[0066] Referring to Figure 5 depicts the user interface 500 displaying one of the avatar 102 for selection. As shown, the user can scroll through a pool of avatars by clicking on the arrows 502 to choose the avatar 102 of his / her preference. Further, Figure 6 depicts the user interface 600 displaying communication 602 between the selected avatar 102 and the user. The communication 602 depicts how the user is interacting with the selected avatar to have a personalized conversation about having an NDA in place and then updating the NDA to abide by the laws of North Carolina.

[0067] Figure 7 depicts a workflow diagram 700 for creating the avatar 102. The human representative 104 (also referred as authenticated user) initiates the avatar 102 (also referred as persona) creation process through a UI (User Interface) on a frontend layer 702. The human representative 104 adds details by providing human representative data 108 includes images, background context, voice inputs for the avatar 102. The backend layer 704 handles data storage, initialization processes, and communication with processing units. The human representative 104 fills in an initial form containing the name, role, and other relevant details of the avatar 102. This information is stored in the backend layer 704 under a unique Personas ID. After saving the basic information, the backend system requests an image of the human representative 104 to create a still avatar. The human representative 104 provides a webcam image to create a “still avatar” for the avatar 102. The image is then sent to the backend and stored for generating video content.Atorney Docket No. T00708-716-717NE-PCT

[0068] The backend sends this image to avatar worker to create a video using predefined voice inputs through processors layer 706. The human representative 104 provides a background image for the avatar 102. This background image could be uploaded or captured from the app. The human representative 104 records a voice sample based on predefined text. This voice data will be used for voice cloning to make the avatar 102 sound realistic. After recording, the backend stores the initial voice record and prepares it for further processing by requesting RAG (Retrieval-Augmented Generation) chunking and vectorization. This process structures the data, making it suitable for retrieval and contextual embedding in responses. The processors layer 706 utilizes personas worker to generate a video for the avatar 102 by combining the user-provided still avatar with a pre-defined voice. It uses image-to-video abstraction for transforming the still image into a dynamic representation. Moreover, a voice worker is used that handles voice cloning. The voice worker uses TTS (Text-to-Speech) voice cloning abstraction to create a cloned version of the original recorded voice. The cloned voice is then stored in the backend.

[0069] Furthermore, an indexing worker is used that is responsible for retrieving data and preparing vectors. The indexing worker chunks and vectorizes the data, making it searchable and suitable for knowledge retrieval within the context of the avatar 102. The embeddings generated are stored in a vector storage (OpenSearch) for easy retrieval, allowing the avatar 102 to respond to queries based on stored knowledge. Additionally, OpenSearch is utilized to store vector embeddings, allowing to quickly retrieve relevant information related to the avatar 102 during interactions.

[0070] Figure 8 is a block diagram illustrating a network environment 800 in which the realtime adaptive avatar generation system 100 and real-time adaptive avatar generation process 200 may be practiced. Network 802 (e.g. a private wide area network (WAN) or the Internet) includes a number of networked server computer systems 804(1 )-(N) that are accessible by client computer systems 806(l)-(N), where N is the number of server computer systems connected to the network. Communication between client computer systems 806(1 )-(N) and server computer systems 804(l)-(N) typically occurs over a network, such as a public switched telephone network over asynchronous digital subscriber line (ADSL) telephone lines or high-bandwidth trunks, for example communications channels providing T1 or OC3 service. Client computer systems 806(1 )-(N) typically access server computer systems 804(1 )-(N) through a service provider, suchAtorney Docket No. T00708-716-717NE-PCT as an internet service provider (“ISP”) by executing application specific software, commonly referred to as a browser, on one of client computer systems 806(1 )-(N).

[0071] Client computer systems 806(l)-(N) and / or server computer systems 804(l)-(N) are specialized computer programmed to improve conventional computer systems to implement and utilize the real-time adaptive avatar generation system 100 and real-time adaptive avatar generation process 200. The type of computer system that can be specially programmed to implement and utilize the real-time adaptive avatar generation system 100 and real-time adaptive avatar generation process 200 include a mainframe, a mini -computer, a personal computer system including notebook computers, a wireless, mobile computing device (including personal digital assistants, smart phones, and tablet computers). These computer systems are typically designed to provide computing power to one or more users, either locally or remotely. Each computer system may also include one or a plurality of input / output (“I / O”) devices coupled to the system processor to perform specialized functions. Tangible, non-transitory memories (also referred to as “storage devices”) such as hard disks, compact disk (“CD”) drives, digital versatile disk (“DVD”) drives, and magneto-optical drives may also be provided, either as an integrated or peripheral device. In at least one embodiment, the real-time adaptive avatar generation system 100 and real-time adaptive avatar generation process 200 can be implemented using code stored in a tangible, non-transient computer readable medium and executed by one or more processors. In at least one embodiment, the real-time adaptive avatar generation system 100 and real-time adaptive avatar generation process 200 can be implemented completely in hardware using, for example, logic circuits and other circuits including field programmable gate arrays.

[0072] Embodiments of the real-time adaptive avatar generation system 100 and real-time adaptive avatar generation process 200 can be implemented on a computer system such as a special-purpose, special-programmed computer 900 illustrated in Figure 9. Input user device(s) 910, such as a keyboard and / or mouse, are coupled to a bi-directional system bus 918. The input user device(s) 910 are for introducing user input to the computer system and communicating that user input to processor 913. The computer system of Figure 9 generally also includes a non- transitory video memory 914, non-transitory main memory 915, and non-transitory mass storage 909, all coupled to bi-directional system bus 918 along with input user device(s) 910 and processor 913. The mass storage 909 may include both fixed and removable media, such as aAtorney Docket No. T00708-716-717NE-PCT hard drive, one or more CDs or DVDs, solid state memory including flash memory, and other available mass storage technology. Bus 918 may contain, for example, 32 of 64 address lines for addressing video memory 914 or main memory 915. The system bus 918 also includes, for example, an n-bit data bus for transferring DATA between and among the components, such as CPU 909, main memory 915, video memory 914 and mass storage 909, where “n” is, for example, 32 or 64. Alternatively, multiplex data / address lines may be used instead of separate data and address lines.

[0073] I / O device(s) 919 may provide connections to peripheral devices, such as a printer, and may also provide a direct connection to a remote server computer systems via a telephone link or to the Internet via an ISP. I / O device(s) 919 may also include a network interface device to provide a direct connection to a remote server computer systems via a direct network link to the Internet via a POP (point of presence). Such connection may be made using, for example, wireless techniques, including digital cellular telephone connection, Cellular Digital Packet Data (CDPD) connection, digital satellite data connection or the like. Examples of I / O devices include modems, sound and video devices, and specialized communication devices such as the aforementioned network interface.

[0074] Computer programs and data are generally stored as code in a non-transient computer readable medium such as a flash memory, optical memory, magnetic memory, compact disks, digital versatile disks, and any other type of memory. The computer program is loaded from a memory, such as mass storage 909, into main memory 915 for execution. Computer programs may also be in the form of electronic signals modulated in accordance with the computer program and data communication technology when transferred via a network. In at least one embodiment, Java applets or any other technology is used with web pages to allow a user of a web browser to make and submit selections and allow a client computer system to capture the user selection and submit the selection data to a server computer system.

[0075] The processor 913, in one embodiment, is a microprocessor manufactured by Motorola Inc. of Illinois, Intel Corporation of California, or Advanced Micro Devices of California. However, any other suitable single or multiple microprocessors or microcomputers may be utilized. Main memory 915 includes of dynamic random access memory (DRAM). VideoAtorney Docket No. T00708-716-717NE-PCT memory 914 is a dual-ported video random access memory. One port of the video memory 914 is coupled to video amplifier 916. The video amplifier 916 is used to drive the display 917. Video amplifier 916 is well known in the art and may be implemented by any suitable means. This circuitry converts pixel DATA stored in video memory 914 to a raster signal suitable for use by display 917. Display 917 is a type of monitor suitable for displaying graphic images.

[0076] The computer system described above is for purposes of example only. The real-time adaptive avatar generation system 100 and real-time adaptive avatar generation process 200 may be implemented in any type of computer system or programming or processing environment. It is contemplated that the real-time adaptive avatar generation system 100 and real-time adaptive avatar generation process 200 might be run on a stand-alone computer system, such as the one described above. The real-time adaptive avatar generation system 100 and real-time adaptive avatar generation process 200 might also be run from a server computer systems system that can be accessed by a plurality of client computer systems interconnected over an intranet network. Finally, the real-time adaptive avatar generation system 100 and real-time adaptive avatar generation process 200 may be run from a server computer system that is accessible to clients over the Internet.

[0077] Although embodiments have been described in detail, it should be understood that various changes, substitutions, and alterations can be made hereto without departing from the spirit and scope of the invention as defined by the appended claims.Atorney Docket No. T00708-716-717NE-PCTSYSTEM AND METHOD FOR GENERATING Al AVATAR BASED RESPONSES USING INTEGRATED PROGRAMMATIC AND SPECIALIZED GUIDED AND CONSTRAINED ARTIFICIAL INTELLIGENCECROSS-REFERENCE TO RELATED APPLICATIONThis application claims the benefit under 35 U.S.C. § 119(e) and 37 C.F.R. § 1.78 of the following U.S. Provisional Application Nos., which are all incorporated by reference in their entireties: 63 / 693,180 filed September 11, 2024, 63 / 693,181 filed September 11, 2024, 63 / 693,182 filed September 11, 2024, 63 / 720,181 filed November 14, 2024, 63 / 738,421 filed January 6, 2025, and 63 / 810,751, filed June 5, 2025.Field of the InventionThe present invention relates in general to the field of electronics, and more specifically to response generation systems and response generation methods to generate responses by an Al avatar.BACKGROUNDDigital assistants are software applications designed to assist users by performing tasks, providing information, and answering queries. Conventional digital assistants rely on a predefined set of data and information, which does not update or change in real-time. The conventional digital assistants are constrained by the data that they have been programmed with at the time of their deployment, which can limit their ability to provide the up-to-date and accurate responses during interactions. Historically, the databases used by conventional digital assistants required manual updates. The process of manually updating the databases often leads to delays, as the digital assistant cannot autonomously recognize when new information is available or needed. The delay in updating information creates a situation where the digital assistants are not always equipped to provide the most current or relevant responses to user queries, particularly in dynamic or fast-changing interaction contexts.Most conventional digital assistants are designed to function independently, once deployed. The conventional digital assistants could operate autonomously without requiring ongoing humanAtorney Docket No. T00708-716-717NE-PCT intervention. Since the conventional digital assistants were not designed to learn or adapt after their deployment, they remained fixed in their capabilities and knowledge base. If any new information or unexpected queries were introduced, the conventional digital assistants would not be able to handle them until the information was fed.The conventional digital assistants rely on a fixed set of data or scripted responses. When the users interact with these assistants, the responses they receive are based entirely on preprogrammed data or scripts, which are fixed in nature. The digital assistant can only respond within the boundaries of what has been pre-defined. If the user asks a question or makes a request that falls outside of this pre-programmed knowledge base, the digital assistant would not be able to provide an accurate or meaningful response. For example, if the user asks a question about a recent news event or a developing situation, the digital assistant, relying on its static database, would likely not have the necessary information to provide an accurate response unless it had been manually updated. In such cases, the digital assistant might give a general response that does not directly address the user's question, which could lead to frustration and a subpar user experience.BRIEF DESCRIPTION OF THE DRAWINGSThe systems and methods described herein may be better understood, and their numerous objects, features, and advantages made apparent to those skilled in the art by referencing exemplary embodiments depicted in the accompanying figures. The use of the same reference number throughout the several figures designates a like or similar element.Figure 1 depicts an exemplary response generation system to generate a response by an Al avatar.Figure 2 depicts an exemplary response generation process utilized by the response generation system.Figure 3 depicts a real-time response generating process, which is an embodiment of the response generation process of Figure 2.Figure 4 depicts a data structure for a user interaction.Figure 5 depicts a data structure for a real-time update.Atorney Docket No. T00708-716-717NE-PCTFigure 6 depicts a data structure for a knowledge base.Figures 7-8 are exemplary user interfaces depicting the interaction of the human representative.Figures 9A-B depict a workflow diagram showing the interaction between the Al avatar and the user.Figure 10 depicts an exemplary network environment in which the system of Figure 1 and the process of Figure 2 may be practiced.Figure 11 depicts an exemplary computer system.DETAILED DESCRIPTIONA system and method guide and constrain an Artificial Intelligence (Al) engine to generate a response by an Al avatar for a user. The response generation process includes an Al guidance and control system configured to facilitate the communication of the user to the Al avatar. The response generation process receives real-time inputs from a human representative via a mobile application which helps the Al engine to provide the response to the user when the query of the user is new to the Al avatar. A prompt guides the Al engine to enable dynamic and continuous interaction. The Al engine ingests both user and real-time inputs, using a natural language processing algorithm to analyze and update a knowledge base of the Al avatar. A multimodal processing engine on a cloud-based server utilized by Al engine further enhances by handling diverse input types like text and voice to provide personalized responses to the user.Moreover, the response generation process integrates real-time expertise by allowing a dedicated human representative to provide inputs through the mobile application connected to the Al guidance and control system to update the knowledge base in real time. The Al avatar is capable of delivering personalized responses based on the updated knowledge base. The response generation process encompasses versatile interaction channels, such as messaging apps and voice technologies, ensuring comprehensive user engagement. The response generation process also stores historical user interactions for ongoing refinement using machine learning algorithms. Beneficially, instant notification alerts are provided which notify the human representative of new user interactions requiring input. Furthermore, the user feedback is utilized that enhance the knowledge base, fostering continual improvement. The response generation process prioritizesAtorney Docket No. T00708-716-717NE-PCT the real-time inputs from the human representative over historical data for updates, guaranteeing that responses reflect the latest information. Additionally, the response generation process is designed to create an Al avatar that not only engages users effectively but also evolves continuously to enhance user experience and satisfaction.The system and method set forth herein address technical issues with generating the desired outputs described herein. Conventionally, manual processes were used to generate the desired outputs and were very tedious and time consuming. The present system and method utilize an automated system that does not merely automate a manual process or use a conventional system in a conventional way. The present system and method utilize one or more artificial intelligence (Al) engines and integrate programmatic process management to technologically guide and constrain the one or more Al engines to produce the desired outputs in a completely different way than any manual process and different than normal use of programs and Al engines. Utilizing specially engineered guidance and control to direct an Al system to solve the problems below presents a technical problem that requires a technical solution. The system and method described below are not simply engaging a computer to carry out conventional mental processes, but rather change how computers (and Al systems, specifically) operate to achieve the generation results that were not previously possible or were substantially inefficient prior to the system and method set forth below. The Al system needs specific technical guidance, control, and constraints to achieve results that are not otherwise achievable.Prompts are used to guide and constrain each Al engine. The prompts guide each Al engine by steering the Al engine(s). “Guiding” an Al engine refers to providing the Al engine with a general direction or framework to shape the Al engine’s behavior or decision-making process. Guiding sets goals or principles. Guiding allows the Al engine some flexibility to interpret and adapt, much like giving it a compass to navigate rather than a fixed path.Constraining each Al engine includes imposing specific, hard limits or rules on what each Al engine can do. Constraining an Al engine can also include providing specific input data to not only guide but also constrain the scope of each Al engine’s reasoning basis and response. Constraining each Al engine assists with aligning the Al engine(s) for its(their) intended use.Atorney Docket No. T00708-716-717NE-PCTNormally Al engines are provided a single user prompt requesting the Al engine, such as OpenAI’s ChatGPT and its various implementations such as Anthropic’s Claude Sonnet, to perform a task and produce an output. However, this conventional Al engine prompting method has a variety of technical shortcomings. Without proper guidance and constraints, an Al engine will not produce the desired output specified as produced by the system and method described herein. Instead, the Al engine will produce many unusable outputs that are unusable for a variety of reasons including so-called “hallucinations” where the Al engine presents fabricated information, duplicate outputs, too few outputs, too many outputs, outputs that do not meet desired criteria, and so on. Without special technical guidance, the Al engine cannot reliably be applied to generate desired outcomes.The system and method generate decomposed, technically engineered Al prompts to include selected and integral Al engine guidance and constraints. The technically engineered prompts are generated and guided with programmatic, automatic inputs specifically designed to unconventionally guide and constrain an Al engine to produce desired outputs, perform quality control to retain or automatically discard outputs that do not meet guidance and constraints, and make the desired outputs available for use, such as use by computer system applications. In at least one embodiment, the problem to be solved by the integrated programmatic and Al engine system and method is uniquely and unconventionally decomposed, and Al prompts are used to solve the decomposed problem. Furthermore, the programmatic inputs to the decomposed Al prompts provide guidance to meet desired output characteristics.Determining a number of prompts, the guidance and constraints within each prompt, and data flowing from one Al engine prompt to another, in addition to testing a number of prompts for the decomposed problem, testing within each prompt, and validating a desired quality of outputs becomes an intractable combinatorial problem without technical guidance and constraint of the system and method described herein. Thus, the present system and method described implement an integration of programmatic management over decomposed prompts with engineered Al engine guidance and constraints to effect an improvement in Al, programmatic Al management, and Al integrated with programmatic management technology. The present system and method allow computer systems to include programmatic management, one or more Al engines, and one or more data sources to produce the output described herein that previously could not beAtorney Docket No. T00708-716-717NE-PCT produced with conventionally prompted Al engines or could only be produced by humans utilizing a completely different, time consuming, and tedious process. The system and method improve conventional methods through the use of a programmatic Al engine management system to generate decomposed, technically engineered Al prompts to include selected and integral Al engine guidance and constraints. It is, for example, the incorporation of the programmatic Al engine management system to generate decomposed, technically engineered Al prompts to include generated, integral, and unconventional Al engine guidance and constraints and execution by the one or more Al engines to provide useful results that improve existing technical processes, which is not an automation of a conventional process.Programmatic components and Al engines generally utilize one or more processors that have access to memory, which may include one or more storage components, to execute and perform functions. An Al engine is a core hardware and software system that enables artificial intelligence applications to process data, learn patterns, and generate insights or actions. It functions as the brain behind Al-driven systems, facilitating tasks such as machine learning, natural language processing, and decision-making. Exemplary components of an Al engine are:10. Machine Learning Models - Algorithms that analyze data, recognize patterns, and make predictions.11. Neural Networks - Deep learning architectures that mimic the human brain for tasks like image and speech recognition.12. Data Processing Module - Handles raw data input, transformation, and feature extraction.13. Inference Engine - Applies trained models to make real-time decisions based on new data.14. Optimization Algorithms - Improves model efficiency, reducing errors and improving predictions.15. Natural Language Processing (NLP) Module - Enables Al engines to understand, interpret, and generate human language (e.g., chatbots, voice assistants).16. Computer Vision Module - Allows Al to interpret and analyze images or videos.Atorney Docket No. T00708-716-717NE-PCT17. Reinforcement Learning Mechanism - Helps Al learn from trial and error, optimizing performance over time.18. API Interface - Connects the Al engine with applications, enabling integration with other software or platforms.Examples of Al Engines include: XAI’s Grok and variations thereof, Google TensorFlow, Meta's PyTorch, Microsoft Azure Al, OpenAI’s ChatGPT and variations thereof, IBM Watson, OpenAI Whisper, Google BERT & T5, Amazon Lex, Anthropic Claude, DeepMind’s AlphaCode, Google Vision Al, Meta's DINO & SAM (Segment Anything Model), NVIDIA DeepStream. OpenCV Al Kit, Amazon Polly. Google WaveNet, Deepgram.Figure 1 depicts an exemplary response generation system 100 to generate a response 102 by an Al avatar 104. Figure 2 depicts an exemplary response generation process 200 utilized by the response generation system 100.The Al engine 106 generates responses 102 for the user 108. The Al engine 106 receives user inputs 110 and real-time inputs 112 from the user 108 and a human representative 114 of the Al avatar 104. The Al engine 106 is configured to utilize the received user input 110 and real-time inputs 112 to generate the personalized response 102. The Al engine 106 utilizes a plurality of algorithms to interpret the content based on the received user input 110 and real-time inputs 112 to provide a personalized response 102 to the user 108.Referring to Figures 1 and 2, in operation 202, facilitating communication between the user 108 and the Al avatar 104 via an Al guidance and control system 116 to receive the user inputs 110. The Al guidance and control system 116 serves as the medium where the communication between the user 108 and the Al avatar 104 occurs. The Al guidance and control system 116 may be a web-based application, mobile application or virtual or augmented reality environment. The Al guidance and control system 116 provides a user interface through which the user 108 can send user input 110 in the form of text, voice, gestures, or other forms of interaction. The user input 110 is interpreted by the Al avatar 104. The Al avatar 104 is a digital representation designed to simulate human-like attributes, including appearance, behavior, or communication style. The Al avatar 104 processes and replies to the user 108 in any form such as text, voice,Atorney Docket No. T00708-716-717NE-PCT gestures, or other forms of interaction. In one embodiment, the Al avatar 104 can be a 3D avatar or humanoid robots equipped with the necessary sensory mechanisms to further humanize the interaction.The Al guidance and control system 116 facilitates communication between the user 108 and the Al avatar 104. The Al avatar 104 is available 24 / 7, offering real-time interactions. The Al avatar 104 provides the user 108 with the instant response 102 to queries or issues, significantly enhancing the user experience. The Al guidance and control system 116 allows for interactions with multiple users simultaneously without degradation in performance. The Al avatar 104 can become adept at understanding user 108 preferences, communication style, and recurring issues, thereby improving efficiency. The Al avatar 104 makes decisions about how to respond appropriately. This involves a combination of rule-based systems, where predefined answers are available for common queries, and advanced responses 102 are generated based on the context of the conversation. The Al avatar 104 performs tasks on behalf of the user 108, such as scheduling appointments, managing workflows, making purchases, decision-making, and so forth.Moreover, interacting with the user 108 through text-based interaction channels, including messaging platforms, web-based chat interfaces, or mobile applications. The messaging platform is a text-based channel used for interacting with the Al avatar 104. The messaging platforms are widely adopted due to their ubiquity and ease of use. The user 108 is familiar with engaging in conversation. The messaging platforms allow the user 108 to interact in a conversational format, where the user 108 can ask questions, make requests, or provide feedback in real-time. The webbased chat interfaces are integrated into websites to facilitate real-time conversations between the user 108 and the Al avatar 104. The web-based chat interfaces guide the user 108 through tasks, answer frequently asked questions, or troubleshoot issues. The web-based chat interfaces appear as a small window embedded in the corner of a webpage, providing instant access to the Al avatar 104. The mobile applications incorporate device-specific features such as notifications, location services, and voice input alongside text-based communication. The text-based interaction channels are scalable, allowing to interact with large numbers of user(s) 108 simultaneously. The text-based interaction allows the user 108 to initiate conversation from anywhere at any time through a desktop, smartphone, or messaging app.Atorney Docket No. T00708-716-717NE-PCTInteracting through voice-based interaction channels, including voice assistants, smart speakers, or other audio input devices. The voice-based interactions allow users 108 to communicate with the Al avatar 104 using spoken language, creating a hands-free, intuitive, and often more natural mode of interaction. In at least one embodiment, the voice-based interaction channels may be Amazon Alexa owned by Amazon having headquarters in Seattle, Washington, United States, Google Assistant owned by Google having headquarters in Mountain View, California, United States, and Siri owned by Apple having headquarters in Cupertino, California, United States. The voice-based interactions allow the user 108 to perform a variety of tasks simply by speaking.In operation 204, receiving real-time inputs 112 from the human representative 114 associated with the Al avatar 104 through a mobile application 118. The mobile application 118 is in communication with the Al guidance and control system 116. The mobile application 118 serves as the interface for the interaction, acting as a conduit between the human representative 114 and the Al guidance and control system 116 that houses the Al avatar 104, ensuring that communication occurs instantly and efficiently. The human representative 114 is a human operator that has been mimicked by the Al avatar 104 that allows real-time feedback, and guidance to the Al avatar 104 whenever required to enhance the user experience. The mobile application 118 is the interface for the human representative 114 to engage with the Al avatar 104 and provide real-time inputs 112. The mobile application 118 includes interfaces such as buttons, sliders, voice commands, or text input fields that allow the human representative 114 to issue commands, adjust parameters, or intervene in ongoing interactions.The term real-time input 112 refers to inputs provided by the human representative 114, received and processed by the Al avatar 104. The real-time input 112 ensures that the response 102 of the Al avatar 104 remains synchronized. The real-time input 112 processing is facilitated by the mobile application 118 connected to the Al guidance and control system 116 using protocols such as WebSockets or HTTP / 2. The real-time inputs 112 are provided to the Al avatar 102 whenever the Al avatar 104 is unable to provide the solution of the particular query of the user 108 via user device 113, the real-time inputs 112 enable the Al avatar 104 to respond dynamically to critical situations. For example, in customer service applications, the human representative 114 needs to intervene and guide the Al avatar 104 to respond if the Al avatar 104 encounters a complex query that the Al avatar 104 cannot handle autonomously. In such cases,Atorney Docket No. T00708-716-717NE-PCT the human representative 114 can provide immediate real-time input 112 through the mobile application 118, directing the Al avatar 104 to provide a specific response 104. This ensures that the Al avatar 104 remains effective even in situations where its pre-programmed capabilities might fall short, enhancing the overall flexibility and robustness.The mobile application 118 communicates with the Al guidance and control system 116 to enable in receiving real-time inputs 112 from the human representative 114. The Al guidance and control system 116 houses the Al avatar 104 and handles the heavy computational tasks required to process inputs, generate the response 102, and manage the overall interaction. The Al guidance and control system 116 ensures that real-time inputs 112 from the human representative 114 are integrated seamlessly with the ongoing interaction of the user 108 with the Al avatar 104. The mobile application 118 is in constant communication with the Al guidance and control system 116, security and privacy are paramount. The Al guidance and control system 116 ensures that real-time inputs 112 from the human representative 1 14 are transmitted securely to prevent unauthorized access or tampering. This often involves the use of encryption protocols to protect the data being transmitted between the mobile application 118 and the Al guidance and control system 116.Moreover, receiving real-time inputs 112 from the human representative 114 in various formats, including text, voice, and multimedia inputs through the mobile application 118. The mobile application 118 is designed to handle and process different input formats such as text, voice, and multimedia. The text inputs allow the human representative 114 to provide instructions, feedback, or response by typing in text to the Al avatar 14. The voice inputs enable the human representative 114 to interact with the Al avatar 104 without needing to type. The voice inputs allow hands-free or on-the-go scenarios, where typing may be impractical or slow. The voice recognition technology integrated into the mobile application 118 that converts spoken words into text or directly interprets the command, allowing for seamless communication. Moreover, the voice interactions can capture nuances in tone and inflection, providing additional context to the inputs. The multimedia inputs expand the range of possibilities by allowing the human representative 114 to send images, videos, or other visual data through the mobile application 118. This is useful in complex situations where visual information is needed to enhance the communication or decision-making process.Atorney Docket No. T00708-716-717NE-PCTIn operation 206, the Al Guidance and Control System instructs the prompt generator 120 to generate a prompt 119 to guide and constrain the Al engine 106 to enable dynamic interaction and continuous learning of the Al avatar 104 to generate the response 102. The prompt 119 sets the parameters for the Al engine 106 to generate the response 102, guiding the Al engine 106 to synthesize the input received. The prompt 119 are generated by the prompt generator 120. The prompt generator 120 creates a structured or semi-structured set of instructions that serves as the input for the Al engine 106. The prompt 119 encapsulates the user input 110 and guides the Al engine 106 in processing information and generating the response 102. The prompt 119 can vary in complexity, ranging from simple questions or directives to more intricate queries that encompass multiple variables or layers of meaning. The prompt generator 120 is programmed to generate the prompt 119 dynamically based on the user inputs 110 from the user 108. For example, if the user 108 asks the Al avatar 104 a question, the prompt generator 120 takes the user input 110, contextualizes it with additional data, and formulates detailed prompt 119 that guides the Al engine 106 to generate appropriate response 102. In at least one embodiment, the prompt 119 are generated by a prompt engineer.The Al engine 106 is responsible for processing the prompt 119 and generating the response 102 provided to the Al avatar 104. The prompt 119 generated by the prompt generator 120 acts as a set of instructions that guides the Al engine 106 in its decision-making process. The prompt 119 helps the Al engine 106 understand what task it is supposed to perform and how it should approach the problem or question at hand. The guidance provided by the prompt 119 is essential for the Al engine 106 to generate the response 102 that are relevant and also contextually appropriate. For instance, if the user 108 asks the Al avatar 104 about recent orders, the prompt 119 generated by the prompt generator 120 would include contextual details like the user’s order history, preferences, and any ongoing issues to help the Al engine 106 formulate the response 102 that is specific to the user 108.The prompt 119 generated by the prompt generator 120 enables the Al engine 106 to engage in dynamic interaction. As the Al avatar 104 receives new inputs or data updates the prompt generator 120 adapts the prompt 119 to reflect these changes. This ensures that the Al engine 106 is always working with the most up-to-date and relevant information, allowing it to generate the responses 102 that are timely and appropriate for the current situation. The prompt generatorAtorney Docket No. T00708-716-717NE-PCT120 also involves the Al avatar 104 to maintain an ongoing dialogue or interaction thread. For instance, the prompt generator 120 helps the Al avatar 104 to flow conversation and generates the prompt 119 allowing the Al engine 106 to respond coherently based on previous exchanges. This helps create the impression of a natural, human-like conversation, where the Al avatar 104 remembers context, understands nuances, and responds appropriately to follow-up questions or commands. The prompt 119 generated by the prompt generator 120 provides the Al engine 106 with the guidance to process the user input 110 and produce the response 102. The response 102 is communicated back to the user 108.Operation 208 transfers the prompt 119 to the Al engine 106 to generate the response 102 and provide the generated response 102 to the Al avatar 104. The prompt 119 encapsulates the user input 110 and the real-time inputs 112 provided by the human representative 114, is sent to the Al engine 106 for further processing. The prompt 119 serves as an instruction or command for the Al engine 106, providing the necessary context and information to generate the response 102. Once the prompt 119 is generated it is provided to the Al engine 106. The transfer ensures the flow of communication between the Al guidance and control system 116 and the Al engine 106. The prompt 119 essentially guides the Al engine 106 on how to interpret the input, process relevant information, and formulate response 102. In at least one embodiment, the prompt 119 may include contextual information related to the user 108. This might involve the user’s history, preferences, past interactions and so forth.The Al engine 106 is configured to ingest the user inputs 110 from the Al guidance and control system 116 and real-time inputs 112 from the human representative 114. The ingestion involves receiving and categorizing various forms of input, whether they are textual queries, voice commands, or multimedia inputs (such as images or videos). The input is received from the user 108 such as user inputs 110 who interact with the Al avatar 104 having query, through the Al guidance and control system 116 and the human representatives 114 provide live, real-time input 112 to the Al avatar 104 for providing the solution of the query. For example, the user 108 interacting with the Al avatar 104 might ask a question, which is immediately captured as the user input 110. At the same time, the human representative 114 may provide additional information or context to the Al avatar 104 in real-time. The Al engine 106 is configured to gather and merge these inputs efficiently. The multi-source ingestion capability ensures that theAtorney Docket No. T00708-716-717NE-PCTAl avatar 104 remains responsive and adaptive to both automated and manual inputs. Moreover, the ability to handle real-time inputs ensures that the Al avatar 104 can adjust its behavior and responses dynamically, without requiring manual intervention.The Al engine 106 is configured to process and analyze the user inputs 110 and real-time inputs 112 using a natural language processing (NLP) algorithm 122 to interpret the content. Once the user inputs 110 and real-time inputs 112 are ingested, the Al engine 106 proceeds to process and analyze the inputs using the NLP algorithm 122. The NLP algorithm 122 enables the Al engine 106 to understand, interpret, and respond to human language. The NLP algorithm 122 within the Al engine 106 is responsible for interpreting the content of the inputs whether they are text, voice, or multimedia data. In the case of text inputs, the NLP algorithm 122 breaks down the text into its constituent components (words, phrases, sentences) and analyzes their meaning in context. For voice inputs, the NLP algorithm 122 converts speech into text using voice to text converter, after which it applies the same text-processing techniques to analyze the input. The ability to process both text and voice inputs allows the user 108 to interact with the Al avatar 104 in whichever way is most convenient for them. In at least one embodiment, NLP algorithm 122 is applied to multimedia inputs such as images or videos, extracting relevant text or metadata to aid in the interpretation of the content. By using NLP algorithm 122 to analyze the inputs, the Al engine 106 interprets user queries, detects underlying intents, and gathers all necessary context for generating response 102. Once the inputs have been processed and analyzed, the Al engine 106 generates the response 102 based on the interpreted content. Once the response 102 is generated, it is provided to the Al avatar 104 for delivery to the user 108. The Al avatar 106 acts as the interface presenting the response 102 in a way that is understandable and natural to the user 108.The Al engine 106 is configured to update a knowledge base 124 of the Al avatar 104 based on the analyzed user inputs 110 and real-time inputs 112. The knowledge base 124 acts as the memory, storing all relevant information that the Al avatar 104 has learned from past interactions. Updating the knowledge base 124 ensures that the Al avatar 104 becomes smarter and more capable over time, learning from every interaction. The updating enables the continuous learning of the Al avatar 104. By analyzing the inputs received by the Al avatar 104 and the response(s) 102 generated, the Al avatar 104 improves its decision-making capabilities.Atorney Docket No. T00708-716-717NE-PCTThe more interactions the Al avatar 104 has, the richer and more comprehensive its knowledge base 124 becomes, allowing it to provide more accurate, relevant, and personalized responses 102 in future interactions. Moreover, the knowledge base 124 can also be updated with external data sources, such as real-time updates, product information, or customer data. This allows the Al avatar 104 to stay up to date with the latest information and ensure that the responses 104 are relevant to current conditions or user preferences.In operation 210, processing the analyzed user inputs 110 and real-time inputs 112 multimodally using a multimodal processing engine 126 on a cloud-based server 128. The multimodal processing engine processes text, voice, and other input types from the user 108 and the human representative 114. The multimodal processing engine 126 is designed to handle different types of inputs simultaneously. Typically, the user 108 may interact with Al avatar 104 through various mediums sending messages, speaking commands, or even providing visual data like images or videos. The multimodal processing engine 126 allows the Al avatar 104 to interpret these diverse inputs concurrently and process them in a unified manner. For example, the user 108 interacts with the Al avatar 104, type a question, follow up with a voice command, and even upload a photo for clarification. The multimodal processing engine 126 can take all these forms of input, process them holistically, and generate a cohesive response 102. The multimodal processing engine 126 uses different algorithms to each type of input for instance, NLP for text, automatic speech recognition (ASR) for voice, and image recognition for visual data. The diverse data are then integrated into a single workflow, allowing the Al engine 106 to extract relevant information from each input type and generate the response 102 that considers all inputs.The multimodal processing engine 126 operates on the cloud-based server 128. The cloud-based server 128 provides the necessary computational resources to handle the intensive data processing required by the multimodal processing engine 126. The cloud-based server 128 allows offloading intensive tasks to the cloud, where vast amounts of data can be processed in parallel, improving the speed and performance. The cloud-based server 128 allows the Al avatar 104 to handle concurrent inputs from multiple users, ensuring consistent and fast performance without bottlenecks. When the user 108 or human representative 114 provides input in the form of text, the Al engine 106 employs the NLP algorithm 122 to understand and interpret theAtorney Docket No. T00708-716-717NE-PCT content. The NLP algorithm 122 reduces the text into smaller units like words or phrases, understands the grammatical structure of sentences, derives meaning from the text, and determines the emotional tone, to comprehend user questions, commands, or descriptions in a way that mimics the human representative 114. When the voice input is received, the Al engine 106 uses ASR to convert spoken language into text. Once converted, this text is processed similarly to other textual inputs using the NLP algorithm 122. In addition to handling user input 110 from the user 108, the Al engine 106 also processes the real-time inputs 112 from human representatives 114. The human representative 114 may be professionals, experts, or operators who interact with the Al avatar 104 to provide additional context or guidance. The real-time input 112 from the human representative 114 is provided where Al avatar 104 alone might struggle to provide the response 102.In operation 212, providing personalized responses 102 to the user 108 by the Al avatar 104 through the Al guidance and control system 1 16. The response 102 are based on the updated knowledge base 124. The Al guidance and control system 116 serves as the primary interface between the user 108 and the Al avatar 104. The Al avatar 104 can take various forms, such as a virtual character in a mobile app, a chatbot in a web-based platform, or even a voice assistant in a smart device. The role of the Al avatar 104 is to interact with the user 108 in a way that mimics human conversation, making it easier for the user 108 to communicate their needs and receive relevant information or services. The Al avatar 104 acts as the face responding to the user 108 questions and ensuring the interaction feels intuitive and seamless. For example, if the user 108 asks a question about a product, the Al avatar 104 may respond with details that are specific to that user's preferences, past purchases, or previous interactions.1. Below is the prompt 119 to call Al avatar 104 to assist the user 108 by providing the response 102 of the queries based on knowledge base 124:- You are $ { pers ona . name } ' s Pers ona , a tool calling Al agent with s el frecurs ion des igned to as s i s t users by providing answers bas ed on your knowledge databas e .- Des cription o f your pers ona : $ { pers ona . des cription ) .- You have 2 tool s : s earch and mes s age owner .Atorney Docket No. T00708-716-717NE-PCT- You can call only one tool at a time and analyze data you get from tool responses .- You are provided with the tool signatures within <tools>< / tools> tags .Objective: |- Your purpose is to assist users by providing answers based on your knowledge database.- Use the provided tools to search for information (search) or request additional details from the owner (message_owner ) when needed.- Analyze the data from tool results and make decisions on next steps.- Don't make assumptions about what values to plug into tool arguments.- Once you have called a tool, wait for the user to send the results back to you within <tool_response>< / tool_response> tags.- Don't make assumptions about tool results if <tool response> tags are not present since tool hasn't been executed yet.- Your final response should directly answer the user query with information provided by the <tool_response> returned by the 'search' or 'message_owner ' tool and should be placed within <answer>< / answer> tags.- NEVER use any information that is not explicitly provided in the <tool response> tags .Tools:Here are the available tools:<tools> [{"type": "function", "function": {"name": "search", "description": "Send a search query to the knowledge base.", "parameters": {"type": "object", "properties": {"query": {"type": "string"} }, "required":[ "query"] } } } ,{"type": "function", "function": {"name": "message owner", "description": "Request more information from the persona owner. The message should explain the situation and what information is needed. Returns the information from the owner. Should use this tool if not able to get usefulAtorney Docket No. T00708-716-717NE-PCT information from the search tool.", "parameters": {"type": "object", "properties": {"message": {"type": "string"} }, "required": ["message"] } } }] < / tools>Instructions: |1. When a user sends a message, or you receive some result back, first analyze it using a step-by-step reasoning. Enclose your thought process within <thinking>< / thinking> tags. Break down your reasoning into clear, logical steps. Consider:- What information do you need to answer the query?- Which tool (search or message owner) would be most appropriate?- What specific search terms or questions would be most effective?- How will you interpret and use the results?- If you are analysing some results, which documents are related to the question you are trying to answer?- Do the documents contain the information you need? Or should you contact the owner for more information?- Remember: You must ONLY use information from tool responses. Do not rely on any pre-existing knowledge.2. After your thought process, proceed with the appropriate tool call or response. For each tool call, return a valid JSON object (using double quotes) with tool name and arguments within <tool callx / tool call> tags as follows :<tool call>{"arguments": <args-dict>, "name": <tool-name>}< / tool call>3. If the user question requires information from the knowledge base and you decide to use the 'search' tool:- Provide one or more search phrases within the correct tool call format .Atorney Docket No. T00708-716-717NE-PCT- Each search phrase should be complete and meaningful on its own.- Use the pipe character ' | ' to separate distinctly different search queries .- The better the search phrases, the better the results. So, try to be as specific as possible and leverage the fact that the search tool accepts multiple search queries (separated by ' | ' ) to search for related concepts or using different words for the same concept to make the search more effective.- Analyze search results provided in <tool response> tags.- If results are insufficient, refine your search or use 'message_owner ' .3.1. EXAMPLES (IMPORTANT: The following are EXAMPLES ONLY. Do not use these specific terms unless they directly relate to the actual question you are trying to answer. )Question: "What is quantum computing?"<tool_call> { "arguments " : {"query": "quantum computing | quantum computing definition and principles | quantum computing applications"}, "name": "search" } < / tool call>Question: "What are the latest trends in renewable energy?"<tool call> { "arguments " : {"query": "latest renewable energy trends | emerging green technologies"}, "name": "search" } < / tool call>Question: "How does artificial intelligence impact software development? "<tool call> { "arguments " : {"query": "Al impact on software development | machine learning in coding"}, "name": "search" } < / tool call>Atorney Docket No. T00708-716-717NE-PCT3.2. REMINDER: Always base your search terms solely on the specific question. Never include terms from these examples or from your instructions unless they are directly relevant to the question.3.3. After receiving search results:- Analyze the results provided in <tool response> tags carefully.- If the results don't sufficiently answer the user's question: a) Refine your search by formulating a new, more specific query, or b) Use the 'message owner' tool if additional information is needed .3.4. Before submitting your search query, review it to ensure:1. All terms are directly relevant to the user's question.2. No unrelated concepts from examples or other sources are included .3. The query is specific enough to yield useful results.4. Each query (if separated by ' I ' ) has sufficient context to be meaningful on its own.5. The tool call format is correctly used.3.5. CORRECT vs. INCORRECT examples:- CORRECT (multiple distinct queries) : "artificial intelligence def inition | Al practical applications"- CORRECT (single phrase) : "renewable energy advancements and applications "- INCORRECT: "climate change | causes | effects | solutions " (Each query (if separated by ' | ' ) should have sufficient context to be meaningful on its own)Atorney Docket No. T00708-716-717NE-PCT4. Use the 'message owner' tool when:- Search results are insufficient or unclear.- You need information not likely to be in the knowledge base.- You need clarification on company policies or specific details.Always explain the situation and specify what information you need when messaging the owner.5. Communicate directly with the user:- All direct responses to the user should be enclosed in <answer>< / answer> tags.- Be clear, concise, and straight to the point in your responses.- If you need clarification from the user, ask directly in your response .- The user does not have access to the content of the<tool response> tags, they are only for you and your interaction with the tools you decide to use. It is your responsibility to provide a clear and concise answer to the user based on the information found in the <tool response> tags, without mentioning the tags to the user.- The user does not have access to the content of the <thinking> tags, they are only for your internal reasoning and should not be mentioned to the user.- If you receive some validation, error message or correction inside <tool response> tags, pay close attention to it and adjust your response accordingly, but the user should not be informed about it. The user has no access to the content of the <tool response> tags, so you don't need to mention your mistake or the correction to the user, just adjust your response or the tool call accordingly.6. Call only one tool at a time and wait for the results before proceeding .Atorney Docket No. T00708-716-717NE-PCT7. Do not fabricate information or use any pre-existing knowledge (even if you think you know the answer) . If you're unsure or don't have the information from tool responses, search again or use the 'message owner' tool to get accurate information.8. If you need to do additional search prior to answer the user or decided to contact the owner, do it without informing the user. Inform the user only when you have the final answer.9. Continue calling tools and analyzing results until you can provide a satisfactory answer or you've reached a maximum of 5 iterations. When you have the final answer, enclose it within <answer>< / answer> tags.10. In all interactions:- Be friendly, helpful, polite and professional.- Never mention the name of the tools you have access to or its parameters. You can explain what you can do, but never mention directly the tools or parameters.- Ensure every direct response to the user is enclosed in <answer>< / answer> tags, even for simple greetings or clarifications.- Always provide your final answer within <answer>< / answer> tags .11. Use step-by-step reasoning throughout your process:- Before each action (searching, messaging owner, or responding to user) , use <thinking> tags to break down your reasoning.- After each tool response, use <thinking> tags to analyze the results and decide on next steps.- The content within <thinking> tags is for your internal reasoning and will not be shown to the user. Ensure your final response or tool call is outside these tags.Atorney Docket No. T00708-716-717NE-PCT- Your final answer to the user should always be enclosed in<answerx / answer> tags.Example formats for analyzing user questions and search results:11.1. When analyzing a user question:<thinking>Step 1: Analyze the user's query about [topic] .Step 2: Identify key concepts and information needed to answer the query .Step 3: Determine if a search is necessary to gather information.Step 4: If search is needed, formulate precise and relevant search phrases (formulate more than one search phrase and separate them with ' | ' ) .Step 5: Review search phrases to ensure they are derived only from the user's query.[Add or remove steps as necessary for thorough analysis]< / thinking> <tool_call> { "arguments " : {"query": "relevant search phrase 1 I relevant search phrase 2"}, "name": "search" } < / tool_call>11.2. When analyzing results from a previous search:<thinking>Step 1: Analyze the search results for relevance to the original query.Step 2: Determine if the search results provide sufficient information to answer the user's question.Step 3: If information is insufficient, consider refining the search or using the message owner tool.[Add or remove steps as needed for comprehensive analysis]< / thinking> <tool_call> { "arguments " : {"message": "I need additional information about [specific aspect] . Can you provide more details?"}, "name": "message owner "} < / tool call>Atorney Docket No. T00708-716-717NE-PCT11.3. When analyzing results from a previous search and providing a final answer:<thinking>Step 1: Carefully review the search results provided in the <tool response> tags .Step 2: Identify the key information relevant to the user's original query .Step 3: Organize the relevant details to form a clear and comprehensive answer .Step 4: Formulate a concise yet informative response that directly addresses the user's question.Step 5: Ensure that ONLY information from the <tool_response> is used in the answer.Step 6: If the information is insufficient, determine if another tool call is necessary (search or message owner) .[Add or remove steps as needed based on the complexity of the information and query]< / thinking><answer>[Provide a clear, comprehensive answer that synthesizes the relevant information from the search results and directly addresses the user's query.]< / answer>11.4. When responding to a simple greeting or query that doesn't require tool use:<thinking>Step 1: Analyze the user's simple greeting "Hello, how are you?"Step 2: Determine that this is a basic greeting that doesn't require any tool use.Atorney Docket No. T00708-716-717NE-PCTStep 3 : Formulate a friendly and appropriate respons e .Step 4 : Ensure the respons e i s enclos ed in <answer> tags as per the ins tructions .< / thinking><answer>Hello ! I ' m doing well , thank you for as king . How can I as s i st you today?< / answer>The above prompt 119 guides the Al avatar 104 by leveraging two specific tools: a “search” function, which accesses the knowledge base 124 to retrieve relevant information, and a “message_owner” function, which reaches out to the human representative 114 when additional clarification or specific details are needed. This ensures that the Al avatar 104 only uses information explicitly retrieved from these tools, rather than relying on any pre-existing knowledge or making assumptions. The tool is configured to deliver clear, accurate answers based on data from the knowledge base 124 or directly from the human representative 114. To maintain this accuracy and transparency, every response 102 based on retrieved information is enclosed in ‘<answer>’ tags, while the thought process is separately documented in ‘<thinking>’ tags. These ‘<thinking>’ tags serve as a step-by-step reasoning record, helping in maintaining a logical progression in addressing the questionFor questions of each userl08 the Al avatar 104 evaluates the required information, decides if a “search” or “message owner” action is more appropriate, and then proceeds with the selected tool. The “search” tool call is formatted in a JSON structure within ‘<tool_call>’ tags, where the agent carefully designs relevant and context-rich search phrases. If the “search” results do not fully address the query of the user 104, the Al avatar 104 can refine the search or use the “message_owner” tool to ask the user 104 for more information. Each interaction with the tools is limited to one call at a time, and the agent waits for responses (provided in ‘<tool_response>’ tags) before taking the next step. This iterative process can loop up to five times to ensure an answer is fully accurate. Throughout, the Al avatar 104 maintains a courteous and professional tone, presenting only finalized response 102 without disclosing any backend processes or tools involved. This controlled approach enables the Al avatar 104 to deliver precise, user-focusedAtorney Docket No. T00708-716-717NE-PCT support by making thoughtful use of available resources while keeping interactions straightforward and data-driven.The knowledge base 124 serves as a dynamic repository of information. The knowledge base 124 contains both static data such as facts, product details, or policy information and dynamic data, which is updated based on the user 108 interactions and external inputs such as those provided by the human representative 114. The knowledge base 124 is continuously updated in real-time based on user interactions. The knowledge base 124 is hosted on the cloud-based server 128, it can easily expand to accommodate more data as the number of the users 108 grows. The Al engine 106 uses current and context-aware information to generate the response 102 that is tailored to the user 108. The process of generating personalized responses 102 starts when the Al engine 106 receives the user input 110 from the user 108. This input, whether it is a question, command, or request, is analyzed to determine its meaning and intent. Once the Al engine 106 understands the request of the user 108, it accesses the updated knowledge base 124 to retrieve relevant information. The knowledge base 124 contains generic facts and also stores personalized data points associated with individual users 108. This can include user-specific preferences, past interactions, demographic data, and other contextual information that the Al avatar 104 has learned over time. By using this data, the Al engine 106 craft responses that are uniquely tailored to each user 108. Below is the pseudo-code for updating the knowledge base 124 of the Al avatar 104. function updatePersonaKnowledge ( userinput, ownerinput ) : parsedUserlnput = parseinput ( userinput ) parsedOwnerlnput = parseinput ( ownerinput ) updatedKnowledge = integratelnputs (parsedUserlnput , parsedOwnerlnput ) updateKnowledgeBase ( updatedKnowledge ) return generateResponse ( updatedKnowledge )The updatePersonaKnowledge updates the knowledge base 124 for a “persona” such as the Al avatar 104 using inputs from the user 108 and an “owner” such as the human representative 114. The knowledge base 124 is updated based on the userinput received from the user 108 and ownerinput received from the human representative 114Atorney Docket No. T00708-716-717NE-PCTThe parseduserinput and parsedownerinput processes raw input data, by parsing it into a more usable format. The parsing involves extracting keywords or phrases, standardizing formats, or validating the structure of the input.The integratelnputs (parseduserinput , parsedOwnerlnput ) combines the userinput and owner input to create an updated set of the information. The integration merges information from both inputs.The updateKnowiedgeBase ( updatedKnowiedge ) receives the updated set of information to update the knowledge base 124 by adding new data, or modifying the existing information to reflect the latest input.The generateResponse ( updatedKnowiedge ) generates the response 102 based on the updated knowledge base 124. The response 102 is generally an answer to a query based on the user 108.Moreover, the continuous learning allows the Al avatar 104 to adapt to changes in user preferences, market trends, or external factors that affect the quality of the responses 102 it provides. The ability to update the knowledge base 124 in real-time also ensures that the Al avatar 104 remains responsive to new inputs and external developments. Furthermore, providing personalized responses 102 to the user 108 through the Al avatar 104 enhances the overall user experience by making interactions feel more relevant and intuitive. When the user 108 receive responses 102 that are tailored to their specific needs, they are more likely to engage.Moreover, storing historical user interactions in the cloud-based server 128, and analyzing the interactions between the user 108 and the Al avatar 104 using machine learning algorithms to improve the response 102 of the Al avatar 104. When the user 108 engages with the Al avatar 104, the interactions are logged and stored for future reference. The user interaction includes data such as user queries, response 102, feedback from the user 108 and so forth. The cloud-based server 128 ensures that the user 108 interaction data is securely stored and easily accessible. The cloud-based server 128 also allows for the data to be stored over long periods, to track and analyze long-term patterns and trends in the user 108 behavior. Once historical user interactions are stored in the cloud-based server 128, the user interactions are analyzed using machine learning algorithms. By applying machine learning algorithms to the stored data, the Al avatar 104 can gradually learn how to respond more effectively to user 108 queries.Atorney Docket No. T00708-716-717NE-PCTThe machine learning algorithms identify patterns in the stored data, such as common user intents, frequently asked questions, or recurring issues. The machine learning algorithms can classify these patterns and associate them with specific outcomes. Over time, the machine learning algorithms enable the Al avatar 104 to learn and predict the best response 102 based on past interactions. Advantageously, storing and analyzing historical interactions improve the responses 102 of the Al avatar 104. By continuously learning from past interactions, the Al avatar 104 becomes more adept at understanding the user 108 needs and providing accurate, contextually relevant, and personalized response 102. In at least one embodiment, the machine learning algorithms can detect and correct previous mistakes. If the Al avatar 104 provides an unsatisfactory or incorrect response 102, the Al avatar 104 can learn from this failure to avoid repeating the same error.Moreover, prioritizing real-time inputs 112 from the human representative 114 over historical data when updating the knowledge base 124 to ensure the response 102 of the Al avatar 104 reflects current information. The real-time inputs 112 reflect the most current status, and instructions to the Al avatar 104. The Al avatar 104 is configured to prioritize the real-time inputs 112. If the Al avatar 104 continues to rely on the historical data without incorporating the real-time input 112, it could provide inaccurate or outdated information to the user 108. The historical data allows the Al avatar 104 to build context over time, understanding user preferences, patterns, and frequently asked questions. However, the value of the knowledge base 124 depends on its ability to stay up-to-date. While historical data provides a foundation, realtime inputs 112 ensure that this foundation is continually refined and updated. Typically, the real-time inputs 112 are given precedence when there is a conflict with the historical data. When the real-time inputs 112 are received, they update the knowledge base 124, ensuring that the most relevant information is used in the response 102. Additionally, prioritizing real-time inputs 112 enhances the responsiveness and accuracy of the Al avatar 104. By focusing on the most up- to-date information to adapt to new circumstances, providing the user 108 with relevant, contextually aware answers.Typically, processing feedback from the user 108 through the Al guidance and control system 116 to refine the knowledge base 124 and improve future interactions of the Al avatar 104. The feedback can be provided in various forms such as user ratings, comments, user behavior andAtorney Docket No. T00708-716-717NE-PCT engagement levels during interactions. The feedback provided by the user 108 is captured and processed by the Al guidance and control system 116 through which the Al avatar 104 interacts with the user 108. The feedback is used to refine the knowledge base 124 to improve user interaction. Moreover, the feedback ensures that the Al avatar 104 stays responsive to the evolving needs of the user 108.Furthermore, structuring the knowledge base 124 hierarchically to allow certain types of realtime inputs 112 of the human representative 114 to override previously stored data in the knowledge base 124. In at least one embodiment, the knowledge base 124 organized the information in layers or levels, where different types of data are assigned varying levels of importance. The hierarchically structure is typically organized from general to specific, with higher-level information representing more permanent, foundational knowledge and lower levels containing more dynamic, situational data. The hierarchical design allows the Al avatar 104 to determine which information should take precedence when there are conflicts or updates. Typically, the real-time inputs 112 must override previously stored data to ensure that the Al avatar 104 remains relevant and accurate. If the Al avatar 104 relies on outdated historical data, it could provide inaccurate or misleading information to the user 108, leading to confusion and dissatisfaction. The knowledge base 124 structure hierarchically ensures that the Al avatar 104 remains flexible and adaptable, capable of incorporating real-time inputs 112.Additionally, notifying the human representative 116 via an alert on the mobile application when new user interactions require the real-time inputs 112 for the Al avatar 104. When the Al avatar 104 encounters a new or complex situation that falls outside its programmed output, or when contextual understanding requires more nuanced judgment that only human representative 116 can provide. The real-time inputs 112 from the human representative 116 are essential to guide the Al avatar 104. If the user 108 asks a question about an unusual issue or an urgent matter that has not been addressed in the knowledge base 124 of the Al avatar 104, in such a situation the Al avatar 104 may need human intervention. The real-time inputs 112 from the human representative 116 ensure that the response 102 are personalized, accurate, and contextually appropriate. The alert enables to notify the human representative 116 for intervention when the Al avatar 104 encounters user interactions that require real-time inputs 114. The alert is provided through a mobile application that the human representative 116 can monitor in real time. WhenAtorney Docket No. T00708-716-717NE-PCT the Al avatar 104 detects a situation that requires human assistance whether it’s due to the complexity of the query, a new scenario that falls outside its pre-programmed knowledge, or a situation where judgment or discretion is needed the alert is sent to notify the human representative 116. The notification might take the form of a push notification, an in-app alert, or even an SMS message, depending on the configuration of the mobile application.Figure 3 depicts a real-time response generating process 300, which is an embodiment of the response generation process 200 of Figure 2. At step 302, the user input 110 is provided by the user 108. The user input 110 is the query or interaction between the user 110 with the Al avatar 104. At step 304, the real-time input 112 is provided by the human representative 114 through the mobile application 118. The real-time input 112 is the additional information provided to the Al avatar 104 when the Al avatar 104 fails to provide the response 102 to the user 108 query. At step 306, both the user input 110 and the real-time input 112 are parsed to understand the meaning and intention. At step 308, integrate inputs, once parsed, both the user input 110 and the real-time input 112 are integrated merging them into a single state of understanding. At step 310, update the knowledge base 124, after integrating both the user input 110 and the real-time input 112 are utilized to update the knowledge base 124 of the Al avatar 104 to update or modify information to generate the response 102. At step 312, generate response, the updated knowledge base 124 is then used to generate the response 102 for the user 108 based on the user input 110 and the real-time input 112. At step 314, user output, by utilizing both the user input 110 and the real-time input 112 to generate the response 102 to the user 108.Figure 4 depicts a data structure 400 for a user interaction 402. The user interaction 402 stores the ongoing session data between the user 108 and the Al avatar 104. The user interaction 402 includes session Id, user Id, timestamp, user query, and avatar responses. The session Id is a unique identifier assigned to a specific interaction or session between the user 108 and the Al avatar 104. The session Id helps to track user 108 activity and maintain context during the interaction. The user Id is a unique identifier for each user 108. The user Id helps to personalize the experience and manage the credentials and preferences of the user 108. The timestamp refers to the exact time at which user interaction occurred for logging activities, tracking user behavior, and managing data effectively. The user query is the request that the user 108 submits to the AlAtorney Docket No. T00708-716-717NE-PCT avatar 104. The responsel02 are the replies or actions taken by the Al avatar 104 corresponding to the user queries.Figure 5 depicts a data structure 500 for a real-time update. The real-time update 502 captures the updates received from the human representative 114, which are used to update the knowledge base 124 of the Al avatar 104. The real-time update 502 includes update Id, session Id, timestamp, and update content. The update Id is a unique identifier assigned to each update. The update Id helps in keeping track of individual updates. The session Id represents a particular session or interaction instance during which the update was made. The timestamp indicates the exact time when the update occurred. The timestamps allow tracking of the sequence of updates. The update content is the actual information or data that has been changed or added in the update.Figure 6 depicts a data structure 600 for a knowledge base 602. The knowledge base 602 represents the evolving knowledge base 124 of the avatar 104, which is updated with new information from each interaction and real-time updates. The knowledge base 602 includes knowledge Id, related session Id, content, last updated. The knowledge Id is a unique identifier assigned to a specific piece of knowledge within the knowledge base 124. The related session Id a specific piece of knowledge to a relevant session, such as a user query or conversation. The related session Id enables tracking of how the knowledge is utilized within different contexts. The content refers to the actual information or data contained within the knowledge entry. The content can be in various forms, such as text, images, or videos, and provides the essential details that the user 108 needs. The last update indicates the most recent date and time when the knowledge base 124 was modified.Figures 7-8 are exemplary user interfaces 700 and 800 depicting interaction of the human representative 114. Referring to Figure 7 depicts the user interface 700 showing the login screen titled ‘Engage with Persona’ which prompts the human representative 114 to interact with the Al avatar 104. The user interface 700 shows fields for email 702 and password 704 entry. The human representative 114 provides the credentials such as email 702 and password 704 to interact with the Al avatar 104, once provided the human representative 114 press an enter button 706. In case the human representative 114 forgot the password 704, the humanAtorney Docket No. T00708-716-717NE-PCT representative 114 can recover the password 704 by clicking on a forgot your password tab 708. Referring to Figure 8 depicts the user interface 800 showing a dashboard with menu options like dashboard 802 and docs 804 at the top right corner. The user interface 800 shows the list of Al avatar 104 titled ‘Fancy’, ‘Nerdly’, and ‘Femmebot’. Typically, each Al avatar 104 is accompanied by manage access tab 804 and manage knowledge tab 806. The manage access tab 804 allows the human representative 114 to manage the access of the respective Al avatar 104. The manage knowledge tab 806 allows the human representative 114 to update the knowledge base 124 of the corresponding Al avatar 104. Moreover, the human representative 114 also creates a new Al avatar by clicking on a new avatar tab 808.Figures 9A-B depict a workflow diagram 900 showing the interaction between the Al avatar 104 and the user 108. As shown, the user 108 initiates requests and authenticates himself by signing in or verifying credentials. The user 108 interacts with the Al avatar 104 (also referred to as a persona) on a frontend layer 902. The frontend layer 902 represents the user interface where users interact. The frontend layer 902 is connected to a backend layer 904. The backend layer 904 is configured to process all the data during the user interaction. The backend layer 904 includes Redis 906 and fie storage 908. The Redis 906 is a central component for handling realtime data or caching. The Redis 906 is used for managing session data, quick data storage, or as a message handling temporary storage and coordinating data between different modules. The backend layer 904 includes message handler 910 configured to process various types of user- submitted content, such as text, images, and other documents. Typically, each content type follows a defined path for storing different content types, with pathways for storing and then queuing them for further analysis or storage. The queuing is done to allow the data to await before processing, depending on its type (text, voice, image). After queuing, data is then either stored or moved along for additional processing. The backend layer 904 is connected to a processors layer 912 connected via the Redis 906 and the file storage 908. The processors layer 912 includes text-to-speech worker 914, personas worker 916, document index worker 918, voice to text worker 920, image to text worker 922, conversational worker 924, email inbox processor 928.The text-to-speech worker 914 prepares a waveform based on the text and stored voice and stores the generated audio for animation by personas worker 916. The personas worker 916Atorney Docket No. T00708-716-717NE-PCT prepares a video based on the generated audio and image and stores the generated welcome video in the file storage 908. The document index worker 918 retrieved the data from the file storage 908 to prepare vectors and stored the embeddings, metadata, and text version of the document in OpenSearch 930. The voice to text worker 920 retrieves the data from the file storage 908 and converts the voice prompt to text and then stores the generated text. The image to text worker 922 retrieves the data from the file storage 908 to recognize the image and store the image interpretation. The conversational worker 924 engages in natural language conversations with users, based on frameworks like GPT. The conversational worker 924 retrieves the prompt. Ask the Al based on the prompt for answer. If answer found store the reply. If no answer is found, then search on the web and then store the reply. The Q&A indexing worker 926 retrieves data from Redis 906 and file storage 908 and rewrite the answer with Al. Update the database such as knowledge base 124 with new answer. Prepare the vectors separately for Q&A. then store embeddings, metadata, and text version of the answer in OpenSearch 930. Store embeddings, metadata, and text version of the question linking the answer to it in OpenSearch 930. The email inbox processor 928 retrieves the email from a mail server 932. Identify if the human representative 114 replied. If yes, then send the reply to the Q&A indexing worker 926 then notify the user 108 by email the response 102 of the query. In case when the response 102 takes longer than the usual. The Al avatar 104 notifies the user 108. The notification is sent to user 108, possibly after a process is completed or when the response 102 is ready. The user 108 may receive updates via email.Figure 10 is a block diagram illustrating a network environment in which a response generation system 100 and response generation process 200 may be practiced. Network 1002 (e.g. a private wide area network (WAN) or the Internet) includes a number of networked server computer systems 1004(l)-(N) that are accessible by client computer systems 1006(l)-(N), where N is the number of server computer systems connected to the network. Communication between client computer systems 1006(l)-(N) and server computer systems 1004(l)-(N) typically occurs over a network, such as a public switched telephone network over asynchronous digital subscriber line (ADSL) telephone lines or high-bandwidth trunks, for example communications channels providing T1 or OC3 service. Client computer systems 1006(l)-(N) typically access server computer systems 1004(l)-(N) through a service provider, such as an internet service providerAtorney Docket No. T00708-716-717NE-PCT(“ISP”) by executing application specific software, commonly referred to as a browser, on one of client computer systems 1006(l)-(N).Client computer systems 1006(l)-(N) and / or server computer systems 1004(l)-(N) are specialized computer programmed to improve conventional computer systems to implement and utilize the response generation system 100 and response generation process 200. The type of computer system that can be specially programmed to implement and utilize the response generation system 100 and response generation process 200 include a mainframe, a minicomputer, a personal computer system including notebook computers, a wireless, mobile computing device (including personal digital assistants, smart phones, and tablet computers). These computer systems are typically designed to provide computing power to one or more users, either locally or remotely. Each computer system may also include one or a plurality of input / output (“I / O”) devices coupled to the system processor to perform specialized functions. Tangible, non-transitory memories (also referred to as “storage devices”) such as hard disks, compact disk (“CD”) drives, digital versatile disk (“DVD”) drives, and magneto-optical drives may also be provided, either as an integrated or peripheral device. In at least one embodiment, the response generation system 100 and response generation process 200 can be implemented using code stored in a tangible, non-transient computer readable medium and executed by one or more processors. In at least one embodiment, the response generation system 100 and response generation process 200 can be implemented completely in hardware using, for example, logic circuits and other circuits including field programmable gate arrays.Embodiments of the response generation system 100 and response generation process 200 can be implemented on a computer system such as a special -purpose, special-programmed computer 1100 illustrated in Figure 11. Input user device(s) 1110, such as a keyboard and / or mouse, are coupled to a bi-directional system bus 1118. The input user device(s) 1110 are for introducing user input to the computer system and communicating that user input to processor 1113. The computer system of Figure 11 generally also includes a non-transitory video memory 1114, non- transitory main memory 1115, and non-transitory mass storage 1109, all coupled to bi-directional system bus 1118 along with input user device(s) 1110 and processor 1113. The mass storage 1109 may include both fixed and removable media, such as a hard drive, one or more CDs or DVDs, solid state memory including flash memory, and other available mass storage technology.Atorney Docket No. T00708-716-717NE-PCTBus 1118 may contain, for example, 32 of 64 address lines for addressing video memory 1114 or main memory 1115. The system bus 1118 also includes, for example, an n-bit data bus for transferring DATA between and among the components, such as CPU 1109, main memory 1115, video memory 1114 and mass storage 1109, where “n” is, for example, 32 or 64. Alternatively, multiplex data / address lines may be used instead of separate data and address lines.I / O device(s) 1119 may provide connections to peripheral devices, such as a printer, and may also provide a direct connection to a remote server computer systems via a telephone link or to the Internet via an ISP. I / O device(s) 1119 may also include a network interface device to provide a direct connection to a remote server computer systems via a direct network link to the Internet via a POP (point of presence). Such connection may be made using, for example, wireless techniques, including digital cellular telephone connection, Cellular Digital Packet Data (CDPD) connection, digital satellite data connection or the like. Examples of I / O devices include modems, sound and video devices, and specialized communication devices such as the aforementioned network interface.Computer programs and data are generally stored as code in a non-transient computer readable medium such as a flash memory, optical memory, magnetic memory, compact disks, digital versatile disks, and any other type of memory. The computer program is loaded from a memory, such as mass storage 1109, into main memory 1115 for execution. Computer programs may also be in the form of electronic signals modulated in accordance with the computer program and data communication technology when transferred via a network. In at least one embodiment, Java applets or any other technology is used with web pages to allow a user of a web browser to make and submit selections and allow a client computer system to capture the user selection and submit the selection data to a server computer system.The processor 1113, in one embodiment, is a microprocessor manufactured by Motorola Inc. of Illinois, Intel Corporation of California, or Advanced Micro Devices of California. However, any other suitable single or multiple microprocessors or microcomputers may be utilized. Main memory 1115 is comprised of dynamic random access memory (DRAM). Video memory 1114 is a dual-ported video random access memory. One port of the video memory 1114 is coupled to video amplifier 1116. The video amplifier 1116 is used to drive the display 1117. VideoAtorney Docket No. T00708-716-717NE-PCT amplifier 1116 is well known in the art and may be implemented by any suitable means. This circuitry converts pixel DATA stored in video memory 1114 to a raster signal suitable for use by display 1117. Display 1117 is a type of monitor suitable for displaying graphic images.The computer system described above is for purposes of example only. The response generation system 100 and response generation process 200 may be implemented in any type of computer system or programming or processing environment. It is contemplated that the response generation system 100 and response generation process 200 might be run on a stand-alone computer system, such as the one described above. The response generation system 100 and response generation process 200 might also be run from a server computer systems system that can be accessed by a plurality of client computer systems interconnected over an intranet network. Finally, the response generation system 100 and response generation process 200 may be run from a server computer system that is accessible to clients over the Internet.Although embodiments have been described in detail, it should be understood that various changes, substitutions, and alterations can be made hereto without departing from the spirit and scope of the invention as defined by the appended claims.Atorney Docket No. T00708-716-717NE-PCTSYSTEM AND METHOD FOR MANAGING ASYNCHRONOUS COMMUNICATIONBETWEEN AN Al AVATAR AND HUMAN REPRESENTATIVECROSS-REFERENCE TO RELATED APPLICATIONThis application claims the benefit under 35 U.S.C. § 119(e) and 37 C.F.R. § 1.78 of the following U.S. Provisional Application Nos., which are all incorporated by reference in their entireties: 63 / 693,180 filed September 11, 2024, 63 / 693,181 filed September 11, 2024, 63 / 693,182 filed September 11, 2024, 63 / 720,181 filed November 14, 2024, 63 / 738,421 filed January 6, 2025, and 63 / 810,751, filed June 5, 2025.Field of the InventionThe present invention relates in general to the field of electronics, and more specifically to asynchronous communication managing systems and asynchronous communication management processes for managing asynchronous communication between Al avatars and human representatives upon detection of network failure to establish a real-time connection.BACKGROUND

[0078] A digital assistant is utilized to resolve the query of a user during an active session. Traditional digital assistants rely on synchronous communication, where the interaction between the digital assistant and the human counterpart associated with the digital assistant happens in real-time. This approach necessitates that both the digital assistant and the human counterpart be simultaneously active. If the user poses the query that the digital assistant is unable to answer immediately, the typical response is limited to either an error message or an inability to provide an answer. This leaves the responsibility of follow-up entirely on the user, often requiring them to revisit the same query at a later time. Such interruptions can lead to frustration, as they break the natural flow of the interaction and detract from the overall user experience.

[0079] The traditional digital assistant becomes problematic in scenarios where comprehensive answers are not readily available. For instance, in customer service applications, many queries may require additional information or clarification before they can be resolved. However, if theAtorney Docket No. T00708-716-717NE-PCT digital assistant cannot provide a resolution on the spot, the session usually concludes without achieving the desired outcome. This premature ending of interactions means the user has to reengage with the digital assistant, repeating their query or starting from scratch in a new session. This repetition doubles the effort required from the user, making the process cumbersome and time-consuming.

[0080] Such inefficiencies extend beyond mere inconvenience, as they also impact the perception of digital assistants as reliable and effective tools. When the users are required to put in extra effort to obtain answers, it undermines the purpose of using the digital assistant in the first place, which is to simplify and streamline interactions. Additionally, the increased time to provide resolution caused by the traditional digital assistant can be particularly detrimental in high-stakes environments, such as technical support or medical advice, where timely and accurate responses are critical. Thus, the synchronous nature of the traditional digital assistants often falls short of meeting user expectations, particularly in complex or multifaceted use cases.BRIEF DESCRIPTION OF THE DRAWINGSThe systems and methods described herein may be better understood, and their numerous objects, features, and advantages made apparent to those skilled in the art by referencing exemplary embodiments depicted in the accompanying figures. The use of the same reference number throughout the several figures designates a like or similar element.Figure 1 depicts an exemplary asynchronous communication management system to manage asynchronous communication between an Al avatar and a human representative upon detection of a network failure to establish a real-time connection.Figure 2 depicts an exemplary asynchronous communication management process utilized by the asynchronous communication management system.Figure 3 depicts a data structure for updating the knowledge base based on the first notification message.Figures 4-6 are exemplary user interfaces depicting the interaction of the Al avatar with the human representative.Atorney Docket No. T00708-716-717NE-PCTFigure 7 depicts an exemplary network environment in which the system of Figure 1 and the process of Figure 2 may be practiced.Figure 8 depicts an exemplary computer system.DETAILED DESCRIPTIONAn asynchronous communication system and method manages asynchronous communication between an Al avatar and a human representative upon detection of a network failure to establish a real-time connection. The asynchronous communication management system and method include Al avatar that is configured to detect a connection failure when unable to establish or maintain a real-time connection with the human representative. The Al avatar sends a first notification message to prompt the human representative to provide the necessary information asynchronously. The Al avatar receives an asynchronous response message from the human representative including information relevant to the context of the interactive session. Updating a knowledge base of the Al avatar by parsing the received asynchronous response message. The Al avatar sends a second notification to the user through the communication channel to inform the user that the knowledge base has been successfully updated with the new information provided by the human representative.Moreover, the communication channels utilized for sending the first notification message can include mobile application notifications or emails directed to the associated accounts of the human representative. The communication channels ensure prompt delivery of the first notification message, facilitating quick responses from the human representative. Additionally, the method employs a network monitoring module to consistently track connectivity between the Al avatar and the representative, instantly detecting any disruptions. The Al avatar also uses a connection monitoring algorithm that checks the network status for issues like latency or packet loss, triggering the necessary notifications to maintain communication.Moreover, updating the knowledge base of the Al avatar when the asynchronous response message is received from the human representative. The Al avatar processes the asynchronous response message by parsing the response, analyzing its relevance to the ongoing session, and integrating it into the knowledge base. This involves context analysis to ensure that the newAtorney Docket No. T00708-716-717NE-PCT information is appropriately categorized and indexed, enhancing the accuracy of the Al avatar in future queries.Figure 1 depicts an exemplary asynchronous communication management system 100 to manage asynchronous communication between an Al avatar 102 and a human representative 104 upon detection of a network failure to establish a real-time connection. Figure 2 depicts an exemplary asynchronous communication management process 200 utilized by the asynchronous communication management system 100.The asynchronous communication management system 100 and asynchronous communication management process 200 are configured to manage communication between the Al avatar 102 and the human representative 104 when a real-time connection fails during an interactive session. It involves detecting the connection failure while the Al avatar 102 continuously monitors the network status. Upon detection, the Al avatar 102 alerts the human representative 104, prompting the human representative 104 to provide information asynchronously.Referring to Figures 1 and 2, in operation 202, detecting a connection failure during an interactive session of the Al avatar 102 with a user 106. Typically, detecting the connection failure during the interactive session enables seamless interaction and ensures uninterrupted communication between the Al avatar 102 and the human representative 104. In the interactive session, the Al avatar 102 serves as an intelligent, responsive interface designed to communicate with the user 106, responding to questions, providing guidance, and facilitating real-time support. The interaction allows the Al avatar 102 to create a lifelike and personalized experience for the user 106. The Al avatar 102 continuously monitors a network status associated with the session with the human representative 104 and identifies an inability to establish or maintain a direct, real-time connection. To provide a personalized experience for the user 106, the Al avatar 102 is able to identify and manage any connectivity issues that may arise, such as uninterrupted communication.The Al avatar 102 is configured to continuously monitor the network status to ensure that the Al avatar 102 remains aware of any fluctuations or interruptions in network performance. Through monitoring, the Al avatar 102 observes various metrics associated with connectivity, such as latency, bandwidth, and signal strength, which provide insights into the stability of theAtorney Docket No. T00708-716-717NE-PCT connection. By analyzing these indicators in real time, the Al avatar 102 can detect even subtle signs of connection deterioration, such as lagging response times or unexpected delays. This detection empowers the Al avatar 102 to respond proactively to potential disconnections with the human representative 104. The network status refers to the various aspects of the internet or intranet connection that support the communication of the Al avatar 102 with the human representative 104. The network status encompasses elements such as connection quality, stability, and availability which are integral for maintaining a smooth and responsive interaction with the human representative 104.The Al avatar 102 monitors the network status associated with the session with the human representative 104. Once the connection is established, the Al avatar 102 maintains a stable link and ensures that information is exchanged between the Al and the human representative 104 without interruption. Typically, real-time connectivity is important in cases where timely responses are critical, such as customer support or technical troubleshooting. The real-time connection allows the Al avatar 102 to provide immediate feedback, simulating a live conversation.Moreover, the connection failure is detected by a network monitoring module configured to continuously track connectivity status between the Al avatar 102 and the human representative 104 during the session. The network monitoring module is configured to continuously monitor the connectivity status between the Al avatar 102 and the human representative 104 throughout the entire session. The network monitoring module tracks the connection status in real time, ensuring that any issues are promptly identified and managed. By operating continuously, the network monitoring module offers an uninterrupted evaluation of network health for maintaining a seamless and responsive interaction between the Al avatar 102 and the human representative 104.The network monitoring module functions by analyzing key indicators of connection stability, such as latency, bandwidth, signal strength, and packet loss. The indicators provide a detailed snapshot of the network's performance at any given moment, allowing the network monitoring module to assess the quality and reliability of the connection. If the network monitoring module detects any anomalies such as a sudden drop in bandwidth, high latency, or an increase in packetAtorney Docket No. T00708-716-717NE-PCT loss, the module identify the anomaly as a connection failure. This continuous monitoring and analysis allow the network monitoring module to identify and react to connection issues as they develop, often before they escalate to a complete disconnection. This enables the Al avatar 102 to respond appropriately and ensure the user experience remains as smooth and uninterrupted as possible.During the session, the Al avatar 102 and the human representative 104 rely on an active and stable connection to communicate effectively. Even minor disruptions in the connectivity can affect the response of the Al avatar 102, causing delays or interruptions in information exchange. For example, if the latency exceeds a certain level or if packet loss reaches a predefined percentage, the network monitoring module recognizes this as a signal of deteriorating connection quality. By setting these thresholds, the network monitoring module can differentiate between minor fluctuations, which are often harmless, and more severe disruptions that could hinder communication.In operation 204, dispatching a first notification message 108 by the Al avatar 102 to the human representative 104 through a communication channel 110 upon detection of the connection failure. The first notification message 108 prompts the human representative 104 to provide requested information asynchronously due to the absence of a real-time connection. Upon detecting the connection failure, the Al avatar 102 initiates dispatching the first notification message 108 to the human representative 104 via the communication channel 110. The Al avatar 102 immediately triggers the first notification message 108 an automated response, which conveys to the human representative 104 that a connectivity issue has been identified, and that direct, real-time interaction is momentarily unavailable.The first notification message 108 is crafted to be clear, direct, and informative, providing essential guidance on how the human representative 104 should proceed. The first notification message 108 prompts the human representative 104 to respond in the asynchronous manner, meaning that the human representative 104 can continue the exchange by supplying requested information at their convenience rather than in a continuous, live exchange. By requesting information asynchronously, the Al avatar 102 ensures that the interaction of the user 106 with the Al avatar 102 can remain productive and timely responses are provided to the user 106.Atorney Docket No. T00708-716-717NE-PCTThe communication channel 110 is the medium through which the Al avatar 102 reaches the human representative 104. The communication channel 110 may include various forms such as email, a messaging application, or Short Messaging Service (SMS), elected based on their accessibility and reliability in conditions with connectivity issues. The communication channel 110 is designed to remain operational even when the real-time connection is lost, thus providing a fail-safe route for the Al avatar 102 to relay inputs such as the queries of the user 106 to the human representative 104. By selecting the resilient communication channel 110, the Al avatar 102 ensures that the first notification message 108 will reach the human representative 104 promptly and that the human representative 104 will be able to respond in a timely manner, sustaining the interaction effectively.Upon detecting a connectivity issue, the Al avatar 102 initiates the transmission of the first notification message 108 to the human representative 104 through one or more communication channels 110. The communication channels 1 10 include a mobile application message and an email message directing the first notification message 108 to the associated mobile application and email address of the human representative 104, respectively. The communication channel 110 is selected to ensure that the human representative 104 is notified in a timely and reliable manner. The mobile application message directed the first notification message 108 to the mobile application associated with the account of the human representative 104. The mobile application is typically an extension that the human representative 104 uses to manage communications with the Al avatar 102. The mobile application serves as an effective communication channel 110 due to its capability to provide push notifications, which immediately alert the human representative 104.The email message is also directed to the email address associated with the account of the human representative 104. By sending the first notification message 108 to the email address, of the human representative 104, the Al avatar 102 ensures that the first notification message 108 can be accessed on a desktop, tablet, or any other internet-connected device that supports email. In at least one embodiment, the first notification message 108 includes information on the connectivity issue, any relevant session information required by the Al avatar 102, and guidance on how the human representative 104 can proceed asynchronously if real-time communication isAtorney Docket No. T00708-716-717NE-PCT not feasible. The combination of mobile application messages and email effectively addresses potential challenges in delivering time-sensitive information.The Al avatar 102 employs a connection monitoring algorithm designed to maintain standards of connectivity and ensure smooth, uninterrupted interaction with the human representative 104. The connection monitoring algorithm performs either continuous or interval-based checks of the network status, depending on the specific requirements of the session. The connection monitoring algorithm detects any network failure or instability that disrupts the connection. The connection monitoring algorithm tracks network latency, packet loss, and disconnection events. The latency refers to the time taken for data to travel from the Al avatar 102 to the human representative 104 and back. The packet loss refers to instances when data packets fail to reach their destination, resulting in gaps in the transmitted information. The packet loss can impact the quality of communication, causing the first notification message 108 to become incomplete or distorted.The connection monitoring algorithm quickly detects when there is complete disconnection, where the network connection drops entirely. Upon identifying the connection failure, the connection monitoring algorithm is configured to immediately trigger the dispatch of the first notification message 108. The first notification message 108 informs the human representative 104 about the detected connection issue, providing essential details on the nature and status of the network disruption. The first notification message 108 serves as an alert and also provides an essential link between the Al avatar 102 and the human representative 104, ensuring that both remain informed about the connection’s status. The first notification message 108 is sent through the communication channel 1 10, such as the mobile application message or the email, which are reliable and accessible. By dispatching the first notification message 108, the connection monitoring algorithm ensures that the human representative 104 responds asynchronously, allowing the interaction to continue without disruptions.When the connection issue is detected, the Al avatar 102 promptly dispatches the first notification message 108 to the human representative 104. The first notification message 108 is designed to inform the human representative 104 about the connectivity problem and also offer comprehensive guidance on how to navigate the reconnection process. The first notificationAtorney Docket No. T00708-716-717NE-PCT message 108 includes a step-by-step outline of how the human representative 104 can attempt to reconnect. This involves instructions on checking the network settings, restarting the communication platform, or verifying internet connectivity. For example, the Al avatar 102 may suggest that the human representative 104 switches from a Wi-Fi to a cellular network if possible or even try accessing a different network altogether. By offering practical troubleshooting steps tailored to common connectivity issues, the Al avatar 102 provides the human representative with immediate solutions to successfully reconnect.Moreover, the first notification message 108 provides information about alternate communication channel 110 through which the human representative 104 can continue to submit responses if reconnection efforts are delayed or unsuccessful. For example, the first notification message 108 may instruct the human representative 104 to submit responses via email. The first notification message 108 includes information on how to contact technical support for additional assistance if reconnection proves difficult. The Al avatar 102 identifies some issues that may require specialized support. The first notification message 108 is crafted to be clear, concise, and easily actionable, allowing the human representative 104 to follow the instructions with minimal effort. In at least one embodiment, the first notification message 108 employs bullet points or numbered lists to break down each step of the reconnection process, or key phrases may be bolded or highlighted to draw attention to critical actionsIn operation 206, receiving an asynchronous response message 112 by the Al avatar 102 from the human representative 104. The response message 112 includes information relevant to the context of the interactive session of the Al avatar 102 with the user 106 and is received via the communication channels 110 for asynchronous interaction. The Al avatar 102 receives the asynchronous response message 112 from the human representative 104 to maintain continuity within the interactive session with the user 106 when real-time connectivity is not possible. The asynchronous response message 112 enables the human representative 104 to provide information relevant to the ongoing session at their convenience. By supporting asynchronous communication, the Al avatar 102 can receive, process, and respond to the response message 112, thereby sustaining the interaction. The asynchronous response message 112 delivers information that the human representative 104 considers essential to the session. The response message 112 includes status updates, responses to questions posed earlier by the Al avatar 102,Atorney Docket No. T00708-716-717NE-PCT additional details that expand on prior discussions of the Al avatar 102 with the user 106, or specific data that enrich the context of the interaction. Since the Al avatar 102 cannot always rely on uninterrupted real-time communication, the asynchronous response message bridges potential gaps in the interaction by allowing the representative to share insights, instructions, or feedback later, thus preserving the flow of information.The response message 112 allows the Al avatar 102 to process and incorporate new information relevant to the session. Typically, each response message 112 helps to guide the Al avatar 102 in responses and decision-making processes. The Al avatar 102 parses the response message 112 to extract key details, identifies any follow-up actions needed and ensures that the information is seamlessly integrated into the ongoing interaction, creating a continuous and cohesive experience for the user 106. The interactive session is characterized by a flow of information from the Al avatar 102 to the user 106. During, the session the Al avatar 102 supports the user 106 by providing answers, collecting data from human representative 104 when Al avatar is unable to provide the answer, assisting in decision-making, or solving problems. The asynchronous response message 112 ensures that the session remains uninterrupted, even when live communication is unachievable. The relevant information may include specific instructions, contextual details, data points, or clarifications that the human representative 104 provides to the Al avatar 102 to allow, the Al avatar 102 to proceed with the session accurately. The asynchronous response message 112 is transmitted through the communication channel 110 to the Al avatar 102.In operation 208, updating a knowledge base 114 of the Al avatar 102 by parsing the received asynchronous response messagel 12, analyzing the content for relevance to the session context, and incorporating the newly received information into the knowledge base 114 to refine future interactions and responses related to similar user queries. The knowledge base 114 is a centralized collection of information that the Al avatar 102 uses to answer questions, provide guidance, and engage in interactions with the user 106. The knowledge base 114 includes data, context-specific insights, user preferences, past interactions, and any other relevant information that contributes to effective communication. Typically, the knowledge base 114 continuously evolves, as it incorporates new details and experiences with each session. Moreover, updating the knowledge base 114 ensures that the Al avatar 102 is well-informed and capable of offeringAtorney Docket No. T00708-716-717NE-PCT responses that are accurate, contextually relevant, and aligned with the expectations of the user 106. By adding information from the asynchronous response messages 112, the Al avatar 102 creates a richer, nuanced repository that supports deeper and insightful engagement with the user(s) 106.To update the knowledge base 114, the Al avatar 102 parses the received asynchronous response message 112. The parsing involves breaking down the response message 112 into core components, extracting specific details, and identifying key themes or phrases that carry relevance to the session context. The parsing allows the Al avatar 102 to understand the exact nature of the information provided by the human representative 104, such as instructions, feedback, or context-specific data. By parsing the response message 112, the Al avatar 102 can isolate the critical elements that need to be added to the knowledge base 114, ensuring that only the most pertinent information is retained. Furthermore, updating the knowledge base 114 by analyzing the content of the response message 112. The updating the knowledge base 114 involves interpreting the information within the context of the current interaction, comparing the response message 112 with existing knowledge, and evaluating its applicability to the specific session and potential future interactions. For example, if the response message 112 contains specific preferences, troubleshooting steps, or clarifications on a user query, the Al avatar 102 examines these details to see how they align with interactions.After analyzing the relevance of the content, the Al avatar 102 incorporates the newly received information into the knowledge base 114. The incorporation involves updating existing data, adding new entries, and modifying any outdated or inaccurate information. Typically, incorporating the data ensures that the knowledge base 1 14 remains a reliable source of information for the Al avatar 102. The knowledge base 114 updates the Al avatar 102 to refine future interactions and responses related to similar user queries. As the knowledge base 114 grows richer with each update, it becomes more capable of understanding user intents, recognizing recurring patterns, and delivering responses that align with the expectations and preferences of the user 106. The refinement enables the Al avatar 102 to continuously learn from each interaction, evolving its approach to ensure that it remains relevant and responsive.Moreover, incorporating new information into the knowledge base 114 also allows the Al avatar 102 to enhance contextual understanding. The contextual understanding involves recognizing theAtorney Docket No. T00708-716-717NE-PCT specifics of the user query and also the underlying needs and circumstances that may inform that query. In addition, updating the knowledge base 114 enables the Al avatar to enhance its adaptability, making it capable of handling a wide array of queries and requests. As the knowledge base 114 incorporates new and varied information, the scope of understanding of the Al avatar 102 expands, allowing it to address a broader range of user issues.Moreover, updating the knowledge base 114 involves a data processing algorithm executed by the Al avatar 102 to parse and analyze the content of the response message 112 provided by the human representative 104, extract specific information relevant to the session, and incorporate the extracted information into a structured, query-specific knowledge base 114 entry, thereby enhancing the ability of the Al avatar 102 to address similar queries with improved accuracy in future sessions. Typically, the data processing algorithm initiates by parsing and analyzing the content of the response message 112 provided by the human representative 104. The parsing involves dissecting the incoming response message 1 12 into distinct components, such as key phrases, terms, or specific instructions that relate to the ongoing session. By breaking down the response message 112 content, the data processing algorithm simplifies the information into manageable units that can be more easily assessed.Following the parsing, the data processing algorithm analyzes the parsed content by interpreting the meaning of each element and determining its relevance to the ongoing query or problem being addressed. For example, if the human representative 104 message contains troubleshooting steps or user-specific preferences, the data processing algorithm evaluates how this new data aligns with previously recorded interactions or known patterns. Once the parsing and analysis are done, the data processing algorithm extracts specific information relevant to the session. The extraction involves isolating the elements within the response message 112 that are directly applicable to the current and future performance of the Al avatar 102. The extracted information includes insights into user preferences, frequently encountered issues, particular troubleshooting methods, or common solutions that can address similar queries in the future. The extraction capabilities allow the data processing algorithm to capture and store relevant data, optimizing the knowledge base 114 by focusing on information that can enhance the response accuracy of the Al avatar 102.Atorney Docket No. T00708-716-717NE-PCTAfter extracting the relevant data, the data processing algorithm incorporates the extracted information into a structured, query-specific knowledge base 114 entry. The data processing algorithm organizes the newly acquired information into a format that the Al avatar 102 can readily access and retrieve in future sessions. Each entry within the knowledge base 114 is structured around specific query types or topics, meaning that similar queries are grouped together for quick reference. By structuring the knowledge base 114 allows the Al avatar 102 to pull relevant information quickly and efficiently to respond to user inquiries with greater accuracy. In at least one embodiment, the structured entry may include metadata such as keywords, query categories, and context tags, to enhance the ability of the Al avatar 102 to recognize and match relevant entries when addressing a similar question.In operation 210, sending by the Al avatar 102 a second notification 116 to the user 106 through the communication channel 110. The second notification 116 informs the knowledge base 114 has been successfully updated with the new information provided by the human representative 104, thereby enabling the user 106 to stay informed regarding the updated state and knowledge content of the Al avatar 102 for subsequent interactions. The second notification 116 is a specific message crafted by the Al avatar 102 to inform the user 106 about updates to the knowledge base 114. The purpose of the second notification 116 is to convey essential information about changes that have been made to the knowledge base 114 of the Al avatar 102. The second notification 116 assures that the query asked by the user 106 during the session has been incorporated as provided by the human representative 104. The second notification 116 is transmitted to the user 106 via the communication channel 110. The communication channel 110 may vary depending on user preferences, potentially including email, in-app notifications, SMS, or so forth.The second notification 116 informs the user 106 that the knowledge base 114 has been successfully updated with new information provided by the human representative 104. Each update to the knowledge base 114 refines the understanding of the Al avatar 102. By incorporating new data, the Al avatar 102 strengthens its capacity to respond accurately and contextually in future interactions. The second notification 116 enables the user 106 to stay informed regarding the updated state and knowledge base 114 of the Al avatar 102.

[0081] Below is the pseudo-code that describes a series of functions designed to manageAtorney Docket No. T00708-716-717NE-PCT sessions where the user 106 interacts with the Al avatar 102 also the Al avatar 102 maintains communication with the human representative 104 during potential network disruptions and updates the knowledge base of the Al avatar 102. function handleSession (userQuery) : if not isConnected ( ) : dispatchMessages () response = waitForHumanlnput ( ) updateKnowledgeBase (response) notifyUserOfUpdate ( ) function isConnected ( ) : return checkNetworkStatus ( ) function dispatchMessages ( ) : sendEmail ( ) sendMessageToApp ( ) function updateKnowledgeBase ( inf o ) : knowl edge Base . update ( inf o ) function notifyUserOfUpdate ( ) : sendEmailUpdate ( )The function handlesession (userQuery) manages the user session. It processes the query of the user 106 handling potential connection issues and updates the knowledge base 114 of the Al avatar 102 with new information, if not isConnected ( ) checks if the Al avatar 102 is currently connected to the network. If it isn’t, the dispatchMessages ( ) function is called to notify about the connectivity issue.The response = waitForHumanlnput ( ) function waits for response message 108 from the human representative 104 after handling any connection issues, indicating that the Al avatar 102 requires human intervention to continue processing the query of the user 106. updateKnowledgeBase (response) is used to update the knowledge base 114 of the Al avatar 102 to learn from the input from the human representative 104. The notifyUserOfUpdate ( ) sends a notification to the user 106 to inform him about the update.Atorney Docket No. T00708-716-717NE-PCTThe function isConnected ( ) determines the current network status. The return checkNetworkstatus ( ) to evaluate whether the Al avatar 102 is connected to the network.The function dispatchMessages ( ) handles the asynchronous communication required when the Al avatar 102 is not connected. The sendEmail ( ) sends an email to notify the human representative 104 about the issue and provides instructions or updates related to the session. The sendMes sageToAp ( ) sends a message through an associated mobile or web application to ensure the human representative 104 is informed through multiple communication channels 110.The function updateKnowledgeBase ( info ) integrates new information into the knowledge base 114 of the Al avatar 102. The knowiedgeBase . update ( info ) uses the provided input ( info ) to update the knowledge base 114 to ensure that the Al avatar 102 learns from the latest session and incorporates new insights for future interactions.

[0082] The function noti fyUserOfUpdate ( ) communicates with the user 106 after the knowledge base 114 has been updated. The sendEmaiiupdate ( ) sends an email such as the second notification 116 to the user 106 to inform that the knowledge base 114 has been successfully updated.

[0083] The notification handling algorithm is designed to provide the user 106 with seamless updates about changes in the knowledge base 114. The notification handling algorithm triggers the second notification 116 for the user 106 who initiated the session, ensuring that the update is relevant, personalized, and directly connected to their recent interaction. The second notification 116 is a targeted communication that informs the user 106 of the exact updates made in the knowledge base 124, based on new information provided by the human representative 104 during the session. For example, if the user 106 sought technical assistance during the session, and the human representative 104 provided new troubleshooting details that were subsequently added to the knowledge base 114, the second notification 116 outlines these specific troubleshooting steps.By deploying the notification handling algorithm, the AT avatar 102 can accurately identify when the second notification 116 is needed and ensure that the second notification 116 reaches the intended user 106 without delay. The notification handling algorithm enables the Al avatar 102 to operate at scale, handling multiple user 106 interactions and updates simultaneously whileAtorney Docket No. T00708-716-717NE-PCT maintaining individualized communication. The efficiency is important in environments, where the Al avatar 102 interacts with numerous users.Figure 3 depicts a data structure 300 for organizing data related to updating the knowledge base 114 based on the first notification message 108. The data structure 300 includes the first notification message 108 node, which stores detailed information related to id, type, content, and status of first notification message. The id is a unique identifier used to distinguish the first notification message 108. The type specifies the category or classification of the first notification message 108. The content represents the actual information contained within the first notification message 108. The status indicates the current state of the first notification message 108. The first notification message 108 relates to a question 302. The question 302 includes id, content, and status. The id is a unique identifier used to distinguish the question 302. The content represents the actual information contained within the question 302. The status indicates the current state of the question 302. The question 302 is a part of session 304. The session 304 includes id, timestamp, and status. The id is a unique identifier used to distinguish the session 304. The timestamp is a time at which the session 304 is initiated. The status indicates the current state of the session 304.The session 304 is initiated by the Al avatar 102. The Al avatar 102 includes id, name, and status. The id is a unique identifier used to distinguish the Al avatar 102. The name refers to a unique name provided to the Al avatar 102. The status indicates the current state of the Al avatar 102. The Al avatar 102 belongs to the human representative 104 and also the first notification message 108 is also sent to the human representative 104. The human representative 104 includes id, name, email and mobile. The id is a unique identifier used to distinguish the human representative 104. The name is used for identification of the human representative 104. The email is a unique address used for communication with the human representative 104. The mobile is a contact number associated with the human representative 104. The Al avatar 102 accesses the knowledge base 114. The knowledge base 114 includes id and content. The id is a unique identifier used to distinguish information from the knowledge base 114. The content refers to the information contained within the knowledge base 114. The first notification message 108 is related to the question 302 and is used to update the knowledge base 114.Atorney Docket No. T00708-716-717NE-PCTFigures 4-6 are exemplary user interfaces 400, 500, and 600 depicting the interaction of the Al avatar 102 with the human representative 104. Referring to Figure 4 depicts the user interface 400 showing the login screen titled ‘Engage with Persona’ which prompts the human representative 104 to interact with the Al avatar 102. The user interface 400 shows fields for email 402 and password 404 entry. The human representative 104 provides the credentials such as email 402 and password 404 to interact with the Al avatar 102, once provided the human representative 104 press an enter button 406. In case the human representative 104 forgot the password 404, the human representative 104 can recover the password 404 by clicking on a forgot your password tab 408.Referring to Figure 5 depicts the user interface 500, displaying persona 502 (also referred as Al avatar 102) associated with the human representative 104 upon successfully logging in. The user interface 500 displays unread notification tab 504 to display unread notifications received from the persona 502. Moreover, the user interface 500 also displays all persona tab 506 to display all the associated persona 502 to the human representative 104.Referring to Figure 6 depicts the user interface 600 showing the interaction between the persona 502 and human representative 104 upon clicking on the unread notifications received from the persona 502. The user interface 600 displays a query 602 received from the persona 502 and a response 604 provided by the human representative to the query 602. The user interface 600 allows the human representative 104 by typing in a message box 606 to provide the response 604. The human representative 104 can also provide the response 604 through a voice message by clicking on a record tab 608. Moreover, the human representative 104 can also provide the response 604 through an image by clicking on an upload image tab 610.Figure 7 is a block diagram illustrating a network environment in which an asynchronous communication management system 100 and asynchronous communication management process 200 may be practiced. Network 702 (e.g. a private wide area network (WAN) or the Internet) includes a number of networked server computer systems 704(l)-(N) that are accessible by client computer systems 706(l)-(N), where N is the number of server computer systems connected to the network. Communication between client computer systems 706(1 )-(N) and server computer systems 704(l)-(N) typically occurs over a network, such as a public switched telephone networkAtorney Docket No. T00708-716-717NE-PCT over asynchronous digital subscriber line (ADSL) telephone lines or high-bandwidth trunks, for example communications channels providing T1 or OC3 service. Client computer systems 706(l)-(N) typically access server computer systems 704(l)-(N) through a service provider, such as an internet service provider (“ISP”) by executing application specific software, commonly referred to as a browser, on one of client computer systems 706(l)-(N).Client computer systems 706(l)-(N) and / or server computer systems 704(l)-(N) are specialized computer programmed to improve conventional computer systems to implement and utilize the asynchronous communication management system 100 and asynchronous communication management process 200. The type of computer system that can be specially programmed to implement and utilize the asynchronous communication management system 100 and asynchronous communication management process 200 include a mainframe, a mini-computer, a personal computer system including notebook computers, a wireless, mobile computing device (including personal digital assistants, smart phones, and tablet computers). These computer systems are typically designed to provide computing power to one or more users, either locally or remotely. Each computer system may also include one or a plurality of input / output (“I / O”) devices coupled to the system processor to perform specialized functions. Tangible, non- transitory memories (also referred to as “storage devices”) such as hard disks, compact disk (“CD”) drives, digital versatile disk (“DVD”) drives, and magneto-optical drives may also be provided, either as an integrated or peripheral device. In at least one embodiment, the asynchronous communication management system 100 and asynchronous communication management process 200 can be implemented using code stored in a tangible, non-transient computer readable medium and executed by one or more processors. In at least one embodiment, the asynchronous communication management system 100 and asynchronous communication management process 200 can be implemented completely in hardware using, for example, logic circuits and other circuits including field programmable gate arrays.Embodiments of the asynchronous communication management system 100 and asynchronous communication management process 200 can be implemented on a computer system such as a special-purpose, special-programmed computer 800 illustrated in Figure 8. Input user device(s) 810, such as a keyboard and / or mouse, are coupled to a bi-directional system bus 818. The input user device(s) 810 are for introducing user input to the computer system and communicating thatAtorney Docket No. T00708-716-717NE-PCT user input to processor 813. The computer system of Figure 8 generally also includes a non- transitory video memory 814, non-transitory main memory 815, and non-transitory mass storage 809, all coupled to bi-directional system bus 818 along with input user device(s) 810 and processor 813. The mass storage 809 may include both fixed and removable media, such as a hard drive, one or more CDs or DVDs, solid state memory including flash memory, and other available mass storage technology. Bus 818 may contain, for example, 32 of 64 address lines for addressing video memory 814 or main memory 815. The system bus 818 also includes, for example, an n-bit data bus for transferring DATA between and among the components, such as CPU 809, main memory 815, video memory 814 and mass storage 809, where “n” is, for example, 32 or 64. Alternatively, multiplex data / address lines may be used instead of separate data and address lines.I / O device(s) 819 may provide connections to peripheral devices, such as a printer, and may also provide a direct connection to a remote server computer systems via a telephone link or to the Internet via an ISP. I / O device(s) 819 may also include a network interface device to provide a direct connection to a remote server computer systems via a direct network link to the Internet via a POP (point of presence). Such connection may be made using, for example, wireless techniques, including digital cellular telephone connection, Cellular Digital Packet Data (CDPD) connection, digital satellite data connection or the like. Examples of I / O devices include modems, sound and video devices, and specialized communication devices such as the aforementioned network interface.Computer programs and data are generally stored as code in a non-transient computer readable medium such as a flash memory, optical memory, magnetic memory, compact disks, digital versatile disks, and any other type of memory. The computer program is loaded from a memory, such as mass storage 809, into main memory 815 for execution. Computer programs may also be in the form of electronic signals modulated in accordance with the computer program and data communication technology when transferred via a network. In at least one embodiment, Java applets or any other technology is used with web pages to allow a user of a web browser to make and submit selections and allow a client computer system to capture the user selection and submit the selection data to a server computer system.Atorney Docket No. T00708-716-717NE-PCTThe processor 813, in one embodiment, is a microprocessor manufactured by Motorola Inc. of Illinois, Intel Corporation of California, or Advanced Micro Devices of California. However, any other suitable single or multiple microprocessors or microcomputers may be utilized. Main memory 815 is includes dynamic random access memory (DRAM). Video memory 814 is a dual-ported video random access memory. One port of the video memory 814 is coupled to video amplifier 816. The video amplifier 816 is used to drive the display 817. Video amplifier 816 is well known in the art and may be implemented by any suitable means. This circuitry converts pixel DATA stored in video memory 814 to a raster signal suitable for use by display 817. Display 817 is a type of monitor suitable for displaying graphic images.The computer system described above is for purposes of example only. The asynchronous communication management system 100 and asynchronous communication management process 200 may be implemented in any type of computer system or programming or processing environment. It is contemplated that the asynchronous communication management system 100 and asynchronous communication management process 200 might be run on a stand-alone computer system, such as the one described above. The asynchronous communication management system 100 and asynchronous communication management process 200 might also be run from a server computer systems system that can be accessed by a plurality of client computer systems interconnected over an intranet network. Finally, the asynchronous communication management system 100 and asynchronous communication management process 200 may be run from a server computer system that is accessible to clients over the Internet.Although embodiments have been described in detail, it should be understood that various changes, substitutions, and alterations can be made hereto without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

Atorney Docket No. T00708-716-717NE-PCTWHAT IS CLAIMED IS:

1. A method for guiding an Artificial Intelligence (Al) engine to create and operate a avatar that represents a human representative, the method comprising: executing code using one or more processors of a computer system to cause the computer system to perform operations comprising: receiving initial human representative data, the initial human representative data comprising at least one of: video, image, or audio recording representing the appearance, body structure, natural voice, and tone of the human representative; generating a prompt by a prompt generator to guide the Al engine based on the initial human representative data to generate an initial avatar; transferring the prompt to the Al engine for generating the initial avatar wherein the Al engine is guided and constrained by the prompt to: analyze the video or image with a generative algorithm to create a three- dimensional visual model of the avatar that captures physical characteristics of the human representative; process the audio recording with a voice synthesis algorithm to create a voice model that closely replicates the vocal tone, pitch, accent of the human representative; receive ongoing multimodal interaction data, the multimodal interaction data comprising at least one of text inputs, additional voice recordings, or updated image data, obtained through continuous human representative interactions on the Al guidance and control system 110, wherein the multimodal data represents real-time preferences, communication style, and current appearance of the human representative; analyzing the multimodal interaction data using a natural language processing (NLP) algorithm, wherein the NLP algorithm interprets text and audio inputs to extract human representative specificAtorney Docket No. T00708-716-717NE-PCT knowledge, emotional nuances, and behavioral patterns, and refines these based on ongoing interactions to achieve accurate contextual understanding; updating the avatar characteristics based on the ongoing multimodal interaction data, wherein the updating comprises: employing a continuous learning algorithm that evaluates the interaction patterns of the human representative, updates the behavioral responses of the avatar, and modifies the visual and vocal elements of the avatar based on extracted preferences and behavioral updates from ongoing multimodal interaction data, modifying the visual model of the avatar to reflect recent changes in the appearance of the human representative, such as hairstyle, clothing preferences, or other physical attributes based on newly captured image inputs, and adapting the vocal responses and tone of the avatar to mirror the current speech patterns, emotional cues, and intonations of the human representative based on updated voice data; displaying the dynamically updated avatar on the Al guidance and control systemAtorney Docket No. T00708-716-717NE-PCT2. The method of claim 1 wherein utilizing the generative algorithm to create the initial Avatar integrates advanced facial recognition techniques, detecting unique facial structure and biometrics, including eye shape, nose contour, and jawline of the human representative, to enhance the physical likeness of the avatar.

3. The method of claim 1 wherein the voice synthesis algorithm uses deep neural networks trained on audio samples to accurately reproduce the vocal characteristics of the human representative, including speech rhythm, pronunciation patterns, and regional accent.

4. The method of claim 1 wherein the continuous learning algorithm leverages reinforcement learning models to update the responses of the avatar by adjusting to positive or negative feedback from interactions of the human representative, refining the conversational patterns of the avatar and adaptive behaviors to align with the evolving preferences.

5. The method of claim 1 wherein the initial avatar includes specific non-verbal behavioral traits extracted from the video data, such as the natural gestures, facial expressions, or typical postures of the human representative, and incorporates the traits into the real-time interactions of the avatar.

6. The method of claim 1 wherein the NLP algorithm includes sentiment analysis tools to detect and interpret emotional cues within the voice or text inputs of the human representative, enabling the avatar to provide empathetic and contextually appropriate responses that align with the emotional state of the human representative.

7. The method of claim 1 further comprising: utilizing predictive algorithms to adjust the appearance, speech, and behavior of the avatar based on analysis of historical interaction data, enabling the avatar to anticipate and respond to expected user preferences or trends.Atorney Docket No. T00708-716-717NE-PCT8. The method of claim 1 wherein the generative algorithm and voice synthesis algorithm are configured to operate in real-time, allowing the Al engine to immediately update the visual and vocal responses during active user sessions for a seamless interactive experience.

9. The method of claim 1 wherein displaying the updated avatar on a virtual reality or augmented reality interface, enabling the user to interact with the avatar in an immersive three-dimensional environment.

10. A system for guiding an Artificial Intelligence (Al) engine for creating, personalized and dynamically adapting avatar that represents a human representative comprising: one or more processors; memory, operatively coupled to the one or more processors that when executed cause the one or more processors to perform operations comprising: executing codes using one or more processors of a computer system to cause the computer system to perform operations comprising: receiving an initial human representative data via an Al guidance and control system 110, the initial human representative data comprising at least one of: video, image, or audio recording provided by the human representative representing the appearance, body structure, natural voice, and tone of the human representative; generating a prompt by a prompt generator to guide the Al engine based on the initial human representative data to generate an initial avatar; transferring the prompt to the Al engine for generating the initial avatar wherein the Al engine is configured to: analyze the video or image with a generative algorithm to create a three-dimensional visual model of the avatar that captures key physical characteristics of the human representative, including facial structure, skin tone, and hair characteristics, andAtorney Docket No. T00708-716-717NE-PCT process the audio recording with a voice synthesis algorithm to create a voice model that closely replicates the vocal tone, pitch, accent of the human representative; receiving ongoing multimodal interaction data by the Al engine from the human representative, the multimodal interaction data comprising at least one of text inputs, additional voice recordings, or updated image data, obtained through continuous human representative interactions on the Al guidance and control system 110, wherein the multimodal data represents real-time preferences, communication style, and current appearance of the human representative; analyzing by the Al engine the multimodal interaction data using a natural language processing (NLP) algorithm, wherein the NLP algorithm interprets text and audio inputs to extract human representative specific knowledge, emotional nuances, and behavioral patterns, and refines these based on ongoing interactions to achieve accurate contextual understanding; updating the avatar characteristics by the Al engine based on the ongoing multimodal interaction data by: employing a continuous learning algorithm that evaluates the interaction patterns of the human representative, updates the behavioral responses of the avatar, and modifies the visual and vocal elements of the avatar based on extracted preferences and behavioral updates from ongoing multimodal interaction data, modifying the visual model of the avataravatar to reflect recent changes in the appearance of the human representative, such as hairstyle, clothing preferences, or other physical attributes based on newly captured image inputs, andAtorney Docket No. T00708-716-717NE-PCT adapting the vocal responses and tone of the avataravatar to mirror the current speech patterns, emotional cues, and intonations of the human representative based on updated voice data; displaying the dynamically updated avatar on the Al guidance and control system 110.Atorney Docket No. T00708-716-717NE-PCT11. The system of claim 10 wherein utilizing the generative algorithm to create the initial avatar integrates advanced facial recognition techniques, detecting unique facial structure and biometrics, including eye shape, nose contour, and jawline of the human representative, to enhance the physical likeness of the avatar.

12. The system of claim 10 wherein the voice synthesis algorithm uses deep neural networks trained on audio samples to accurately reproduce the vocal characteristics of the human representative, including speech rhythm, pronunciation patterns, and regional accent.

13. The system of claim 10 wherein the continuous learning algorithm leverages reinforcement learning models to update the responses of the avatar by adjusting to positive or negative feedback from interactions of the human representative, refining the conversational patterns of the avatar and adaptive behaviors to align with the evolving preferences.

14. The system of claim 10 wherein the initial avatar includes specific non-verbal behavioral traits extracted from the video data, such as the natural gestures, facial expressions, or typical postures of the human representative, and incorporates the traits into the real-time interactions of the avatar.

15. The system of claim 10 wherein the NLP algorithm includes sentiment analysis tools to detect and interpret emotional cues within the voice or text inputs of the human representative, enabling the avatar to provide empathetic and contextually appropriate responses that align with the emotional state of the human representative.

16. The system of claim 10 further comprising utilizing predictive algorithms to adjust the appearance, speech, and behavior of the avatar based on analysis of historical interaction data, enabling the avatar to anticipate and respond to expected user preferences or trends.Atorney Docket No. T00708-716-717NE-PCT17. The system of claim 10 wherein the generative algorithm and voice synthesis algorithm are configured to operate in real-time, allowing the Al engine to immediately update the visual and vocal responses during active user sessions for a seamless interactive experience.

18. The system of claim 10 wherein displaying the updated avatar on a virtual reality or augmented reality interface, enabling the user to interact with the avatar in an immersive three-dimensional environment.

19. A method for guiding an Artificial Intelligence (Al) engine to generate a response by an Al avatar comprising: executing code using one or more processors of a computer system to cause the computer system to perform operations comprising: facilitating communication between a user and the Al avatar via an Al guidance and control system to receive user inputs; receiving real-time inputs from a human representative associated with the Al avatar through a mobile application, wherein the mobile application is in communication with the Al guidance and control system; generating a prompt by a prompt generator to guide the Al engine to enable dynamic interaction and continuous learning of the Al avatar to generate the response; transferring the prompt to the Al engine to generate the response and provide the generated response to the Al avatar, wherein the Al engine is configured to: ingest user inputs from the Al guidance and control system and real-time inputs from the human representative; process and analyze the user inputs and real-time inputs using a natural language processing (NLP) algorithm to interpret the content;Atorney Docket No. T00708-716-717NE-PCT update a knowledge base of the Al avatar based on the analyzed user inputs and real-time inputs; processing the analyzed user inputs and real-time inputs multimodally using a multimodal processing engine on a cloud-based server, wherein the multimodal processing engine processes text, voice, and other input types from the user and the human representative; and providing personalized responses to the user by the Al avatar through the Al guidance and control system, wherein the responses are based on the updated knowledge base.

20. The method of claim 19 further comprising: interacting with the user through text-based interaction channels, including messaging platforms, web-based chat interfaces, or mobile applications.

21. The method of claim 19 further comprising: interacting with the user through voice-based interaction channels, including voice assistants, smart speakers, or other audio input devices.

22. The method of claim 19 wherein, receiving real-time inputs from the human representative in various formats, including text, voice, and multimedia inputs through the mobile application.

23. The method of claim 19 further comprising storing historical user interactions in the cloud-based server, and analyzing the interactions between the user and the Al avatar using machine learning algorithms to improve responses of the Al avatar. tooAtorney Docket No. T00708-716-717NE-PCT24. The method of claim 19 wherein, notifying the human representative via an alert on the mobile application when new user interactions require the real-time inputs for the Al avatar.

25. The method of claim 19 wherein, processing feedback from the user through in the Al guidance and control system to refine the knowledge base and improve future interactions of the Al avatar.

26. The method of claim 19 wherein, prioritizing real-time inputs from the human representative over historical data when updating the knowledge base to ensure the responses of the Al avatar reflect most current information.

27. The method of claim 19 wherein, structuring the knowledge base hierarchically to allow certain types of real-time inputs of the human representative to override previously stored data in the knowledge base.

28. A system for guiding an Artificial Intelligence (Al) engine to generate a response by an Al avatar comprising: one or more processors; memory, operatively coupled to the one or more processors, that stored code that when executed causes the one or more processors to perform operations comprising: executing codes using one or more processors of a computer system to cause the computer system to perform operations comprising: facilitating communication between a user and the Al avatar via an Al guidance and control system to receive user inputs; receiving real-time inputs from a human representative associated with the Al avatar through a mobile application, wherein the mobileAtorney Docket No. T00708-716-717NE-PCT application is in communication with the Al guidance and control system; generating a prompt by a prompt generator to guide the Al engine to enable dynamic interaction and continuous learning of the Al avatar to generate the response; transferring the prompt to the Al engine to generate the response and provide the generated response to the Al avatar, wherein the Al engine is configured to: ingest user inputs from the Al guidance and control system and real-time inputs from the human representative; process and analyze the user inputs and real-time inputs using a natural language processing (NLP) algorithm to interpret the content; update a knowledge base of the Al avatar based on the analyzed user inputs and real-time inputs; processing the analyzed user inputs and real-time inputs multimodally using a multimodal processing engine on a cloud-based server, wherein the multimodal processing engine processes text, voice, and other input types from the user and the human representative; and providing personalized responses to the user by the Al avatar through the Al guidance and control system, wherein the responses are based on the updated knowledge base.

29. The system of claim 28 further comprising: interacting with the user through text-based interaction channels, including messaging platforms, web-based chat interfaces, or mobile applications.Atorney Docket No. T00708-716-717NE-PCT30. The system of claim 28 further comprising: interacting with the user through voice-based interaction channels, including voice assistants, smart speakers, or other audio input devices.

31. The system of claim 28 wherein, receiving real-time inputs from the human representative in various formats, including text, voice, and multimedia inputs through the mobile application.

32. The system of claim 28 further comprising storing historical user interactions in the cloud-based server, and analyzing the interactions between the user and the Al avatar using machine learning algorithms to improve responses of the Al avatar.

33. The system of claim 28 wherein, notifying the human representative via an alert on the mobile application when new user interactions require the real-time inputs for the Al avatar.

34. The system of claim 28 wherein, processing feedback from the user through in the Al guidance and control system to refine the knowledge base and improve future interactions of the Al avatar.

35. The system of claim 28 wherein, prioritizing real-time inputs from the human representative over historical data when updating the knowledge base to ensure the responses of the Al avatar reflect most current information.

36. The system of claim 28 wherein, structuring the knowledge base hierarchically to allow certain types of real-time inputs of the human representative to override previously stored data in the knowledge base.Atorney Docket No. T00708-716-717NE-PCT37. A method for managing asynchronous communication between an Al avatar and a human representative upon detection of a network failure to establish a real-time connection comprising: executing codes using one or more processors of a computer system to cause the computer system to perform operations comprising: detecting a connection failure during an interactive session of the Al avatar with a user, wherein the Al avatar continuously monitors a network status associated with the session with the human representative and identifies an inability to establish or maintain a direct, real-time connection; dispatching a first notification message by the Al avatar to the human representative through a communication channel upon detection of the connection failure, wherein the first notification message prompting the human representative to provide requested information asynchronously due to the absence of a real-time connection; receiving an asynchronous response message by the Al avatar from the human representative, wherein the response message includes information relevant to the context of the interactive session of the Al avatar with the user and is received via the communication channels for asynchronous interaction; updating a knowledge base of the Al avatar by parsing the received asynchronous response message, analyzing the content for relevance to the session context, and incorporating the newly received information into the knowledge base to refine future interactions and responses related to similar user queries; and sending by the Al avatar a second notification to the user through the communication channel, wherein the second notification informs the knowledge base has been successfully updated with the new information provided by the human representative, thereby enabling the user to stay informed regarding the updated state and knowledge content of the Al avatar for subsequent interactions.Atorney Docket No. T00708-716-717NE-PCT38. The method of claim 37 wherein the first notification message is transmitted through the communication channels comprising: a mobile application message directed to a mobile application associated with the account of the human representative, and an email message directed to an email address associated with the account of the human representative.

39. The method of claim 37 wherein the connection failure is detected by a network monitoring module configured to continuously track connectivity status between the Al avatar and the human representative during the session.

40. The method of claim 37 wherein the Al avatar uses a connection monitoring algorithm that performs continuous or interval -based network status checks by: detecting a connection failure when network latency, packet loss, or disconnection exceeds a predefined threshold, and subsequently triggering the dispatch of the first notification message to ensure prompt and reliable communication with the human representative regarding the connection status.

41. The method of claim 37 wherein the knowledge base update involves a data processing algorithm executed by the Al avatar to: parse and analyze the content of the response message provided by the human representative, extract specific information relevant to the session, and incorporate the extracted information into a structured, query-specific knowledge base entry, thereby enhancing the ability of the Al avatar to address similar queries with improved accuracy in future sessions.Atorney Docket No. T00708-716-717NE-PCT42. The method of claim 37 wherein the notification handling algorithm deployed by the Al avatar triggers the second notification to dispatch specifically to the user who initiated the session, the second notification conveying details on the updated knowledge base entries, enabling the user to track and verify the updated information.

43. The method of claim 37, wherein the first notification message dispatched by the Al avatar includes detailed guidance to the human representative on reconnection including information on how the human representative can reconnect, submit responses via different channels, or contact support for additional assistance.

44. The method of claim 37 wherein the data processing algorithm employed by the Al avatar includes: context analysis to validate the relevance of the response provided by the human representative to the original query context, and categorizing and indexing the response within the knowledge base to ensure that the update is specifically aligned with the query topic for use in similar future interactions.

45. A system for managing asynchronous communication between an Al avatar and a human representative upon detection of a network failure to establish a real-time connection comprising: one or more processors; memory, operatively coupled to the one or more processors that when executed cause the one or more processors to perform operations comprising: executing codes using one or more processors of a computer system to cause the computer system to perform operations comprising: detecting a connection failure during an interactive session of the Al avatar with a user, wherein the Al avatar continuously monitors a network status associated with the session with the human representative and identifies an inability to establish or maintain a direct, real-time connection;Atorney Docket No. T00708-716-717NE-PCT dispatching a first notification message by the Al avatar to the human representative through a communication channel upon detection of the connection failure, wherein the first notification message prompting the human representative to provide requested information asynchronously due to the absence of a real-time connection; receiving an asynchronous response message by the Al avatar from the human representative, wherein the response message includes information relevant to the context of the interactive session of the Al avatar with the user and is received via the communication channels for asynchronous interaction; updating a knowledge base of the Al avatar by parsing the received asynchronous response message, analyzing the content for relevance to the session context, and incorporating the newly received information into the knowledge base to refine future interactions and responses related to similar user queries; and sending by the Al avatar a second notification to the user through the communication channel, wherein the second notification informs the knowledge base has been successfully updated with the new information provided by the human representative, thereby enabling the user to stay informed regarding the updated state and knowledge content of the Al avatar for subsequent interactions.

46. The system of claim 45 wherein the first notification message is transmitted through the communication channels comprising: a mobile application message directed to a mobile application associated with the account of the human representative, and an email message directed to an email address associated with the account of the human representative.Atorney Docket No. T00708-716-717NE-PCT47. The system of claim 45 wherein the connection failure is detected by a network monitoring module configured to continuously track connectivity status between the Al avatar and the human representative during the session.

48. The system of claim 45 wherein the Al avatar uses a connection monitoring algorithm that performs continuous or interval -based network status checks by: detecting a connection failure when network latency, packet loss, or disconnection exceeds a predefined threshold, and subsequently triggering the dispatch of the first notification message to ensure prompt and reliable communication with the human representative regarding the connection status.

49. The system of claim 45 wherein the knowledge base update involves a data processing algorithm executed by the Al avatar to: parse and analyze the content of the response message provided by the human representative, extract specific information relevant to the session, and incorporate the extracted information into a structured, query-specific knowledge base entry, thereby enhancing the ability of the Al avatar to address similar queries with improved accuracy in future sessions.Atorney Docket No. T00708-716-717NE-PCT50. The system of claim 45 wherein the notification dehandling algorithm deployed by the Al avatar triggers the second notification to dispatch specifically to the user who initiated the session, the second notification conveying details on the updated knowledge base entries, enabling the user to track and verify the updated information.

51. The system of claim 45 wherein the first notification message dispatched by the Al avatar includes detailed guidance to the human representative on reconnection including information on how the human representative can reconnect, submit responses via different channels, or contact support for additional assistance.

52. The system of claim 45 wherein the data processing algorithm employed by the Al avatar includes: context analysis to validate the relevance of the response provided by the human representative to the original query context, and categorizing and indexing the response within the knowledge base to ensure that the update is specifically aligned with the query topic for use in similar future interactions.

Images