US-20260127802-A1 - VIRTUAL AVATAR EVOLUTION SYSTEM BASED ON AI LEARNING AND OBSERVATION AND METHOD THEREOF

US20260127802A1US 20260127802 A1US20260127802 A1US 20260127802A1US-20260127802-A1

Abstract

A virtual avatar evolution system based on AI learning and observation and a method thereof are disclosed. In the system, when a virtual avatar triggers an conversation event, speech of the virtual avatar is continuously recorded to generate a complete conversational speech, and the complete conversational speech is converted into a complete conversation message via a speech-to-text technology, then the complete conversation message is used as new training data for re-training a pre-trained language model; the complete conversation message is input into the personality analysis model to obtain real-person personality data, and the virtual personality data of the virtual avatar is dynamically adjusted based on the real-person personality data, thereby achieving the technical effect of enhancing the interaction compatibility of the virtual avatar.

Inventors

Chuan-Cheng Chiu
Ta-Wei Yen
Qiu-Long JIANG

Assignees

SQ Technology (Shanghai) Corporation
INVENTEC CORPORATION

Dates

Publication Date: 20260507
Application Date: 20250114
Priority Date: 20241101

Claims (10)

1 . A virtual avatar evolution system based on AI learning and observation, comprising: a non-transitory computer-readable storage medium, configured to store computer readable instruction, a personality analysis model, a virtual personality data and a language model corresponding to a virtual avatar, wherein the personality analysis model and the language model are pre-trained machine learning models; and a hardware processor, electrically connected to the non-transitory computer-readable storage medium, and configured to execute the computer readable instructions to operate: loading the personality analysis model, the virtual personality data and the language model corresponding to the virtual avatar; when detecting that the virtual avatar triggers a conversation event, continuously recording speech of the virtual avatar to generate complete conversational speech, and converting the complete conversational speech into a complete conversation message through a speech-to-text technology; using the complete conversation message as new training data, and inputting the new training data into the pre-trained language model for retraining the language model; and inputting the complete conversation message into the personality analysis model to output real-person personality data, and dynamically adjusting the virtual personality data of the virtual avatar based on the real-person personality data.
2 . The virtual avatar evolution system based on AI learning and observation according to claim 1 , wherein the language model is re-trained through a fine-tuning technology, the new training data is pre-processed, hyperparameters are then set for fine-tuning for retraining the language model, wherein the hyperparameters at least comprise a learning rate and a batch size.
3 . The virtual avatar evolution system based on AI learning and observation according to claim 1 , wherein the language model is retrained through incremental learning technology in which the language model is adjusted based on the new training data and a gradient descent algorithm, and a memory-augmented neural network is used to store history learning content during training to prevent the language model from forgetting past learning content.
4 . The virtual avatar evolution system based on AI learning and observation according to claim 1 , wherein the personality analysis model comprises a support vector machine, a decision tree, and a deep learning model for characteristic extraction and classification, the personality analysis model is configured to infer personality characteristics based on the complete conversation message to output the personality characteristics as the real-person personality data, and the personality analysis model allows receiving at least one feedback opinion to adjust weights thereof as a basis for optimization.
5 . The virtual avatar evolution system based on AI learning and observation according to claim 1 , wherein each of the real-person personality data and the virtual personality data comprises characteristic parameters having a personality characteristic, a conversational style, a decision mode, and a interaction manner, each of the characteristic parameters corresponding to a characteristic weight, and one of linear weighting adjustment, adaptive adjustment, weighted average, or direct replacement is used to dynamically adjust the virtual personality data of the virtual avatar based on the real-person personality data.
6 . A virtual avatar evolution method based on AI learning and observation, wherein the virtual avatar evolution method is executed by a hardware processor and comprises: loading a personality analysis model, a virtual personality data and a language model corresponding to a virtual avatar, wherein the personality analysis model and the language model are pre-trained machine learning models; when detecting that the virtual avatar triggers a conversation event, continuously recording speech of the virtual avatar to generate a complete conversational speech, and converting the complete conversational speech into a complete conversation message through a speech-to-text technology; using the complete conversation message as new training data, and inputting the new training data into the pre-trained language model to retrain the language model; and inputting the complete conversation message to the personality analysis model to output real-person personality data, and dynamically adjusting the virtual personality data of the virtual avatar based on the real-person personality data.
7 . The virtual avatar evolution method based on AI learning and observation according to claim 6 , wherein the language model is re-trained through a fine-tuning technology, the new training data is pre-processed, hyperparameters are then set for fine-tuning for retraining the language model, wherein the hyperparameters at least comprise a learning rate and a batch size.
8 . The virtual avatar evolution method based on AI learning and observation according to claim 6 , wherein the language model is retrained through incremental learning technology in which the language model is adjusted based on the new training data and a gradient descent algorithm, and a memory-augmented neural network is used to store history learning content during training to prevent the language model from forgetting past learning content.
9 . The virtual avatar evolution method based on AI learning and observation according to claim 6 , wherein the personality analysis model comprises a support vector machine, a decision tree, and a deep learning model for characteristic extraction and classification, the personality analysis model is configured to infer personality characteristics based on the complete conversation message to output the personality characteristics as the real-person personality data, and the personality analysis model allows receiving at least one feedback opinion to adjust weights thereof as a basis for optimization.
10 . The virtual avatar evolution method based on AI learning and observation according to claim 6 , wherein each of the real-person personality data and the virtual personality data comprises characteristic parameters having a personality characteristic, a conversational style, a decision mode, and a interaction manner, each of the characteristic parameters corresponding to a characteristic weight, and one of linear weighting adjustment, adaptive adjustment, weighted average, or direct replacement is used to dynamically adjust the virtual personality data of the virtual avatar based on the real-person personality data.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an evolution system and a method thereof, and more particularly to a virtual avatar evolution system based on AI learning and observation and a method thereof. 2. Description of the Related Art In recent years, with the widespread and rapid development of virtual technology, various related applications have emerged in great numbers. Among these applications, a virtual avatar is the most common. Generally, an existing virtual avatar typically interacts with a user using fixed behavior patterns, for example, conversation messages of the virtual avatar are pre-set. When a user interacts with a virtual avatar, the virtual avatar responds based on the pre-configured conversation messages, such as the behavior of non-player characters (NPCs) in games. However, while the existing method allows interaction with users, it often results in a rigid interaction manner and fails to provide the users with a satisfactory interaction experience. Thus, the existing virtual avatar suffers from insufficient interactivity. For this reason, some companies have proposed a method of incorporating natural language processing techniques to generate natural language through understanding, to make the dialog of a virtual avatar no longer rigid. However, while this method allows a virtual avatar to avoid repetitive dialog, it may fail to resonate with the user, for example, in a condition that a user is introverted but the virtual avatar's dialog is highly extroverted, the virtual avatar may make user feel uneasy or uncomfortable. Conversely, when a user is extroverted, but the virtual avatar behaves very introverted, it can also make the user feel uncomfortable. Therefore, this method may reduce the willingness for interaction or communication due to personality differences between the user and the virtual avatar. In other words, this method has the problem of poor interaction compatibility with between a user and a virtual avatar. According to above-mentioned contents, what is needed is to develop an improved solution to solve the problem of poor interaction compatibility with a user and a virtual avatar. SUMMARY OF THE INVENTION An objective of the present invention is to disclose a virtual avatar evolution system based on AI learning and observation and a method thereof, to solve the problem of poor interaction compatibility with a user and a virtual avatar. To achieve the objective, the present invention discloses a virtual avatar evolution system based on AI learning and observation, the system includes a non-transitory computer-readable storage medium and a hardware processor. The non-transitory computer-readable storage medium is configured to store computer readable instruction, a personality analysis model, a virtual personality data and a language model corresponding to a virtual avatar, wherein the personality analysis model and the language model are pre-trained machine learning models. The hardware processor is electrically connected to the non-transitory computer-readable storage medium, and configured to execute the computer readable instructions to perform operations of: loading the personality analysis model, the virtual personality data and the language model corresponding to the virtual avatar; when detecting that the virtual avatar triggers a conversation event, continuously recording speech of the virtual avatar to generate complete conversational speech, and converting the complete conversational speech into a complete conversation message through a speech-to-text technology; using the complete conversation message as new training data, and inputting the new training data into the pre-trained language model for retraining the language model; inputting the complete conversation message into the personality analysis model to output real-person personality data, and dynamically adjusting the virtual personality data of the virtual avatar based on the real-person personality data. To achieve the objective, the present invention discloses a virtual avatar evolution method based on AI learning and observation, the virtual avatar evolution method is executed by a hardware processor and includes steps of: loading a personality analysis model, a virtual personality data and a language model corresponding to a virtual avatar, wherein the personality analysis model and the language model are pre-trained machine learning models; when detecting that the virtual avatar triggers a conversation event, continuously recording speech of the virtual avatar to generate a complete conversational speech, and converting the complete conversational speech into a complete conversation message through a speech-to-text technology; using the complete conversation message as new training data, and inputting the new training data into the pre-trained language model to retrain the language model; inputting the complete conversation message to the personalit