Dell products l.p. (20240303534). METHOD, DEVICE, AND COMPUTER PROGRAM PRODUCT FOR PROCESSING DATA simplified abstract
Contents
METHOD, DEVICE, AND COMPUTER PROGRAM PRODUCT FOR PROCESSING DATA
Organization Name
Inventor(s)
METHOD, DEVICE, AND COMPUTER PROGRAM PRODUCT FOR PROCESSING DATA - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240303534 titled 'METHOD, DEVICE, AND COMPUTER PROGRAM PRODUCT FOR PROCESSING DATA
The method described in the abstract involves iteratively improving a model by training it on subsets of a sample set of question-answer pairs.
- Determining a first sample subset in an initial sample set using an initial model.
- Generating a first model by training the initial model with the first sample subset.
- Determining a second sample subset in the first sample subset using the first model.
- Generating a second model by training the first model with the second sample subset.
- Determining a third sample subset of the initial sample set using the second model.
- Generating a third model by training the second model with the third sample subset.
Potential Applications: - This method can be applied in machine learning and artificial intelligence systems to improve model performance. - It can be used in natural language processing tasks such as question-answering systems.
Problems Solved: - This method addresses the challenge of improving model accuracy and performance over multiple iterations. - It helps in refining models based on feedback from different sample subsets.
Benefits: - Enhanced model accuracy and performance. - Efficient iterative model training process. - Adaptability to changing data patterns.
Commercial Applications: Title: Iterative Model Training Method for Enhanced Performance in AI Systems This technology can be utilized in developing advanced AI systems for various industries such as customer service, healthcare, and finance. It can improve the accuracy and efficiency of chatbots, recommendation systems, and data analysis tools.
Questions about Iterative Model Training Method: 1. How does this method compare to traditional model training approaches?
- The iterative approach allows for continuous improvement of the model by training on different sample subsets, leading to enhanced performance over time.
2. What are the key factors to consider when determining sample subsets for training?
- Factors such as diversity, representativeness, and relevance of the samples play a crucial role in selecting subsets for training.
Original Abstract Submitted
a method includes: determining a first sample subset in an initial sample set by an initial model based on the initial sample set, wherein the initial sample set comprises a plurality of question-answer pairs, each of the plurality of question-answer pairs comprising a question and an answer; generating a first model by training the initial model with the first sample subset; determining a second sample subset in the first sample subset by the first model based on the first sample subset; generating a second model by training the first model with the second sample subset; determining, in response to at least one of the second sample subset and the second model satisfying a corresponding predetermined condition, a third sample subset of the initial sample set by the second model based on the initial sample set; and generating a third model by training the second model with the third sample subset.
