Decoding based on data reliability
By using the trained model to process the bits and reliability indicators of the encoded data, the problem of uncorrectable packet decoding is solved, and higher data transmission reliability and efficiency are achieved.
CN120226268APending Publication Date: 2025-06-27QUALCOMM INC
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202380080774.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-12-02
- Filing Date
- 2023-09-26
- Publication Date
- 2025-06-27
AI Technical Summary
Technical Problem
In data communication, it is difficult for the prior art to effectively decode encoded data affected by errors, especially uncorrectable packets, resulting in high uncertainty and error rates in data transmission.
Method used
The decoded output is generated by processing bits representing the time series data of the encoded data and an indicator of its reliability using one or more trained models. The model generates an estimated version of the decoded data based on the input bits and reliability indicators, taking into account data reliability.
Benefits of technology
The decoding capability of uncorrectable packets is improved, the error rate is reduced, and the reliability and efficiency of data transmission are enhanced.
✦ Generated by Eureka AI based on patent content.
Abstract
An apparatus includes one or more processors configured to obtain a first bit representing first encoded time series data, and to obtain a first indicator of reliability of the first bit. The one or more processors are further configured to process the input using the one or more trained models to generate a decoded output. The input is based at least in part on the first bit and the first indicator, and the decoded output represents decoded time series data.
Need to check novelty before this filing date? Find Prior Art