METHOD OF BUILDING AND OPERATING DECODING STATUS AND PREDICTION SYSTEM
A method of building a decoding status prediction system is provided. Firstly, plural read records are collected during read cycles of a flash memory. Then, the plural read records are classified into read records with a first read result and read records with a second read result. Then, a first portion of the read records with the first read result are divided into K0 groups according to a clustering algorithm, and a second portion of the read records with the second read result are divided into K1 groups according to the clustering algorithm. Then, the read records of the K0 groups and the K1 groups are used to train prediction models. Consequently, K0×K1 prediction models are generated. Then, the prediction models are combined as a prediction database.
1 . A method of building a decoding status prediction system, the method comprising steps of:
collecting plural read records during read cycles of a flash memory;
classifying the plural read records into read records with a first read result and read records with a second read result;
dividing a first portion of the read records with the first read result into K0 groups according to a clustering algorithm
dividing a second portion of the read records with the second read result into K1 groups according to the clustering algorithm;
training the prediction models with the read records of the K0 groups and the K1 groups, so that K0×K1 prediction models are generated; and
collecting all the prediction models as a prediction database.
2 . The method as claimed in claim 1 , wherein each of the plural read records contains plural parameters and one of the first read result and the second read result.
3 . The method as claimed in claim 1 , wherein the plural parameters include at least one of a block erase count, a read voltage, an environment temperature, a data program time, an address information and a data retention time of the flash memory, wherein the first read result indicates a successful decoding result, and the second read result indicates a failed decoding result.
4 . The method as claimed in claim 1 , wherein the clustering algorithm is a k-means clustering algorithm.
5 . The method as claimed in claim 1 , further comprising a step of selecting a first group from the K0 groups and selecting a second group from the K1 groups, wherein after the read records in the first group and the second group are used to train a prediction model, a first prediction model of the plural prediction models is obtained.
6 . The method as claimed in claim 5 , wherein the first prediction model is a binary classifier.
7 . The method as claimed in claim 6 , wherein the binary classifier is a random forest classifier.
8 . An operating method of a prediction system for use in a flash memory, the prediction system comprising a prediction database, the prediction database containing K0×K1 prediction models that are obtained by using records in K0 groups and K1 groups to train the prediction models, the operating method comprising steps of:
calculating K0 central points of the K0 groups, and calculating K1 central points of the K1 groups;
receiving a reference point;
calculating K0 distances between the reference point and the central points of the K0 groups, and calculating K1 distances between the reference point and the K1 central points of the K1 groups;
selecting K prediction models from the prediction database according to the (K0+K1) distances; and
inputting the reference point into the K prediction models, so that a prediction result is obtained.
9 . The operating method as claimed in claim 8 , wherein the prediction models corresponding to the distances between the reference point and the (K0+K1) groups, the shorter of the distances the higher of the priority to be selected from the prediction database as the K prediction models.
10 . The operating method as claimed in claim 8 , wherein after the reference point is inputted into a first prediction model of the K prediction models, a probability of a first read result and a probability of a second read result are obtained.
11 . The operating method as claimed in claim 10 , wherein after the probability of the first read result is divided by the probability of the second read result, a probability ratio of the first prediction model is obtained.
12 . The operating method as claimed in claim 11 , wherein a sign of the sum of log probability ratios obtained by the K prediction models represents the prediction result.
13 . The operating method as claimed in claim 11 , further comprising steps of:
collecting plural read records during read cycles of the flash memory; and
allocating the read records into the corresponding (K0+K1) groups, so that the central points of the K0 groups and the central points of the K1 groups are changed.
14 . The operating method as claimed in claim 11 , further comprising steps of:
collecting plural read records and corresponding read result during read cycles of the flash memory;
allocating the read records into the corresponding (K0+K1) groups; and
using the read records of the K0 groups and the K1 groups to train predication models, so that K0×K1 updated prediction models are generated.