Flash memory particle classification method, electronic device and computer readable storage medium

Abstract

The present application discloses a flash memory particle classification method, an electronic device, and a computer-readable storage medium, the method comprising: obtaining flash memory particles to be screened, determining the number of bad blocks corresponding to bad blocks in all blocks of the flash memory particles; obtaining a first original bit error rate corresponding to reading and writing data in a normal block of the flash memory particles, and a second original bit error rate corresponding to writing data in a normal block of the flash memory particles after a preset waiting time; wherein, the flash memory particle operation time is collected during the test; based on the flash memory particle operation time, the first original bit error rate, and the second original bit error rate, determining the block classification corresponding to the normal block; based on the number of bad blocks corresponding to the bad blocks in the flash memory particles and the block classification corresponding to the normal blocks, determining the particle classification of the flash memory particles. In the above manner, the present application can improve the accuracy of flash memory particle classification.

Description

Technical Field

[0001] The present application relates to the technical field of storage device analysis, and in particular to a flash memory particle grading method, an electronic device, and a computer-readable storage medium. Background Art

[0002] Flash memory, as a key component of storage devices, has been widely used in the market. Consequently, the quality and reliability of flash memory chips are receiving increasing attention. However, conventional flash memory chip screening methods typically use read and write operations to screen out high- and low-performance flash memory chips, resulting in low flash memory chip grading accuracy. Therefore, improving the accuracy of flash memory chip grading has become an urgent issue. Summary of the Invention

[0003] The main technical problem solved by the present application is to provide a flash memory particle grading method, an electronic device and a computer-readable storage medium, which can improve the accuracy of flash memory particle grading.

[0004] To solve the above technical problems, the first aspect of the present application provides a flash memory particle grading method, comprising: obtaining flash memory particles to be screened, and determining the number of bad blocks corresponding to bad blocks in all blocks of the flash memory particles; obtaining a first raw bit error rate corresponding to reading and writing data in normal blocks of the flash memory particles, and a second raw bit error rate corresponding to writing data in the normal blocks of the flash memory particles and after a preset waiting time; wherein, the flash memory particle operation time is collected during the test; based on the flash memory particle operation time, the first raw bit error rate and the second raw bit error rate, the block grade corresponding to the normal block is determined; based on the number of bad blocks corresponding to the bad blocks in the flash memory particles and the block grade corresponding to the normal block, the particle grade of the flash memory particles is determined.

[0005] To solve the above technical problems, the second aspect of the present application provides an electronic device, which includes: a memory and a processor coupled to each other, wherein the memory stores program data, and the processor calls the program data to execute the method described in the first aspect above.

[0006] In order to solve the above technical problems, the third aspect of the present application provides a computer-readable storage medium on which program data is stored. When the program data is executed by a processor, the method described in the first aspect is implemented.

[0007] The above scheme obtains flash memory particles to be screened, and determines bad blocks and their corresponding number of bad blocks from all blocks of the flash memory particles. A first raw bit error rate corresponding to the normal blocks of the flash memory particles during the process of reading and writing data, and a second raw bit error rate corresponding to the normal blocks of the flash memory particles after the data is written and the data is retained for a preset waiting time are obtained, wherein the flash memory particle operation time is collected during the test. Based on the obtained flash memory particle operation time, the first raw bit error rate, and the second raw bit error rate, the normal blocks are graded, thereby comprehensively considering the flash memory particle operation time, data reading and writing performance, and data retention performance of the normal blocks to obtain an accurate block grade corresponding to the normal blocks. Based on the number of bad blocks corresponding to the bad blocks in the flash memory particles and the block grade corresponding to the normal blocks, the flash memory particles are graded, thereby comprehensively considering the information related to the bad blocks and normal blocks in the flash memory particles, finely grading the flash memory particles, determining the particle grade corresponding to the flash memory particles, and improving the accuracy of the flash memory particle grading. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. Among them:

[0009] Figure 1 This is a flow chart of an embodiment of a flash memory particle classification method of the present application;

[0010] Figure 2 This is a flow chart of another embodiment of the flash memory particle classification method of the present application;

[0011] Figure 3 This is a schematic structural diagram of an embodiment of the electronic device of the present application;

[0012] Figure 4 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them, and different implementation methods can be adaptively combined. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0014] The flash memory particle grading method provided in the present application is used to screen and grade flash memory particles, and its corresponding execution subject is a processing unit capable of performing data processing.

[0015] It can be understood that the essence of flash memory particle screening is the screening of storage units (target); among them, target is the largest unit of flash memory particle packaging, and there are several chips (die) in a target; among them, die is the unit that can perform concurrent operations in the target, and a die contains several blocks (Block); Block is the minimum erase unit of flash memory particles, and a block contains several data pages (Page); Page is the minimum read and write operation unit of flash memory particles; Raw Bit Error Rate (RBER) is an important indicator for measuring the reliability of flash memory particles. The raw bit error rate refers to the bit error rate that occurs during data transmission or storage before error correction code processing.

[0016] See also Figure 1 , Figure 1 1 is a flow chart of an embodiment of a flash memory particle classification method of the present application, the method comprising:

[0017] S101: Obtain a flash memory cell to be screened, and determine the number of bad blocks corresponding to bad blocks in all blocks of the flash memory cell.

[0018] Specifically, a flash memory particle to be screened is obtained, and bad blocks and their corresponding bad block numbers are determined from all blocks of the flash memory particle, wherein the blocks other than the bad blocks in the flash memory particle are normal blocks.

[0019] In some implementation scenarios, flash memory particles to be screened are obtained, writing results of all blocks in the flash memory particles when writing data are determined, and abnormal bad blocks and their corresponding bad block numbers are obtained from the writing results.

[0020] In some implementation scenarios, flash memory particles to be screened are obtained, reading results of all blocks in the flash memory particles when reading data are determined, and abnormal bad blocks and their corresponding bad block numbers are obtained from the reading results.

[0021] Optionally, the flash memory particles are configured with a lowest bad block level, a highest bad block level, and at least one intermediate bad block level between the lowest bad block level and the highest bad block level, based on the number of bad blocks. When a flash memory particle corresponds to the highest bad block level, the particle level of the flash memory particle is configured as the lowest level particle. The lowest bad block level corresponds to the lowest number of bad blocks, and the highest bad block level corresponds to the highest number of bad blocks. In other words, when a flash memory particle is configured with the highest bad block level, the particle level of the flash memory particle can be directly configured as the lowest level particle.

[0022] In a specific implementation scenario, the number of bad blocks corresponding to bad blocks in a flash memory particle is obtained, a bad block relationship table is constructed based on the flash memory particle, the number of bad blocks of each die in the flash memory particle is recorded, and the first bad block threshold corresponding to a single die is preset to R1 and the second bad block threshold is preset to R2, where R2 is greater than R1. If the number of bad blocks of each die in the flash memory particle is less than R1, it is classified as a GOOD-level particle, which is the lowest bad block level; if the number of bad blocks of each die in the flash memory particle is less than R2, and there is at least one die with a number of bad blocks greater than or equal to R1, it is classified as a NOMAL-level particle, which is an intermediate bad block level; if there is at least one die with a number of bad blocks greater than or equal to R2, it is classified as a BAD-level particle; only GOOD and NOMAL-level particles enter the subsequent testing process, and BAD-level particles can be directly set to the lowest level particle. The bad block threshold and the number of intermediate bad block levels can be customized and adaptively set, and this application does not impose specific restrictions on this.

[0023] S102: Obtain a first raw bit error rate corresponding to reading and writing data in a normal block of the flash memory particle, and a second raw bit error rate corresponding to writing data in the normal block of the flash memory particle after a preset waiting time; wherein, the flash memory particle operation time is collected during the test process.

[0024] Specifically, a first original bit error rate corresponding to a normal block of a flash memory particle during the process of reading and writing data is obtained, as well as a second original bit error rate corresponding to a normal block of a flash memory particle after retaining data for a preset waiting time after writing data, wherein the operation time of the flash memory particle is collected during the test process.

[0025] In some implementation scenarios, data is written to the data page of the normal block at a preset temperature, and the written data in the normal block is read at a preset temperature, and a first raw bit error rate corresponding to reading and writing the data is determined, and data is written to the data page of the normal block at a preset temperature, and a corresponding second raw bit error rate is obtained after a preset waiting time, and during the test process, the writing time and reading time of the data page are counted as the operation time of the flash memory particles.

[0026] In some implementation scenarios, data is written to a data page of a normal block at a first test temperature, and the written data in the normal block is read at a second test temperature to determine a first raw bit error rate corresponding to reading and writing the data, wherein the first test temperature is higher than the second test temperature corresponding to a temperature difference, data is written to a data page of a normal block at the first test temperature, and the corresponding second raw bit error rate is obtained after a preset waiting time, and during the test process, the write time and read time of the data page, as well as the erase time of the normal block are counted as the operation time of the flash memory particles.

[0027] S103: Determine a block level corresponding to the normal block based on the flash memory particle operation time, the first raw bit error rate, and the second raw bit error rate.

[0028] Specifically, based on the obtained flash memory particle operation time, the first raw bit error rate and the second raw bit error rate, the normal blocks are graded, so as to comprehensively consider the flash memory particle operation time, data reading and writing effect and data retention effect of the normal blocks to obtain the accurate block grade corresponding to the normal blocks.

[0029] Optionally, the test process corresponds to multiple test rounds. In different test rounds, the proportion of data pages with data written in the normal block is different from each other. In multiple test rounds, multiple rounds of testing can be performed in a decreasing or increasing or randomly set manner according to the proportion of data pages with written data to all data pages, thereby covering the data reading and writing effects and data retention effects of normal blocks under different data page loads.

[0030] In some implementation scenarios, based on the obtained flash memory particle operation time, normal blocks that do not meet the time requirements and normal blocks that meet the time requirements are determined, the block level of the normal blocks that do not meet the time requirements is set to the lowest level block, and the normal blocks that meet the time requirements are used as blocks to be confirmed. Based on the obtained first raw bit error rate and second raw bit error rate, the block level corresponding to the blocks to be confirmed is determined.

[0031] In some implementation scenarios, based on the obtained flash memory particle operation time, the test score corresponding to the normal block is determined, based on the obtained first raw bit error rate, the data read and write score corresponding to the normal block is determined, based on the obtained second raw bit error rate, the data retention score corresponding to the normal block is determined, and based on the test score, data read and write score and data retention score, the block grade corresponding to the normal block is determined.

[0032] In one specific implementation scenario, the testing process corresponds to multiple test rounds, and normal blocks correspond to multiple levels of block classification. Normal blocks that fail to meet the time requirements in any test round are set as the lowest-level blocks, and normal blocks that meet the time requirements in all test rounds are set as pending blocks. The first raw bit error rate corresponds to multiple increasing classification thresholds, and multiple preset waiting times correspond to respective second raw bit error rates. A pending block whose first raw bit error rate does not exceed the minimum classification threshold in all test rounds, and whose corresponding second raw bit error rate does not exceed the preset threshold at the longest preset waiting time, is set as the highest-level block. A pending block whose first raw bit error rate does not exceed the maximum classification threshold in all test rounds, and whose corresponding second raw bit error rate does not exceed the preset threshold at the shortest preset waiting time, is set as an intermediate-level block. A pending block whose first raw bit error rate exceeds the maximum classification threshold in any test round, or whose second raw bit error rate exceeds the preset threshold at the shortest preset waiting time in any test round, is set as the lowest-level block. Among them, for the intermediate-level blocks, more specific level divisions can be set based on specific scenarios in different implementation scenarios, and this application does not impose specific restrictions on this.

[0033] S104: Determine the particle level of the flash memory particle based on the number of bad blocks corresponding to the bad blocks and the block levels corresponding to the normal blocks in the flash memory particle.

[0034] Specifically, the flash memory particles are graded based on the number of bad blocks corresponding to the bad blocks in the flash memory particles and the block grade corresponding to the normal blocks. Thus, the flash memory particles are finely graded by integrating the information related to the bad blocks and normal blocks in the flash memory particles, and the particle grade corresponding to the flash memory particles is determined, thereby improving the accuracy of the flash memory particle grading.

[0035] In some implementation scenarios, the grading score of the flash memory particle is determined based on the block grading corresponding to the normal blocks in the flash memory particle, and the grading score is adjusted based on the number of bad blocks corresponding to the bad blocks in the flash memory particle, so as to determine the particle grading of the flash memory particle based on the adjusted grading score.

[0036] In some implementations, each block level corresponds to a score. A first block score is determined based on the scores corresponding to the block levels of all normal blocks in the flash memory cell. A second block score is determined based on the number of bad blocks in the flash memory cell, where the second block score is negatively correlated with the number of bad blocks. The flash memory cell's level is determined based on the first and second block scores.

[0037] The above scheme obtains flash memory particles to be screened, and determines bad blocks and their corresponding number of bad blocks from all blocks of the flash memory particles. A first raw bit error rate corresponding to the normal blocks of the flash memory particles during the process of reading and writing data, and a second raw bit error rate corresponding to the normal blocks of the flash memory particles after the data is written and the data is retained for a preset waiting time are obtained, wherein the flash memory particle operation time is collected during the test. Based on the obtained flash memory particle operation time, the first raw bit error rate, and the second raw bit error rate, the normal blocks are graded, thereby comprehensively considering the flash memory particle operation time, data reading and writing performance, and data retention performance of the normal blocks to obtain an accurate block grade corresponding to the normal blocks. Based on the number of bad blocks corresponding to the bad blocks in the flash memory particles and the block grade corresponding to the normal blocks, the flash memory particles are graded, thereby comprehensively considering the information related to the bad blocks and normal blocks in the flash memory particles, finely grading the flash memory particles, determining the particle grade corresponding to the flash memory particles, and improving the accuracy of the flash memory particle grading.

[0038] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of another embodiment of the flash memory particle classification method of the present application, the method comprising:

[0039] S201: Obtain a flash memory cell to be screened, and determine the number of bad blocks corresponding to bad blocks in all blocks of the flash memory cell.

[0040] Specifically, a flash memory particle to be screened is obtained, and bad blocks and their corresponding bad block numbers are determined from all blocks of the flash memory particle, wherein the blocks other than the bad blocks in the flash memory particle are normal blocks.

[0041] It should be noted that the flash memory particles are set with a lowest bad block level, a highest bad block level, and at least one intermediate bad block level between the lowest bad block level and the highest bad block level according to the number of bad blocks. When the flash memory particle corresponds to the highest bad block level, the particle level of the flash memory particle is set to the lowest level particle.

[0042] It can be understood that the lowest bad block level corresponds to the least number of bad blocks, and the highest bad block level corresponds to the most number of bad blocks. Only flash memory particles corresponding to the lowest bad block level and the middle bad block level enter the testing process.

[0043] It should be noted that the testing process involves multiple test rounds, and the proportion of data pages written to normal blocks varies across different test rounds. This allows for the performance of normal blocks in data read / write and data retention under varying data page loads to be measured across multiple test rounds. Steps S202-S203 are executed in each test round.

[0044] S202: writing data to a corresponding proportion of data pages in a normal block at a data read and write test temperature, and reading the written data in the normal block at the data read and write test temperature to determine a first raw bit error rate corresponding to the reading and writing of the data.

[0045] Specifically, a data read / write test temperature is obtained, data is written to a corresponding proportion of data pages in a normal block at the data read / write test temperature, and the written data in the normal block is read at the data read / write test temperature to determine a first raw bit error rate corresponding to the data read / write process. The data read / write test temperature corresponds to the operating environment of the flash memory particles, thereby simulating actual operating conditions.

[0046] In some implementation scenarios, the data read and write test temperature is divided into a first test temperature and a second test temperature, and the first test temperature and the second test temperature have a temperature difference with opposite positive and negative properties compared to the preset temperature. Writing data to a corresponding proportion of data pages of a normal block at the data read and write test temperature, and reading the written data in the normal block at the data read and write test temperature, and determining a first raw bit error rate corresponding to the reading and writing of the data, includes: writing data to a corresponding proportion of data pages of a normal block at the first test temperature, and reading the written data in the normal block at the second test temperature, writing data to a corresponding proportion of data pages of a normal block at the second test temperature, and reading the written data in the normal block at the first test temperature, and determining the first raw bit error rate corresponding to the reading and writing of the data.

[0047] Specifically, the preset temperature corresponds to room temperature, and one of the first test temperature and the second test temperature is higher than room temperature, while the other is lower than room temperature. Therefore, the first test temperature and the second test temperature correspond to the upper and lower limits of the rated operating temperature of the flash memory particles, thereby better testing the read and write capabilities of normal blocks over a wide temperature range.

[0048] For ease of explanation, it is assumed that the first test temperature is higher than the second test temperature, and the proportion of data pages used to write data in the current test round is determined. Data is written to the corresponding proportion of data pages in the normal block at the first test temperature, and the data written in the normal block is read at the second test temperature, thereby realizing a scenario simulation of high-temperature writing and low-temperature reading. Data is written to the corresponding proportion of data pages in the normal block at the second test temperature, and the data written in the normal block is read at the first test temperature, thereby realizing a scenario simulation of low-temperature writing and high-temperature reading. The first raw bit error rate corresponding to reading and writing data is determined under more stringent temperature conditions, thereby improving the accuracy of the first raw bit error rate when used to feedback data reading and writing effects.

[0049] S203: Writing data to a corresponding proportion of data pages in the normal block at a data retention test temperature, and obtaining a corresponding second original bit error rate after a preset waiting time; wherein the data retention test temperature is higher than a preset temperature, and the preset waiting time is divided into a first waiting time and a second waiting time of different durations.

[0050] Specifically, the data retention test temperature is usually higher than room temperature, thereby simulating the process of reading data after long-term storage at room temperature with higher efficiency. Data is written to a corresponding proportion of data pages in the normal block at the data retention test temperature, and the corresponding second original bit error rate is obtained after the first waiting time and the second waiting time, respectively, to determine the data retention effect of the normal block under different time lengths.

[0051] Optionally, the first waiting time and the second waiting time match the activation level of the flash memory particles, thereby better verifying the data retention capability.

[0052] It is understandable that the flash memory particle operation time is also collected during the test process, wherein the flash memory particle operation time generally includes the read time and write time corresponding to the data page and the erase time corresponding to the normal block.

[0053] S204: Determine a block level corresponding to the normal block based on the flash memory particle operation time, the first raw bit error rate, and the second raw bit error rate.

[0054] Specifically, based on the obtained flash memory particle operation time, the first raw bit error rate and the second raw bit error rate, the normal blocks are graded, so as to comprehensively consider the flash memory particle operation time, data reading and writing effect and data retention effect of the normal blocks to obtain the accurate block grade corresponding to the normal blocks.

[0055] In some implementation scenarios, based on the flash memory particle operation time obtained in each test round, the lowest-level block among all normal blocks and the blocks to be confirmed other than the lowest-level block are determined; wherein the flash memory particle operation time of the lowest-level block exceeds a time threshold; based on the first raw bit error rate obtained in each test round, and the second raw bit error rate corresponding to the first waiting time and the second waiting time obtained in each test round, respectively, the block level corresponding to the block to be confirmed is determined.

[0056] Specifically, the flash memory particle operation time obtained in each test round is compared with the time threshold, and based on the comparison results, all normal blocks are divided into lowest-level blocks and blocks to be confirmed outside the lowest-level blocks, thereby reducing the number of blocks to be confirmed and setting normal blocks with longer operation time as lowest-level blocks.

[0057] Furthermore, based on the first raw bit error rate obtained in each test round, and the second raw bit error rates corresponding to the first waiting time and the second waiting time obtained in each test round, the blocks to be confirmed are graded to determine the block grade corresponding to the blocks to be confirmed. The first raw bit error rate can be set with different grade thresholds, so that multiple grade standards can be set for both the data read and write test and the data retention test, thereby facilitating more accurate block grade division.

[0058] It can be understood that the operation time of the flash memory particles includes the reading time and writing time corresponding to the data page and the erasing time corresponding to the normal block; among which, the erasing time of the block to be confirmed and the reading time and writing time corresponding to the data page of the block to be confirmed do not exceed the corresponding time threshold.

[0059] Specifically, the erase time starts when the erase command is sent to the flash memory particle and stops when the flash memory particle returns the erase completion signal. Similarly, similar operations are performed on the write and read time timings of the data pages. The erase time of the block to be confirmed in each test round, as well as the read time and write time corresponding to the data page of the block to be confirmed, do not exceed the corresponding time thresholds, thereby utilizing the flash memory particle operation time to efficiently screen normal blocks.

[0060] It should be noted that the first raw bit error rate corresponds to a first threshold and a second threshold that increase in sequence, the first waiting time is greater than the second waiting time, and the second raw bit error rate corresponds to a third threshold. Determining the block level corresponding to the block to be confirmed based on the first raw bit error rate obtained in each test round, and the second raw bit error rates corresponding to the first waiting time and the second waiting time obtained in each test round, includes: obtaining a first proportion of data pages whose first raw bit error rate does not exceed the first threshold, and a second proportion of data pages whose first raw bit error rate is between the first threshold and the second threshold in each test round; determining the block level corresponding to the block to be confirmed based on the first proportion and the second proportion obtained in each test round, and the second raw bit error rates corresponding to the first waiting time and the second waiting time obtained in each test round, and their corresponding third thresholds.

[0061] Specifically, a first proportion of data pages whose first original bit error rate does not exceed the first threshold in each test round is obtained, and a second proportion of data pages whose first original bit error rate is between the first threshold and the second threshold in each test round is obtained, and a second proportion of data pages whose first original bit error rate is between the first threshold and the second threshold in each test round is obtained, in the data pages where data has been written. Thus, the blocks to be confirmed are graded according to the first proportion and the second proportion obtained in each test round, and the size of the second original bit error rates corresponding to the first waiting time and the second waiting time obtained in each test round respectively compared with the third threshold, to obtain a block grade with multiple gradients corresponding to the blocks to be confirmed.

[0062] For ease of explanation, it is taken as an example that the first original bit error rate corresponds to a first threshold θ1 and a second threshold θ2 which increase in sequence, and the second original bit error rate corresponds to a third threshold θ3.

[0063] Regarding the determination of the highest-level block, for a single block to be confirmed, if the first original bit error rate of all written data pages in each test round does not exceed the first threshold θ1, and the second original bit error rate of all written data pages does not exceed the third threshold θ3 when the first waiting time is placed, then the corresponding block to be confirmed is determined to be a first-level block, that is, the highest-level block.

[0064] Regarding the determination of the block second only to the highest level, for a single block to be confirmed, if the first raw bit error rate of all written data pages in each test round does not exceed the second threshold θ2 and the data pages that exceed the first threshold θ1, the second proportion of all data pages in the block to be confirmed does not exceed the proportion threshold P1, and when the second waiting time is placed, the second raw bit error rate of all its written data pages does not exceed the third threshold θ3, then the corresponding block to be confirmed is determined to be a secondary block, that is, an intermediate-level block.

[0065] Regarding the determination of blocks higher than the lowest level, for a single block to be confirmed, if it only satisfies the first raw bit error rate of the written data pages in one test round that does not exceed the second threshold θ2 and exceeds the first threshold θ1, the second proportion of all data pages in the block to be confirmed does not exceed the proportion threshold P1, and when the second waiting time is placed, the second raw bit error rate of all its written data pages does not exceed the third threshold θ3, then the corresponding block to be confirmed is determined to be a third-level block, that is, an intermediate-level block.

[0066] Regarding the determination of the lowest-level block, if a block to be confirmed does not meet the above three conditions, the corresponding block to be confirmed is determined to be a fourth-level block, that is, the lowest-level block.

[0067] S205: Determine the particle level of the flash memory particle based on the number of bad blocks corresponding to the bad blocks and the block levels corresponding to the normal blocks in the flash memory particle.

[0068] Specifically, the flash memory particles are graded based on the number of bad blocks corresponding to the bad blocks in the flash memory particles and the block grade corresponding to the normal blocks. Thus, the flash memory particles are finely graded by integrating the information related to the bad blocks and normal blocks in the flash memory particles to determine the particle grade corresponding to the flash memory particles.

[0069] In some implementation scenarios, the initial classification of the flash memory particles is determined based on the ratio of the number of normal blocks corresponding to each block classification in the flash memory particles to all normal blocks; the initial classification of the flash memory particles is adjusted based on the number of bad blocks corresponding to the bad blocks in the flash memory particles to obtain the particle classification of the flash memory particles.

[0070] Specifically, the ratio of the number of normal blocks corresponding to each block level in the flash memory particles to all normal blocks is obtained, and the flash memory particles are divided into initial levels only related to the performance of normal blocks based on the corresponding ratio, thereby improving the accuracy of the initial level.

[0071] Furthermore, based on the number of bad blocks corresponding to the bad blocks in the flash memory particles, the initial classification of the flash memory particles is adjusted to determine the final particle classification of the flash memory particles, so that the particle classification is evaluated in combination with multiple dimensions to obtain a particle classification with higher accuracy.

[0072] For ease of explanation, taking the four levels corresponding to particle classification as an example, if the proportion of the number of level one blocks in a certain flash memory particle relative to the total number of all normal blocks of the flash memory particle exceeds the first ratio threshold β1, then the initial classification of the flash memory particle is considered to be a level one particle; if the proportion of the number of level two blocks in a certain flash memory particle relative to the total number of all normal blocks of the flash memory particle exceeds the second ratio threshold β2, then the initial classification of the particle is considered to be a level two particle; if the proportion of the number of level three blocks in a certain flash memory particle relative to the total number of all normal blocks of the flash memory particle exceeds the third ratio threshold β3, then the initial classification of the particle is considered to be a level three particle; in other cases, it is classified as a level four particle.

[0073] It should be noted that, based on the number of bad blocks corresponding to the bad blocks in the flash memory particles, the initial classification of the flash memory particles is adjusted to obtain the particle classification of the flash memory particles, including: in response to the initial classification of the flash memory particles being the highest-level particles, and the flash memory particles being provided with an intermediate bad block classification, the initial classification of the flash memory particles is adjusted based on the intermediate bad block classification to obtain the particle classification of the flash memory particles.

[0074] Specifically, when the initial classification of the flash memory particles is the highest-level particles and the flash memory particles are set with intermediate bad block classification, the initial classification of the flash memory particles is adjusted based on the intermediate bad block classification, so that the flash memory particle classification is corrected by integrating the number of bad blocks, and the particle classification of the corresponding flash memory particles is lowered, thereby improving the standard of the highest-level particles and meeting application scenarios with high quality and reliability requirements for flash memory particles.

[0075] In this embodiment, flash memory particles to be screened are obtained, bad blocks and their corresponding bad block counts are determined from all blocks in the flash memory particles, and only normal blocks are tested. This testing process corresponds to multiple test rounds, and the proportion of data pages with data written to normal blocks varies from test round to test round. Thus, during these multiple test rounds, the data read / write performance and data retention performance of normal blocks under different data page loads are covered. The accurate block classification corresponding to the normal blocks is obtained by combining the flash memory particle operation time, data read / write performance, and data retention performance of the normal blocks in each test round. Flash memory particles are classified based on the number of bad blocks corresponding to the bad blocks in the flash memory particles and the block classification corresponding to the normal blocks. This, combined with information related to the bad blocks and normal blocks in the flash memory particles, allows for fine classification of the flash memory particles, determines the particle classification corresponding to the flash memory particles, and improves the accuracy of the flash memory particle classification.

[0076] See also Figure 3 , Figure 3 This is a structural diagram of an embodiment of an electronic device of the present application. The electronic device 30 includes a memory 301 and a processor 302 coupled to each other, wherein the memory 301 stores program data (not shown in the figure), and the processor 302 calls the program data to implement the method in any of the above embodiments. For an explanation of the relevant content, please refer to the detailed description of the above method embodiments, which will not be repeated here.

[0077] See also Figure 4 , Figure 4 This is a structural diagram of an embodiment of a computer-readable storage medium of the present application. The computer-readable storage medium 40 stores program data 400. When the program data 400 is executed by the processor, the method in any of the above embodiments is implemented. For an explanation of the relevant content, please refer to the detailed description of the above method embodiments, which will not be repeated here.

[0078] It should be noted that the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of this embodiment.

[0079] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0080] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the various implementation methods of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0081] The above description is merely an implementation method of the present application and does not limit the scope of protection of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the scope of protection of the present application.

Claims

1. A flash memory particle classification method, characterized in that: The method comprises: Obtaining the flash memory particles to be screened, and determining the number of bad blocks corresponding to the bad blocks in all blocks of the flash memory particles; Obtaining a first original bit error rate corresponding to reading and writing data in a normal block of the flash memory particle, and a second original bit error rate corresponding to writing data in the normal block of the flash memory particle after a preset waiting time; wherein, the operation time of the flash memory particle is collected during the test; Determine a block level corresponding to the normal block based on the flash memory particle operation time, the first raw bit error rate, and the second raw bit error rate; Determining the particle classification of the flash memory particle based on the number of bad blocks corresponding to the bad blocks in the flash memory particle and the block classification corresponding to the normal blocks; The test process corresponds to a plurality of test rounds, and in different test rounds, the proportions of data pages in which the data are written in the normal blocks are different from each other; The obtaining of the first original bit error rate corresponding to reading and writing data in the normal block of the flash memory particle, and the second original bit error rate corresponding to writing data in the normal block of the flash memory particle after a preset waiting time, comprises performing the following steps for each test round: Writing data into a corresponding proportion of data pages of the normal block at a data read and write test temperature, and reading the written data in the normal block at the data read and write test temperature to determine the first original bit error rate corresponding to the reading and writing of data; Data is written into a corresponding proportion of data pages of the normal block at a data retention test temperature, and the corresponding second original bit error rate is obtained after the preset waiting time; wherein the data retention test temperature is higher than a preset temperature, and the preset waiting time is divided into a first waiting time and a second waiting time with different durations.

2. The flash memory particle classification method according to claim 1, characterized in that: The data reading and writing test temperature is divided into a first test temperature and a second test temperature, and the first test temperature and the second test temperature have a temperature difference with opposite positive and negative properties compared with the preset temperature; The step of writing data into a corresponding proportion of data pages of the normal block at a data read and write test temperature, and reading the written data in the normal block at the data read and write test temperature to determine the first original bit error rate corresponding to the reading and writing of data includes: Writing data to a corresponding proportion of data pages of the normal block at the first test temperature, and reading the written data in the normal block at the second test temperature; writing data to a corresponding proportion of data pages of the normal block at the second test temperature, and reading the written data in the normal block at the first test temperature, and determining the first raw bit error rate corresponding to reading and writing data.

3. The flash memory particle classification method according to claim 1, characterized in that: The determining, based on the flash memory particle operation time, the first raw bit error rate, and the second raw bit error rate, a block level corresponding to the normal block includes: Based on the flash memory particle operation time obtained in each test round, determine the lowest-level block among all the normal blocks and the blocks to be confirmed other than the lowest-level block; wherein the flash memory particle operation time of the lowest-level block exceeds a time threshold; The block level corresponding to the block to be confirmed is determined based on the first original bit error rate obtained in each test round and the second original bit error rates corresponding to the first waiting time and the second waiting time respectively obtained in each test round.

4. The flash memory particle classification method according to claim 3, characterized in that: The flash memory particle operation time includes the read time and write time corresponding to the data page and the erase time corresponding to the normal block; wherein the erase time of the block to be confirmed, and the read time and write time corresponding to the data page of the block to be confirmed do not exceed the corresponding time threshold.

5. The flash memory particle classification method according to claim 3, characterized in that: The first original bit error rate corresponds to a first threshold and a second threshold that increase in sequence, the first waiting time is greater than the second waiting time, and the second original bit error rate corresponds to a third threshold; The determining, based on the first original bit error rate obtained in each test round and the second original bit error rate corresponding to the first waiting time and the second waiting time respectively obtained in each test round, the block level corresponding to the block to be confirmed includes: Obtaining a first proportion of data pages whose first original bit error rate does not exceed the first threshold in each test round, and a second proportion of data pages whose first original bit error rate is between the first threshold and the second threshold; The block grade corresponding to the block to be confirmed is determined based on the first ratio and the second ratio obtained in each test round, and the second original bit error rate corresponding to the first waiting time and the second waiting time obtained in each test round and the corresponding third threshold.

6. The flash memory particle classification method according to claim 1, characterized in that: The determining the particle classification of the flash memory particle based on the number of bad blocks corresponding to the bad blocks in the flash memory particle and the block classification corresponding to the normal blocks includes: Determining an initial classification of the flash memory particles based on a ratio of the number of normal blocks corresponding to each block classification in the flash memory particles to all the normal blocks; Based on the number of bad blocks corresponding to the bad blocks in the flash memory particles, the initial classification of the flash memory particles is adjusted to obtain the particle classification of the flash memory particles.

7. The flash memory particle classification method according to claim 6, characterized in that: The flash memory particles are provided with a lowest bad block level, a highest bad block level, and at least one intermediate bad block level between the lowest bad block level and the highest bad block level according to the number of bad blocks, and when the flash memory particles correspond to the highest bad block level, the particle level of the flash memory particles is set to the lowest level particle; The step of adjusting the initial classification of the flash memory particles based on the number of bad blocks corresponding to the bad blocks in the flash memory particles to obtain the particle classification of the flash memory particles includes: In response to the initial classification of the flash memory particles being the highest level particles and the flash memory particles being provided with the intermediate bad block classification, the initial classification of the flash memory particles is adjusted based on the intermediate bad block classification to obtain the particle classification of the flash memory particles.

8. An electronic device, characterized in that: include: A memory and a processor coupled to each other, wherein the memory stores program data, and the processor calls the program data to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having program data stored thereon, characterized in that: When the program data is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images