Data storage method and system based on artificial intelligence accelerator

Abstract

The invention belongs to the technical field of information, and provides a data storage method and system based on an artificial intelligence accelerator, and the method comprises the steps: carrying out the analysis of a feature index, obtaining a feature index secondary value, carrying out the further analysis of the feature index secondary value, obtaining a feature performance value, and carrying out the comparison of the feature performance value and a feature performance threshold value. Further analyzing the to-be-stored data, obtaining a key data block quantity value and an information entropy over-limit value by analyzing and processing the information entropy value, performing weighted ratio processing on the key data block quantity value and the information entropy over-limit value to obtain a key performance value, and screening the to-be-stored data in the data set according to an access frequency. The high-frequency data block number proportion and the access frequency deviation ratio are obtained, the high-frequency data block number proportion and the access frequency deviation ratio are subjected to weighted summation to obtain a data access value, the key performance value and the data access value are subjected to combined analysis, a to-be-stored data sequence table is generated, and the to-be-stored data is distributed.

Description

Technical Field

[0001] The present invention belongs to the field of information technology, and specifically relates to a data storage method and system based on an artificial intelligence accelerator. Background Art

[0002] With the advent of the big data era, the demand for data storage has increased dramatically, placing higher demands on storage efficiency and accuracy. Traditional data storage methods have performance bottlenecks when processing large-scale data, making it difficult to meet the requirements of real-time and efficiency. At the same time, storage systems in existing technologies often lack intelligent management and optimization mechanisms, resulting in inefficient use of storage resources and increased business risks.

[0003] In the prior art, traditional monitoring tools and methods are relied upon, focusing on basic monitoring of storage hardware and clusters. However, the prior art lacks real-time acquisition and analysis of response data of storage units, and is unable to more accurately identify performance anomalies. The prior art cannot accurately evaluate the storage priority and access characteristics of data, cannot generate an efficient order table of data to be stored, and cannot optimize the data storage allocation strategy.

[0004] To this end, the present invention provides a data storage method and system based on an artificial intelligence accelerator. Summary of the invention

[0005] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0006] The technical solution adopted by the present invention to solve the technical problem is: a data storage method based on artificial intelligence accelerator, comprising: Analyze the characteristic index to obtain the secondary value of the characteristic index, further analyze the secondary value of the characteristic index to obtain the characteristic performance value, and further analyze the data to be stored based on the comparison between the characteristic performance value and the characteristic performance threshold; By analyzing and processing the information entropy value, the number of key data blocks and the information entropy excess value are obtained, and the number of key data blocks and the information entropy excess value are processed by weighted ratio to obtain the key performance value; The data to be stored in the data set is screened according to the access frequency to obtain the proportion of high-frequency data blocks and the access frequency deviation ratio, and the proportion of high-frequency data blocks and the access frequency deviation ratio are weighted and summed to obtain the data access value; Combine and analyze the key performance value and the data access value to generate a sequence table of data to be stored, and allocate the data to be stored based on the sequence table of data to be stored; As a further technical solution of the present invention, the characteristic performance value is obtained by: Count the number of unqualified feature extractions, and perform ratio processing on the number of unqualified feature extractions and the total number of feature extractions to obtain the unqualified feature extraction ratio; Sum up all the minor difference ratios of the characteristic indicators and take the average to obtain the minor deviation value of the characteristic indicator; The feature extraction failure ratio is marked as BHG, and the feature index minor deviation value is marked as YPC; The feature extraction unqualified ratio BHG and the feature index minor deviation value YPC are processed by data, and the formula The characteristic performance value BX is calculated, where s1 and s2 are both preset proportional coefficients; As a further technical solution of the present invention, the feature extraction failure ratio BHG is obtained by: The feature index secondary value is compared with the feature index secondary threshold. The specific comparison process is as follows: If the feature index secondary value is greater than the feature index secondary threshold, the feature extraction fails; If the feature index secondary value is less than or equal to the feature index secondary threshold, the feature extraction is qualified; During the data storage period, the number of times of unqualified feature extraction is counted, and the ratio of the number of unqualified feature extraction to the total number of feature extraction is processed to obtain the unqualified feature extraction ratio; As a further technical solution of the present invention, the method for obtaining the secondary deviation value YPC of the characteristic index is: Based on the unqualified characteristic index, the characteristic index secondary value and the characteristic index secondary threshold are subjected to difference processing, and the absolute value is taken to obtain the characteristic index secondary difference, the characteristic index secondary difference and the characteristic index secondary threshold are subjected to ratio processing to obtain the characteristic index secondary difference ratio, all the characteristic index secondary difference ratios are summed up and the average is taken to obtain the characteristic index secondary deviation value; As a further technical solution of the present invention, the key performance value GJ is obtained by: The key data block quantity value and the information entropy excess value are weighted ratio processed to obtain the key performance value, which is marked as GJ; As a further technical solution of the present invention, the method for obtaining the number of key data blocks and the information entropy excess value is as follows: Sum all information entropy values ​​and take the average to get the information entropy mean. Calculate the difference between the information entropy value and the information entropy mean and take the absolute value to get the information entropy difference. The information entropy difference is compared with the preset information entropy difference threshold. The specific comparison process is as follows: If the information entropy difference is less than the information entropy difference threshold, the data block is marked as a key data block; If the information entropy deviation is greater than or equal to the information entropy deviation threshold, the data block is marked as a non-critical data block; Count the number of key data blocks and calculate the ratio with the number of data blocks to obtain the value of the number of key data blocks; Based on any key information block; The information entropy difference is calculated with the information entropy difference threshold to obtain the information entropy deviation, the information entropy deviation is calculated with the information entropy mean to obtain the information entropy deviation ratio, all the information entropy deviation ratios are summed up and the average is taken to obtain the information entropy excess value; As a further technical solution of the present invention, the data access value FW is obtained in the following manner: The weighted sum of the proportion of high-frequency data blocks and the access frequency deviation ratio is taken to obtain the data access value, which is marked as FW. As a further technical solution of the present invention, the method for obtaining the proportion of the number of high-frequency data blocks and the access frequency deviation ratio is as follows: The number of data blocks exceeding the baseline in the access frequency curve is counted, and the ratio is processed with the number of data blocks to obtain the proportion of high-frequency data blocks; In the access frequency curve, data points exceeding the baseline are selected and connected to obtain a high-frequency data curve; Based on any data point of the high-frequency data curve; Perform difference processing on the access frequency and the access frequency standard value to obtain the access frequency difference, perform ratio processing on the access frequency difference and the access frequency standard value to obtain the access frequency difference ratio; Sum all access frequency difference ratios and take the average to obtain the access frequency deviation ratio; As a further technical solution of the present invention, the storage characterization value CH is obtained in the following manner: The obtained key performance value GJ and data access value FW are processed by the formula The storage characterization value CH is calculated, where a1 and a2 are both preset proportional coefficients; As a further technical solution of the present invention, a feature analysis module is provided: preprocessing the data to be stored, extracting features based on the preprocessed data to be stored to obtain feature indicators, analyzing the feature indicators to obtain feature indicator secondary values, further analyzing the feature indicator secondary values ​​to obtain feature performance values, comparing the feature performance values ​​with the feature performance threshold value, and based on the comparison result, if the feature performance value is less than the feature performance threshold value, further analyzing the data to be stored; Analysis signal processing module: Based on the analysis and processing of the information entropy value, the number of key data blocks and the information entropy excess value are obtained, and the number of key data blocks and the information entropy excess value are weighted ratio processed to obtain the key performance value, and the data to be stored in the data set are screened according to the access frequency to obtain the proportion of high-frequency data blocks and the access frequency deviation ratio, and the proportion of high-frequency data blocks and the access frequency deviation ratio are weighted summed to obtain the data access value; Storage allocation module: combines and analyzes the key performance value and the data access value, generates a sequence table of data to be stored, and allocates the data to be stored based on the sequence table of data to be stored.

[0007] The beneficial effects of the present invention are as follows: 1. Preprocess the data to be stored, extract features based on the preprocessed data to be stored, obtain feature indicators, analyze the feature indicators to obtain feature indicator secondary values, further analyze the feature indicator secondary values ​​to obtain feature performance values, compare the feature performance values ​​with the feature performance threshold values, and based on the comparison result, if the feature performance value is less than the feature performance threshold values, further analyze the data to be stored. The present invention can effectively identify data feature performance, improve the accuracy and efficiency of feature extraction, and facilitate timely discovery and processing of problems; 2. Generate the information entropy value of the data set according to the information entropy method, obtain the key data block quantity value and the information entropy excess value based on the analysis and processing of the information entropy value, perform weighted ratio processing on the key data block quantity value and the information entropy excess value to obtain the key performance value, screen the data to be stored in the data set according to the access frequency, analyze and process the access frequency of the data subset according to the screening result, obtain the high-frequency data block quantity ratio and the access frequency deviation ratio, perform weighted summation on the high-frequency data block quantity ratio and the access frequency deviation ratio to obtain the data access value, combine the key performance value with the data access value for analysis, generate a data sequence table to be stored, and allocate the data to be stored based on the data sequence table to be stored. The present invention can accurately evaluate the storage priority and access characteristics of the data by combining the key performance value and the data access value for analysis, thereby generating an efficient data sequence table to be stored and optimizing the data storage allocation strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The present invention will be further described below in conjunction with the accompanying drawings.

[0009] Figure 1 This is a flowchart of the steps of a data storage method based on an artificial intelligence accelerator according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of the steps of a data storage method based on an artificial intelligence accelerator according to Embodiment 2 of the present invention; Figure 3This is a flowchart of a data storage system based on an artificial intelligence accelerator as described in Example 4 of the present invention. DETAILED DESCRIPTION

[0010] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0011] Example 1 like Figure 1 A data storage method based on an artificial intelligence accelerator according to an embodiment of the present invention includes: Step 1: preprocess the data to be stored, extract features based on the preprocessed data to be stored, obtain feature indicators, analyze the feature indicators to obtain feature indicator secondary values, and further analyze the feature indicator secondary values ​​to obtain feature performance values; It should be noted that the characteristic indicators include access frequency and importance; In some embodiments, the data to be stored are merged to obtain a data set, the data set is cleaned, duplicate data in the data set is removed, and features of the data set are extracted using a recurrent neural network (RNN) and its variants (such as LSTM) to obtain feature indicators, which include access frequency and importance of the data to be stored; Specifically, based on any characteristic indicator; The characteristic index is compared with the standard value of the characteristic index. The specific comparison process is as follows: If the characteristic index is greater than or equal to the characteristic index standard value, no processing will be performed; If the characteristic index is less than the characteristic index standard value, it is marked as an unimportant characteristic index; Calculate the difference between the characteristic index and the characteristic index standard value, and take the absolute value to obtain the characteristic index difference; It should be noted that the characteristic index standard values ​​are set by those skilled in the art by traversing a large amount of historical data, in order to determine whether the characteristic index of the data storage process meets the requirements; Count the number of secondary indicators in the characteristic indicators, and perform ratio processing with the number of characteristic indicators to obtain the ratio of the number of secondary indicators; Based on any of the secondary indicators; Calculate the ratio of the characteristic index difference to the characteristic index standard value, process to obtain the characteristic index difference, sum up all the characteristic index differences, and take the average to obtain the characteristic index difference ratio; The secondary index quantity ratio and the characteristic index difference ratio are summed to obtain the secondary value of the characteristic index; The feature index secondary value is compared with the feature index secondary threshold. The specific comparison process is as follows: If the feature index secondary value is greater than the feature index secondary threshold, the feature extraction fails; If the feature index secondary value is less than or equal to the feature index secondary threshold, the feature extraction is qualified; During the data storage period, the number of times of unqualified feature extraction is counted, and the ratio of the number of unqualified feature extraction to the total number of feature extraction is processed to obtain the unqualified feature extraction ratio; Based on the unqualified characteristic index, the characteristic index secondary value and the characteristic index secondary threshold are subjected to difference processing, and the absolute value is taken to obtain the characteristic index secondary difference, the characteristic index secondary difference and the characteristic index secondary threshold are subjected to ratio processing to obtain the characteristic index secondary difference ratio, all the characteristic index secondary difference ratios are summed up and the average is taken to obtain the characteristic index secondary deviation value; The feature extraction failure ratio is marked as BHG, and the feature index minor deviation value is marked as YPC; The feature extraction unqualified ratio BHG and the feature index minor deviation value YPC are processed by data, and the formula The characteristic performance value BX is calculated, where s1 and s2 are both preset proportional coefficients; It should be noted that the characteristic performance value BX reflects the quantitative standard of the secondary degree of the characteristic index. The larger the characteristic performance value BX is, the smaller the characteristic extraction unqualified ratio BHG and the characteristic index secondary deviation value YPC are, and the smaller the secondary degree of the characteristic index is. Conversely, the smaller the characteristic performance value BX is, the larger the characteristic extraction unqualified ratio BHG and the characteristic index secondary deviation value YPC are, and the greater the secondary degree of the characteristic index is. Step 2: Compare the feature performance value with the feature performance threshold. Based on the comparison result, if the feature performance value is less than the feature performance threshold, further analyze the data to be stored. Specifically, the feature performance value is compared with the feature performance threshold; If the characteristic performance value is greater than or equal to the characteristic performance threshold, the data to be stored is further analyzed to generate an analysis signal; If the feature performance value is less than the feature performance threshold, the data is marked as secondary data; The technical solution of the embodiment of the present invention is: preprocessing the data to be stored, extracting features based on the preprocessed data to be stored to obtain feature indicators, analyzing the feature indicators to obtain secondary values ​​of the feature indicators, further analyzing the secondary values ​​of the feature indicators to obtain feature expression values, comparing the feature expression values ​​with the feature expression threshold values, and based on the comparison result, if the feature expression value is greater than or equal to the feature expression threshold value, further analyzing the data to be stored. The present invention can effectively identify data feature expressions, improve the accuracy and efficiency of feature extraction, and facilitate timely discovery and processing of problems.

[0012] Example 2 like Figure 2 As shown, based on Example 1, a data storage method based on an artificial intelligence accelerator according to an embodiment of the present invention includes: Step 3: Based on the analysis signal, the information entropy value of the data set is generated according to the information entropy method. Based on the analysis and processing of the information entropy value, the number of key data blocks and the information entropy excess value are obtained. The number of key data blocks and the information entropy excess value are weighted ratio processed to obtain the key performance value; It should be noted that the information entropy value reflects the uncertainty or disorder of the data. The larger the information entropy value, the more uncertain or disordered the data is. On the contrary, the smaller the information entropy value, the more certain or orderly the data is. In some embodiments, an information entropy value of each data block in the data set is obtained, and the data set is classified based on the information entropy value; Among them, data blocks represent data in a data set; Sum all information entropy values ​​and take the average to get the information entropy mean. Calculate the difference between the information entropy value and the information entropy mean and take the absolute value to get the information entropy difference. The information entropy difference is compared with the preset information entropy difference threshold. The specific comparison process is as follows: If the information entropy difference is less than the information entropy difference threshold, the data block is marked as a key data block; If the information entropy deviation is greater than or equal to the information entropy deviation threshold, the data block is marked as a non-critical data block; Count the number of key data blocks and calculate the ratio with the number of data blocks to obtain the value of the number of key data blocks; Based on any key information block; The information entropy difference is calculated with the information entropy difference threshold to obtain the information entropy deviation, the information entropy deviation is calculated with the information entropy mean to obtain the information entropy deviation ratio, all the information entropy deviation ratios are summed up and the average is taken to obtain the information entropy excess value; The key data block quantity value and the information entropy excess value are weighted ratio processed to obtain the key performance value, which is marked as GJ; It should be noted that the key performance value means: the key performance value reflects the quantitative standard of the importance of the data set. The larger the key performance value, the higher the importance of the data set. Conversely, the smaller the key performance value, the lower the importance of the data set. Step 4: Filter the data to be stored in the data set according to the access frequency, analyze and process the access frequency of the data subset according to the screening result, obtain the proportion of high-frequency data blocks and the access frequency deviation ratio, and perform weighted summation of the proportion of high-frequency data blocks and the access frequency deviation ratio to obtain the data access value; Divide the data set into several data subsets; Based on any subset of data; In some embodiments, an XY coordinate system is established, wherein the X axis is the data block order and the Y axis is the access frequency, the access frequency values ​​are marked in the coordinate system, and the data points are connected to obtain an access frequency curve; In the access frequency curve, mark the access frequency standard value as the reference point and make a reference line; The number of data blocks exceeding the baseline in the access frequency curve is counted, and the ratio is processed with the number of data blocks to obtain the proportion of high-frequency data blocks; In the access frequency curve, data points exceeding the baseline are selected and connected to obtain a high-frequency data curve; Based on any data point of the high-frequency data curve; Perform difference processing on the access frequency and the access frequency standard value to obtain the access frequency difference, and perform ratio processing on the access frequency difference and the access frequency standard value to obtain the access frequency difference ratio; Sum all access frequency difference ratios and take the average to obtain the access frequency deviation ratio; The weighted sum of the proportion of high-frequency data blocks and the access frequency deviation ratio is taken to obtain the data access value, which is marked as FW. It should be noted that the data access value reflects the quantitative standard of the frequency of data set access. The higher the data access value, the higher the data set access frequency. Conversely, the lower the data access value, the lower the data set access frequency. The data access value is compared with the data access threshold. The specific comparison process is as follows: If the data access value is greater than or equal to the data access threshold, the data subset is frequently accessed and marked as hot data; If the data access value is less than the data access threshold, the data subset is accessed infrequently and marked as cold data; The additional classification criteria for hot data and cold data are: From the time dimension, data within a specified time range is marked as hot data, and data outside of a specified time range is marked as cold data. The specified time range includes three months, five months, and twelve months. Step 5: Combine and analyze the key performance value and the data access value to generate a sequence table of data to be stored, and allocate the data to be stored based on the sequence table of data to be stored; Specifically, the obtained key performance value GJ and data access value FW are processed, and the formula The storage characterization value CH is calculated, where a1 and a2 are both preset proportional coefficients; In some embodiments, the data to be stored are sorted in descending order according to the storage characterization value CH to generate a storage order table; dividing the data storage unit into a secondary storage unit and a primary storage unit; According to the comparison result of the characteristic performance value, the secondary data is stored in the secondary storage unit, and according to the storage order table, the data is sequentially stored in the primary storage unit; Step 6: Obtain the access frequency value of the data to be stored in real time, re-obtain the characteristic performance value according to the real-time access frequency value, and detect the data to be stored according to the comparison result between the characteristic performance value and the characteristic performance threshold; In some embodiments, if the data to be stored is stored back and forth between the primary storage unit and the secondary storage unit, the characteristic performance threshold is increased.

[0013] The technical solution of the embodiment of the present invention is: generate the information entropy value of the data set according to the information entropy method, obtain the key data block quantity value and the information entropy excess value based on the analysis and processing of the information entropy value, perform weighted ratio processing on the key data block quantity value and the information entropy excess value to obtain the key performance value, screen the data to be stored in the data set according to the access frequency, analyze and process the access frequency of the data subset according to the screening result to obtain the proportion of the number of high-frequency data blocks and the access frequency deviation ratio, perform weighted summation on the proportion of the number of high-frequency data blocks and the access frequency deviation ratio to obtain the data access value, combine the key performance value with the data access value for analysis, generate a data sequence table to be stored, and allocate the data to be stored based on the data sequence table to be stored. The present invention can accurately evaluate the storage priority and access characteristics of the data by combining the key performance value and the data access value for analysis, thereby generating an efficient data sequence table to be stored and optimizing the data storage allocation strategy.

[0014] Example 3 A data storage method based on an artificial intelligence accelerator according to an embodiment of the present invention includes: The artificial intelligence accelerator is used to classify the data to be stored, classify the data to be stored in terms of importance, and divide the data storage units based on the importance; The specific process of the AI ​​accelerator to distinguish and store data is as follows: S1: Use data cleaning tools (such as Pandas, etc.) to pre-process the stored data, extract data access frequency, modification time, data size, data type and other information, as one of the characteristics of data importance, clean, denoise and format the stored data to ensure data quality and consistency; S2: Use feature selection algorithms to select the most valuable features, reduce the complexity and computational complexity of the model, select the most valuable features for data importance assessment, normalize and standardize the features, and ensure that different features have the same weight in the model to improve the stability and accuracy of the model; S3: Select a suitable machine learning or deep learning model (such as decision tree, random forest, neural network, etc.), use historical data and features for training, and configure an AI accelerator (such as GPU) to speed up the training process to obtain a trained model; S4: Input the data to be evaluated into the trained model to obtain the importance score of the data, sort the data according to the score result, and determine the order of storing the data; S5: Continuously optimize and adjust the model based on actual application scenarios and feedback, and use the computing power of the accelerator to process the importance assessment task of stored data in real time to ensure the timeliness and accuracy of the data; The data storage unit is divided into core sub-units and edge sub-units, and the data to be stored are stored in sequence according to their importance.

[0015] Example 4 like Figure 3 The data storage system based on artificial intelligence accelerator described in the embodiment of the present invention includes: Feature analysis module: preprocessing the data to be stored, extracting features based on the preprocessed data to be stored to obtain feature indicators, analyzing the feature indicators to obtain feature indicator secondary values, further analyzing the feature indicator secondary values ​​to obtain feature performance values, comparing the feature performance values ​​with the feature performance threshold, and based on the comparison result, if the feature performance value is less than the feature performance threshold, further analyzing the data to be stored; Analysis signal processing module: Based on the analysis and processing of the information entropy value, the number of key data blocks and the information entropy excess value are obtained, and the number of key data blocks and the information entropy excess value are weighted ratio processed to obtain the key performance value, and the data to be stored in the data set are screened according to the access frequency to obtain the proportion of high-frequency data blocks and the access frequency deviation ratio, and the proportion of high-frequency data blocks and the access frequency deviation ratio are weighted summed to obtain the data access value; Storage allocation module: combines and analyzes the key performance value and the data access value, generates a sequence table of data to be stored, and allocates the data to be stored based on the sequence table of data to be stored.

[0016] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A data storage method based on an artificial intelligence accelerator, characterized in that: include: Analyze the characteristic index to obtain the secondary value of the characteristic index, further analyze the secondary value of the characteristic index to obtain the characteristic performance value, and further analyze the data to be stored based on the comparison between the characteristic performance value and the characteristic performance threshold; By analyzing and processing the information entropy value, the number of key data blocks and the information entropy excess value are obtained, and the number of key data blocks and the information entropy excess value are processed by weighted ratio to obtain the key performance value; The data to be stored in the data set is screened according to the access frequency to obtain the proportion of high-frequency data blocks and the access frequency deviation ratio, and the proportion of high-frequency data blocks and the access frequency deviation ratio are weighted and summed to obtain the data access value; The key performance value and the data access value are combined and analyzed to generate a sequence table of data to be stored, and the data to be stored is allocated based on the sequence table of data to be stored.

2. The data storage method based on artificial intelligence accelerator according to claim 1, characterized in that: The method for obtaining the characteristic performance value is as follows: Count the number of unqualified feature extractions, and perform ratio processing on the number of unqualified feature extractions and the total number of feature extractions to obtain the unqualified feature extraction ratio; Sum up all the minor difference ratios of the characteristic indicators and take the average to obtain the minor deviation value of the characteristic indicator; The feature extraction failure ratio is marked as BHG, and the feature index minor deviation value is marked as YPC; The feature extraction unqualified ratio BHG and the feature index minor deviation value YPC are processed by data, and the formula The characteristic performance value BX is calculated, where s1 and s2 are both preset proportional coefficients.

3. The data storage method based on artificial intelligence accelerator according to claim 1, characterized in that: The method for obtaining the feature extraction failure ratio BHG is as follows: The feature index secondary value is compared with the feature index secondary threshold. The specific comparison process is as follows: If the feature index secondary value is greater than the feature index secondary threshold, the feature extraction fails; If the feature index secondary value is less than or equal to the feature index secondary threshold, the feature extraction is qualified; During the data storage period, the number of unqualified feature extractions is counted, and the ratio of the number of unqualified feature extractions to the total number of feature extractions is processed to obtain the unqualified feature extraction ratio.

4. The data storage method based on artificial intelligence accelerator according to claim 3 is characterized in that: The method for obtaining the secondary deviation value YPC of the characteristic index is as follows: Based on the failure of the characteristic indicator, the secondary value of the characteristic indicator is processed with the secondary threshold of the characteristic indicator, and the absolute value is taken to obtain the secondary difference of the characteristic indicator. The secondary difference of the characteristic indicator is processed with the secondary threshold of the characteristic indicator to obtain the secondary difference ratio of the characteristic indicator. All the secondary difference ratios of the characteristic indicators are summed up and the average is taken to obtain the secondary deviation value of the characteristic indicator.

5. The data storage method based on artificial intelligence accelerator according to claim 3 is characterized in that: The key performance value GJ is obtained as follows: The key data block quantity value and the information entropy excess value are weighted ratio processed to obtain the key performance value, which is marked as GJ.

6. The data storage method based on artificial intelligence accelerator according to claim 1, characterized in that: The method for obtaining the number of key data blocks and the information entropy excess value is as follows: Sum all information entropy values ​​and take the average to get the information entropy mean. Calculate the difference between the information entropy value and the information entropy mean and take the absolute value to get the information entropy difference. The information entropy difference is compared with the preset information entropy difference threshold. The specific comparison process is as follows: If the information entropy difference is less than the information entropy difference threshold, the data block is marked as a key data block; If the information entropy deviation is greater than or equal to the information entropy deviation threshold, the data block is marked as a non-critical data block; Count the number of key data blocks and calculate the ratio with the number of data blocks to obtain the value of the number of key data blocks; Based on any key information block; The information entropy difference is calculated with the information entropy difference threshold to obtain the information entropy deviation, the information entropy deviation is calculated with the information entropy mean to obtain the information entropy deviation ratio, all the information entropy deviation ratios are summed up and the average is taken to obtain the information entropy excess value.

7. The data storage method based on artificial intelligence accelerator according to claim 1 is characterized in that: The data access value FW is obtained in the following manner: The weighted sum of the proportion of high-frequency data blocks and the access frequency deviation ratio is taken to obtain the data access value, which is marked as FW.

8. The data storage method based on artificial intelligence accelerator according to claim 1 is characterized in that: The method for obtaining the proportion of the number of high-frequency data blocks and the access frequency deviation ratio is as follows: The number of data blocks exceeding the baseline in the access frequency curve is counted, and the ratio is processed with the number of data blocks to obtain the proportion of high-frequency data blocks; In the access frequency curve, data points exceeding the baseline are selected and connected to obtain a high-frequency data curve; Based on any data point of the high-frequency data curve; Perform difference processing on the access frequency and the access frequency standard value to obtain the access frequency difference, perform ratio processing on the access frequency difference and the access frequency standard value to obtain the access frequency difference ratio; All access frequency difference ratios are summed up and the average is taken to obtain the access frequency deviation ratio.

9. The data storage method based on artificial intelligence accelerator according to claim 1, characterized in that: The storage characterization value CH is obtained in the following manner: The obtained key performance value GJ and data access value FW are processed by the formula The storage characterization value CH is calculated and obtained, wherein a1 and a2 are both preset proportional coefficients.

10. A data storage system based on artificial intelligence accelerator, characterized in that: Feature analysis module: preprocessing the data to be stored, extracting features based on the preprocessed data to be stored to obtain feature indicators, analyzing the feature indicators to obtain feature indicator secondary values, further analyzing the feature indicator secondary values ​​to obtain feature performance values, comparing the feature performance values ​​with the feature performance threshold, and based on the comparison result, if the feature performance value is less than the feature performance threshold, further analyzing the data to be stored; Analysis signal processing module: Based on the analysis and processing of the information entropy value, the number of key data blocks and the information entropy excess value are obtained, and the number of key data blocks and the information entropy excess value are weighted ratio processed to obtain the key performance value, and the data to be stored in the data set are screened according to the access frequency to obtain the proportion of high-frequency data blocks and the access frequency deviation ratio, and the proportion of high-frequency data blocks and the access frequency deviation ratio are weighted summed to obtain the data access value; Storage allocation module: combines and analyzes the key performance value and the data access value, generates a sequence table of data to be stored, and allocates the data to be stored based on the sequence table of data to be stored.

Images