Data storage method and storage medium based on solid state hard disk

Abstract

The present invention discloses a data storage method and storage medium based on a solid-state hard disk. The present invention relates to the technical field of solid-state hard disks and solves the problem that the storage process and historical data of data are not analyzed, so that the storage rate cannot reach the optimal state. The present invention classifies data in different formats, confirms different classified data, and identifies the optimal utilization rate and related storage rate from the historical completion data of different classified data. In the subsequent storage process, the classified data is evenly distributed and stored based on the corresponding utilization rate, so as to ensure the specific storage rate of the corresponding classified data and the overall storage effect. By analyzing the storage rate associated with the relevant storage process, it is identified whether the storage rate is reduced. If there is a reduction, the utilization rate is allocated from other storage paths to ensure the overall storage rate of the corresponding storage process, so that the corresponding storage rate is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of solid state hard disks, and in particular to a data storage method and storage medium based on a solid state hard disk. Background Art

[0002] A solid-state drive is a hard disk made of an array of solid-state electronic storage chips; its working principle is based on flash memory technology; unlike traditional mechanical hard disks that use magnetic heads to read and write data on high-speed rotating platters, solid-state drives use flash memory chips to store data; when writing data, electrical signals change the state of transistors in the flash memory chip to record information; when reading data, the electrical signals are converted into data that the computer can recognize by detecting the state of these transistors.

[0003] The patent application with the publication number CN117407324A discloses a data storage method, device, and solid-state hard disk controller based on a solid-state hard disk. The method includes: receiving and parsing a data storage request at the current moment, determining the data size and data type of the data to be stored according to the parsing result; determining the writing method according to the data type; determining whether there is a cache block that satisfies the storage in the solid-state hard disk according to the data size; if there is a cache block that satisfies the storage at the current moment, selecting a target cache block according to the data size to store the data to be stored in the target cache block by writing; if there is no cache block that satisfies the storage at the current moment, then based on the remaining storage space of each cache block, the data to be stored is divided to store the divided data to be stored in the cache block corresponding to the remaining storage space by writing. The space of the cache block is effectively utilized to reduce the waste of storage space. The writing time is reduced, and the writing wear of the solid-state hard disk is reduced.

[0004] During the data storage process, the corresponding solid state hard disk generally performs synchronous storage based on the storage priority of the corresponding data, and executes the number of synchronous storage paths according to the number of storage channels existing in the corresponding solid state hard disk. However, the original processing method does not analyze the data storage process and historical data, and directly stores them in chronological order. The storage rate is not in the optimal state, which will extend the storage time of the corresponding stored data. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a data storage method and storage medium based on a solid state hard disk, which solves the problem that the storage process and historical data of the data are not analyzed and thus the storage rate cannot reach the optimal state.

[0006] To achieve the above objectives, the present invention is implemented by the following technical solutions: a data storage method based on a solid state hard disk comprises the following steps:

[0007] Step 1: classify the data to be stored. Based on the different data formats in the data to be stored, the data to be stored is divided into the same number of classified data, and different position marks are set for different classified data. The specific sub-steps are:

[0008] Confirm the data formats associated with the data to be stored, and based on the confirmed different data formats, extract and classify the data texts belonging to the same data format to obtain classified data, and position marks are set for the data texts during the extraction and classification process;

[0009] Step 2: Based on the different data formats corresponding to different classified data, identify the storage data associated with the corresponding data format from the historical completion data. The storage data includes chip utilization and storage rate. By analyzing a large amount of storage data, determine the standard execution data belonging to this data format. The processing method is as follows:

[0010] S21. Mark the data formats of different classified data as pending formats, search for storage data associated with such pending formats from historical completed data, each group of storage data is data associated in a single storage process, and the searched storage data is not less than ten groups, based on the correlation between the corresponding chip utilization ratio and storage rate in each group of storage data, identify the chip utilization ratio associated with the maximum storage rate from each group of storage data;

[0011] S22, identifying the chip utilization rate associated with the maximum storage rate from other groups of storage data, and marking the maximum storage rate confirmed by the corresponding undetermined format as V i-k max, where i represents different pending formats and k represents different storage data. i-k The chip utilization rate associated with max is calibrated as ZB i-k , based on different V i-k Different ZBs associated with max i-k , V i-k max is sorted from small to large, confirming V i-k max sequence;

[0012] S23, from V i-k max sequence confirms adjacent V i-k max, prioritize the adjacent V i-k max, VC, VC = (the latter group V i-k max)-(previous group V i-k max), and then confirm the corresponding ZB i-k The difference BC, BC = (the latter group V i-k ZB associated with max i-k)-(Previous group V i-k ZB associated with max i-k ), using VC÷BC=change trend K, and dividing different adjacent V i-k The change trend between max is marked as K q , where q represents different adjacent V i-k max data column;

[0013] S24, based on different adjacent V i-k Different change trends K associated with max data column q , the adjacent V i-k The last group V in the max data column i-k max is calibrated as V t , where t = 2, 3, ..., n, where n represents V i-k max sequence V i-k The total number of max, using PD t =V t ×C1+K q ×C2 confirms the corresponding V t The associated rating value PD t , where C1 and C2 are preset fixed coefficient factors, from different V t The different rating values ​​associated with PD t In the PD t V associated with max t As the standard execution rate for this pending format, V t The corresponding ZB i-k As the standard execution utilization rate of the undetermined format, generating standard execution data belonging to the undetermined format based on the standard execution rate and the standard execution utilization rate;

[0014] S25. For other pending formats, the same method as steps S21-S24 is adopted to confirm the standard execution data corresponding to the pending format;

[0015] Step 3: Based on different standard execution data associated with different data formats of different classification data, a multi-path storage processing method is used to synchronously store different classification data. Based on the standard execution data, the storage priority of different classification data is confirmed in turn and storage processing is performed. The specific method is as follows:

[0016] S31. From different standard execution data associated with different pending formats, lock the standard execution utilization rate associated with the corresponding pending format, and mark the standard execution utilization rate as ZB i , where i represents different pending formats, and the pending formats correspond to the data formats one by one;

[0017] S32, from several groups of different undetermined formats associated with the standard execution utilization ZB i Randomly combine ZB i , so that the combined groups ZB i The sum of ZH1 is closest to 90%, and ZH1≤90%. i The associated classification data is multi-path stored, and the first set of storage processes is executed, and in this storage process, the ZB associated with the corresponding classification data is i Allocate chip utilization;

[0018] S33, in the first group of storage processes, after a group of classified data is stored, the remaining ZB i Select a group of ZB i , the selected ZB i Several groups of ZB in the original stored process i The sum of ZH2 is closest to 90%, and ZH2≤90%, and then execute the second group of storage processes. When a group of classified data in the second group of storage processes is stored, the remaining ZB i In the selection, confirm the classification data to be stored, and execute the subsequent storage process in sequence, and so on, until the different classification data associated with different pending formats are stored, and each group of storage processes is based on the ZB associated with the corresponding classification data. i Allocate chip utilization;

[0019] When the first group of classified data in the corresponding storage process is stored, if there is no determined total value that satisfies: total value ≤ 90%, confirmation will be performed after the next group of classified data is stored. If it still does not exist, confirmation will be continued until the corresponding storage process can be added to store the classified data;

[0020] Based on the different storage processes associated with different classified data, the storage rate of the classified data corresponding to each group of storage processes is monitored in real time. Based on the real-time monitoring results, it is confirmed whether there is a path to be optimized. If so, the associated allocation of standard execution utilization is performed. If not, no associated allocation is performed. The specific method is as follows:

[0021] Confirm the standard execution data associated with the corresponding classification data in each group of storage processes, confirm the standard execution rate associated with the corresponding classification data from the standard execution data, and mark it as V i , where i represents different pending formats;

[0022] Monitor the storage rate of the specified classification data in real time and mark the real-time monitored storage rate as VS i , identify whether the real-time monitored storage rate exists: (Vi -VS i )÷V i ≥10%, if it exists, the storage path associated with the corresponding classification data is marked as the path to be optimized; if it does not exist, no marking is performed;

[0023] Based on the calibrated paths to be optimized, other paths in the current storage process that are not calibrated as paths to be optimized are calibrated as normal paths. The occupied standard execution utilization is allocated from each group of normal paths in turn. The standard execution utilization allocated in each allocation process is 1%. After each allocation process is completed, the storage rate difference associated with each path is confirmed:

[0024] The storage rate of the corresponding path in each allocation process before the allocation is calibrated as V1 i , the storage rate at the moment after allocation is calibrated as V2 i , using CZ i =V2 i -V1 i , confirm the storage rate difference CZ associated with the corresponding path i ;

[0025] The several groups of storage rate differences CZ associated with this allocation process i Perform sum processing and lock the difference sum. If the difference sum is ≥ 0, execute the next group of allocation processes. If the difference sum is < 0, adjust the standard execution utilization allocated in the current allocation process back to the original corresponding path and stop this allocation process.

[0026] Step 4: After the storage process is completed, based on the different position marks associated with each group of classified data, several groups of classified data are reorganized to obtain the original data to be stored.

[0027] Preferably, a data storage medium based on a solid state drive stores several groups of classified data associated in the storage process, and after the storage is completed, the several groups of classified data are reorganized based on different position marks associated with each group of classified data to obtain the original data to be stored.

[0028] The present invention provides a data storage method and storage medium based on a solid state hard disk. Compared with the prior art, it has the following beneficial effects:

[0029] The present invention classifies data of different formats, confirms different classified data, and identifies the best utilization rate and related storage rate from the historical completion data of different classified data. In the subsequent storage process, the classified data is evenly distributed and stored based on the corresponding utilization rate, so as to ensure the specific storage rate of the corresponding classified data and the overall storage effect.

[0030] Analyze the storage rate associated with the relevant storage process to identify whether its storage rate has decreased. If so, adjust the utilization from other storage paths to ensure the overall storage rate of the corresponding storage process and further improve the corresponding storage rate. This method can effectively further improve the overall storage rate of the corresponding storage process to comprehensively improve its overall storage effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic diagram of the process of the present invention;

[0032] Figure 2 A schematic diagram of a flow chart associated with the utilization rate allocation process of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] First embodiment: Please refer to Figure 1 The present application provides a data storage method based on a solid state drive, comprising the following steps:

[0035] Step 1: classify the data to be stored. Based on the different data formats in the corresponding data to be stored, the data to be stored is divided into the same number of classified data, and different position marks are set for different classified data. After the storage is completed, the relevant classified data can be reorganized through the corresponding position marks to obtain the data to be stored before storage. The specific sub-steps of data classification for the data to be stored are:

[0036] Confirm the data format associated with the data to be stored, which generally includes different formats such as text data format, image data format, audio data format and video data format. Based on the confirmed different data formats, extract and classify the data texts belonging to the same data format to obtain classified data. In the process of extracting and classifying, position marks are set for the data texts. Subsequently, the corresponding data texts can be readjusted to the original position based on the position marks to ensure that the data representation of the corresponding data to be stored is consistent before and after storage. When the corresponding data texts are extracted, the data at the front end and the data at the back end are recorded in the corresponding position marks. The same association marks are set at the end of the front-end data and the front end of the back-end data. The association marks correspond to the position marks one by one. Based on the correspondence between the association marks and the position marks, the location of the corresponding extracted data can be quickly found and relevant adjustments can be made.

[0037] Step 2: Based on different data formats corresponding to different classified data, storage data associated with the corresponding data format is identified from historical completion data. The storage data includes chip utilization and storage rate. By analyzing a large amount of storage data, standard execution data belonging to this data format is determined. Specifically, there are corresponding flash memory chips in the solid hard disk. When multi-path storage is used, the general chip will proportionally allocate the associated utilization for each storage path to achieve the comprehensive storage effect of the corresponding storage data. Among them, the processing method for determining the standard execution data belonging to this data format is:

[0038] S21. Mark the data formats of different classified data as pending formats, search for storage data associated with such pending formats from historical completed data, each group of storage data is data associated in a single storage process, and the searched storage data is not less than ten groups, based on the correlation between the corresponding chip utilization ratio and storage rate in each group of storage data, identify the chip utilization ratio associated with the maximum storage rate from each group of storage data;

[0039] S22, identifying the chip utilization rate associated with the maximum storage rate from other groups of storage data, and marking the maximum storage rate confirmed by the corresponding undetermined format as V i-k max, where i represents different pending formats and k represents different storage data. i-k The chip utilization rate associated with max is calibrated as ZB i-k , based on different V i-k Different ZBs associated with max i-k , V i-k max is sorted from small to large, confirming V i-k max sequence;

[0040] S23, from V i-k max sequence confirms adjacent V i-k max, prioritize the adjacent V i-k max, VC, VC = (the latter group V i-k max)-(previous group V i-k max), and then confirm the corresponding ZB i-k The difference BC, BC = (the latter group V i-k ZB associated with max i-k )-(Previous group V i-k ZB associated with max i-k ), using VC÷BC=change trend K, and dividing different adjacent V i-k The change trend between max is marked as K q , where q represents different adjacent V i-k max data column;

[0041] S24, based on different adjacent V i-k Different change trends K associated with max data column q , the adjacent V i-k The last group V in the max data column i-k max is calibrated as V t , where t = 2, 3, ..., n, where n represents V i-k max sequence V i-k The total number of max, using PD t =V t ×C1+K q ×C2 confirms the corresponding V t The associated rating value PD t , where C1 and C2 are preset fixed coefficient factors, and their specific values ​​are determined by the operator based on experience, from different V t The different rating values ​​associated with PD t In the PD t V associated with max t As the standard execution rate for this pending format, V t The corresponding ZB i-k As the standard execution utilization rate of the undetermined format, generating standard execution data belonging to the undetermined format based on the standard execution rate and the standard execution utilization rate;

[0042] S25. For other pending formats, the same method as steps S21-S24 is adopted to confirm the standard execution data corresponding to the pending formats;

[0043] Specifically, for different pending formats, there are different chip utilization rates in the past historical completion data, and different utilization rates correspond to different storage rates. There are different data representations in each different storage data. The maximum storage rate and the associated utilization rate can be locked from the different data representations. Different storage rates have related maximum values ​​and corresponding utilization rates, so there are related change trends between different maximum storage rates, that is, there are corresponding change trends between the corresponding utilization rates and storage rates. When the change trend is too small, it means that the associated numerical representation state will decrease, that is, the storage process will decrease proportionally (it can be understood that the original trend is large, but the subsequent change trend becomes smaller. Compared with the past related trends, it belongs to the related state of geometric reduction in rate). Therefore, when determining the standard execution data, the corresponding storage rate and the related utilization rate are comprehensively considered to determine the corresponding standard execution data.

[0044] Step 3: Based on different standard execution data associated with different data formats of different classification data, a multi-path storage processing method is used to synchronously store different classification data. Based on the standard execution data, the storage priority of different classification data is sequentially confirmed and storage processing is performed, wherein the specific sub-steps of the storage processing are:

[0045] S31. From different standard execution data associated with different pending formats, lock the standard execution utilization rate associated with the corresponding pending format, and mark the standard execution utilization rate as ZB i , where i represents different pending formats, and the pending formats correspond to the data formats one by one;

[0046] S32, from several groups of different undetermined formats associated with the standard execution utilization ZB i Randomly combine ZB i , so that the combined groups ZB i The sum of ZH1 is closest to 90%, and ZH1≤90%. i The associated classification data is multi-path stored, and the first set of storage processes is executed, and in this storage process, the ZB associated with the corresponding classification data is i Allocate chip utilization;

[0047] S33, in the first group of storage processes, after a group of classified data is stored, the remaining ZB i Select a group of ZB i , the selected ZB i Several groups of ZB in the original stored process iThe sum of ZH2 is closest to 90%, and ZH2≤90%, and then execute the second group of storage processes. When a group of classified data in the second group of storage processes is stored, the remaining ZB i In the selection, confirm the classification data to be stored, and execute the subsequent storage process in sequence, and so on, until the different classification data associated with different pending formats are stored, and each group of storage processes is based on the ZB associated with the corresponding classification data. i Allocate chip utilization;

[0048] When the first group of classified data in the corresponding storage process is stored, and there is no determined total value that satisfies: total value ≤ 90%, confirmation will be performed after the next group of classified data is stored. If it still does not exist, confirmation will be continued until the corresponding storage process can be added to store the classified data (that is, the process is added when the corresponding evaluation conditions are met);

[0049] Specifically, it is proposed that there are five groups of pending formats, which are A, B, C, D and E, wherein the utilization rate determined by A is 45%, the utilization rate determined by B is 30%, and the utilization rates determined by C, D and E are 30%, 30% and 25% respectively;

[0050] According to step S32, the five groups of utilization rates are randomly combined, and the combined utilization rates are three classification data of B, C and D. Since the utilization rates associated with the three classification data are 90%, which is the closest numerical state, the three classification data of B, C and D are synchronously stored, and the synchronous storage process is executed;

[0051] When the storage of one of the three classified data of B, C and D is completed, there is a 30% vacancy, and the remaining utilization is 45% and 25%, then the storage process of classified data E is intervened and stored;

[0052] When a certain set of classified data in the second storage process is stored and 45% of it cannot be intervened, the storage process of classified data A will be intervened after the second set of classified data is completed, and the synchronous storage process of the five sets of classified data will be completed;

[0053] This type of data storage method can effectively guarantee the storage rate of the corresponding classified data without causing hard disk load, thereby improving its overall storage effect.

[0054] Second embodiment: This embodiment is a further implementation process of the storage process. Comprehensive optimization is performed for each storage process to further improve the storage rate.

[0055] Step three also includes:

[0056] Based on different storage processes associated with different classified data, the storage rate of the classified data corresponding to each group of storage processes is monitored in real time. Based on the real-time monitoring results, it is confirmed whether there is a path to be optimized. If so, the associated allocation of the standard execution utilization is performed. If not, no associated allocation is performed. Specifically, when the storage rate corresponding to each group of storage processes has a large deviation, it means that the relevant data in the corresponding storage process has more complex data when it is stored, which leads to a decrease in the corresponding storage rate;

[0057] The specific method for confirming whether there is a process to be optimized is:

[0058] Combination Figure 2 , confirm the standard execution data associated with the corresponding classification data in each group of storage processes, confirm the standard execution rate associated with the corresponding classification data from the standard execution data, and mark it as V i , where i represents different pending formats, and different pending formats correspond one-to-one to the corresponding classification data;

[0059] Monitor the storage rate of the specified classification data in real time and mark the real-time monitored storage rate as VS i , identify whether the real-time monitored storage rate exists: (V i -VS i )÷V i ≥10% (that is, the rate difference accounts for more than 10%). If it exists, the storage path associated with the corresponding classification data is marked as the path to be optimized. If it does not exist, no calibration is performed;

[0060] Based on the calibrated paths to be optimized, other paths in the current storage process that are not calibrated as paths to be optimized are calibrated as normal paths. The occupied standard execution utilization is allocated from each group of normal paths in turn. The allocated standard execution utilization in each allocation process is 1% (1% of the normal path is allocated to the path to be optimized). After each allocation process is completed, the storage rate difference associated with each path is confirmed:

[0061] The storage rate of the corresponding path (including normal path and path to be optimized) in each allocation process before allocation is calibrated as V1 i , the storage rate at the moment after allocation is calibrated as V2 i , using CZ i =V2 i -V1 i , confirm the storage rate difference CZ associated with the corresponding path i ;

[0062] The several groups of storage rate differences CZ associated with this allocation process iPerform sum processing and lock the difference sum. If the difference sum is ≥0, execute the next group of allocation processes. If the difference sum is <0, adjust the standard execution utilization allocated in the current allocation process back to the original corresponding path and stop this allocation process. If the difference sum is greater than 0, it means that after the corresponding allocation process completes the allocation, the storage rate of the entire storage process is in an upward state, which means that the corresponding allocation process is reasonable and such allocation can be performed. When the corresponding storage rate decreases after the allocation, adjust the corresponding allocation utilization back to terminate the corresponding allocation process. In this way, the overall storage rate of the corresponding storage process can be effectively further improved to comprehensively improve its overall storage effect.

[0063] Step 4: After the storage process is completed, based on the different position marks associated with each group of classified data, several groups of classified data are reorganized to obtain the original data to be stored.

[0064] The third embodiment: A data storage medium based on a solid state drive is used to store several groups of classified data associated in a storage process, and after the storage is completed, the several groups of classified data are reorganized based on different position marks associated with each group of classified data to obtain the original data to be stored (the data to be stored at this moment has been converted into storage data).

[0065] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0066] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A data storage method based on a solid state hard disk, characterized in that: The following steps are involved: Step 1: classify the data to be stored, divide the data to be stored into the same number of classified data based on different data formats in the data to be stored, and set different position marks for different classified data; Step 2: Based on the different data formats corresponding to different classified data, identify the storage data associated with the corresponding data format from the historical completion data. The storage data includes chip utilization and storage rate. By analyzing a large amount of storage data, determine the standard execution data belonging to this data format. The processing method is as follows: S21. Mark the data formats of different classified data as pending formats, search for storage data associated with such pending formats from historical completed data, each group of storage data is data associated in a single storage process, and the searched storage data is not less than ten groups, based on the correlation between the corresponding chip utilization ratio and storage rate in each group of storage data, identify the chip utilization ratio associated with the maximum storage rate from each group of storage data; S22, identifying the chip utilization rate associated with the maximum storage rate from other groups of storage data, and marking the maximum storage rate confirmed by the corresponding undetermined format as V i-k max, where i represents different pending formats and k represents different storage data. i-k The chip utilization rate associated with max is calibrated as ZB i-k , based on different V i-k Different ZBs associated with max i-k , V i-k max is sorted from small to large, confirming V i-k max sequence; S23, from V i-k max sequence confirms adjacent V i-k max, prioritize the adjacent V i-k max, VC, VC = (the latter group V i-k max)-(previous group V i-k max), and then confirm the corresponding ZB i-k The difference BC, BC = (the latter group V i- k ZB associated with max i-k )-(Previous group V i-k ZB associated with max i-k ), using VC÷BC=change trend K, and dividing different adjacent V i-k The change trend between max is marked as K q , where q represents different adjacent V i-k max data column; S24, based on different adjacent V i-k Different change trends K associated with max data column q , the adjacent V i-k The last group V in the max data column i-k max is calibrated as V t , where t = 2, 3, ..., n, where n represents V i-k max sequence V i-k The total number of max, using PD t =V t ×C1+K q ×C2 confirms the corresponding V t The associated rating value PD t , where C1 and C2 are preset fixed coefficient factors, from different V t The different rating values ​​associated with PD t In the PD t V associated with max t As the standard execution rate for this pending format, V t The corresponding ZB i-k As the standard execution utilization rate of the undetermined format, generating standard execution data belonging to the undetermined format based on the standard execution rate and the standard execution utilization rate; S25. For other pending formats, the same method as steps S21-S24 is adopted to confirm the standard execution data corresponding to the pending formats; Step 3: Based on different standard execution data associated with different data formats of different classification data, a multi-path storage processing method is used to synchronously store different classification data, and based on the standard execution data, the storage priority of different classification data is sequentially confirmed and storage processing is performed; Step 4: After the storage process is completed, based on the different position marks associated with each group of classified data, several groups of classified data are reorganized to obtain the original data to be stored.

2. The data storage method based on a solid state drive according to claim 1, characterized in that: In step 1, the specific sub-steps for dividing the data to be stored are: The data formats associated with the data to be stored are confirmed, and based on the confirmed different data formats, the data texts belonging to the same data format are extracted and classified to obtain classified data, and position marks are set for the data texts during the extraction and classification process.

3. The data storage method based on a solid state drive according to claim 1, characterized in that: In step 3, the specific method of storing and processing different classification data is as follows: S31. From different standard execution data associated with different pending formats, lock the standard execution utilization rate associated with the corresponding pending format, and mark the standard execution utilization rate as ZB i , where i represents different pending formats, and the pending formats correspond to the data formats one by one; S32, from several groups of different undetermined formats associated with the standard execution utilization ZB i Randomly combine ZB i , so that the combined groups ZB i The sum of ZH1 is closest to 90%, and ZH1≤90%. i The associated classification data is multi-path stored, and the first set of storage processes is executed, and in this storage process, the ZB associated with the corresponding classification data is i Allocate chip utilization ratio; S33, in the first group of storage processes, after a group of classified data is stored, the remaining ZB i Select a group of ZB i , the selected ZB i Several groups of ZB in the original stored process i The sum of ZH2 is closest to 90%, and ZH2≤90%, and then execute the second group of storage processes. When a group of classified data in the second group of storage processes is stored, the remaining ZB i In the selection, confirm the classification data to be stored, and execute the subsequent storage process in sequence, and so on, until the different classification data associated with different pending formats are stored, and each group of storage processes is based on the ZB associated with the corresponding classification data. i Allocate chip utilization.

4. The data storage method based on a solid state drive according to claim 3, characterized in that: In the step S33, when the first group of classified data in the corresponding storage process is stored, if there is no determined total value satisfying: total value ≤ 90%, confirmation will be performed after the next group of classified data is stored. If it still does not exist, confirmation will continue until the corresponding storage process can be added to store the classified data.

5. The data storage method based on solid state hard disk according to claim 3, characterized in that: The step three also includes: Based on the different storage processes associated with different classified data, the storage rate of the classified data corresponding to each group of storage processes is monitored in real time. Based on the real-time monitoring results, it is confirmed whether there is a path to be optimized. If so, the associated allocation of standard execution utilization is performed. If not, no associated allocation is performed.

6. The data storage method based on a solid state drive according to claim 5, characterized in that: The specific method for confirming whether there is a path to be optimized and making associated allocations is as follows: Confirm the standard execution data associated with the corresponding classification data in each group of storage processes, confirm the standard execution rate associated with the corresponding classification data from the standard execution data, and mark it as V i , where i represents different pending formats; Monitor the storage rate of the specified classification data in real time and mark the real-time monitored storage rate as VS i , identify whether the real-time monitored storage rate exists: (V i -VS i )÷V i ≥10%, if it exists, the storage path associated with the corresponding classification data is marked as the path to be optimized; if it does not exist, no marking is performed; Based on the calibrated paths to be optimized, other paths in the current storage process that are not calibrated as paths to be optimized are calibrated as normal paths. The occupied standard execution utilization is allocated from each group of normal paths in turn. The standard execution utilization allocated in each allocation process is 1%. After each allocation process is completed, the storage rate difference associated with each path is confirmed: The storage rate of the corresponding path in each allocation process before the allocation is calibrated as V1 i , the storage rate at the moment after allocation is calibrated as V2 i , using CZ i =V2 i -V1 i , confirm the storage rate difference CZ associated with the corresponding path i ; The several groups of storage rate differences CZ associated with this allocation process i Perform summation and lock the difference sum. If the difference sum is ≥ 0, execute the next set of allocation processes. If the difference sum is < 0, adjust the standard execution utilization allocated in the current allocation process back to the original corresponding path and stop this allocation process.

7. A data storage medium based on a solid state drive, for storing the classified data generated by the data storage method based on a solid state drive according to any one of claims 1, 4 to 6, characterized in that: The classified data associated in the plurality of storage processes are stored, and after the storage is completed, the plurality of classified data are reorganized based on different position marks associated with each group of classified data to obtain the original data to be stored.

Images