CN117594109A - Multivariable Nand Flash ec change prediction method, equipment and storage medium - Google Patents
Multivariable Nand Flash ec change prediction method, equipment and storage medium Download PDFInfo
- Publication number
- CN117594109A CN117594109A CN202311540158.3A CN202311540158A CN117594109A CN 117594109 A CN117594109 A CN 117594109A CN 202311540158 A CN202311540158 A CN 202311540158A CN 117594109 A CN117594109 A CN 117594109A
- Authority
- CN
- China
- Prior art keywords
- prediction
- prediction result
- nand flash
- parameters
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000008859 change Effects 0.000 title claims abstract description 23
- 238000012549 training Methods 0.000 claims description 19
- 238000013136 deep learning model Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims 2
- 238000012545 processing Methods 0.000 abstract description 5
- 238000013135 deep learning Methods 0.000 description 9
- 238000004193 electrokinetic chromatography Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
- G11C29/04—Detection or location of defective memory elements, e.g. cell constructio details, timing of test signals
- G11C29/08—Functional testing, e.g. testing during refresh, power-on self testing [POST] or distributed testing
- G11C29/12—Built-in arrangements for testing, e.g. built-in self testing [BIST] or interconnection details
- G11C29/38—Response verification devices
- G11C29/42—Response verification devices using error correcting codes [ECC] or parity check
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of data processing, and discloses a multivariable Nand Flash ec change prediction method, equipment and a storage medium. The method comprises the following steps: when a prediction request of Nand Flash is received, analyzing an initial Ecc value, a time parameter, programming times, erasing parameters and temperature parameters carried by the prediction request; performing multiple prediction operations based on the initial Ecc value, the time parameter, the programming times, the erasing parameters and the temperature parameter to obtain a first prediction result, a second prediction result and a third prediction result; and executing the prediction operation of the multivariable influence on the first prediction result, the second prediction result and the third prediction result to obtain a target prediction result corresponding to the Nand Flash. In the embodiment of the invention, the prediction precision of Nand Flash ec is improved.
Description
Technical Field
The invention relates to the field of data processing, in particular to a multivariable Nand Flash ec change prediction method, equipment and a storage medium.
Background
In Nand Flash, some bit errors may occur because the characteristics of the Cell inside each memory chip are different. Ecc is a numerical representation of Nand Flash error condition at a certain stage, and directly relates to the success or failure of error correction decoding.
In the traditional machine learning method, the mechanism of Ecc is defaulted, the acquisition speed is the fastest, but the Ecc value is the largest; an optimal Ecc mechanism, the acquisition speed is the slowest, but the Ecc value is the smallest; the Retry ec mechanism has moderate acquisition speed, moderate Ecc value and strong practicability. The prediction accuracy of Ecc by these conventional machine learning methods remains to be improved.
Disclosure of Invention
The main purpose of the invention is to solve the technical problem that the prediction accuracy of Ecc is still to be improved.
The first aspect of the invention provides a multivariable Nand Flash ec change prediction method, which comprises the following steps:
when a prediction request of Nand Flash is received, analyzing an initial Ecc value, a time parameter, programming times, erasing parameters and temperature parameters carried by the prediction request;
performing multiple prediction operations based on the initial Ecc value, the time parameter, the programming times, the erasure parameters, and the temperature parameters to obtain a first prediction result, a second prediction result, and a third prediction result;
and executing multivariable influence prediction operation on the first prediction result, the second prediction result and the third prediction result to obtain a target prediction result corresponding to the Nand Flash.
Optionally, in a first implementation manner of the first aspect of the present invention, the step of performing multiple prediction operations based on the initial Ecc value, the time parameter, the programming frequency, the erasing parameter, and the temperature parameter to obtain a first prediction result, a second prediction result, and a third prediction result includes:
performing a prediction operation on the initial Ecc value and the time parameter to obtain the first prediction result;
performing a prediction operation on the initial Ecc value, the programming times and the erasure parameters to obtain the second prediction result;
and performing prediction operation on the initial Ecc value and the temperature parameter to obtain the third prediction result.
Optionally, in a second implementation manner of the first aspect of the present invention, the step of performing a prediction operation of a multivariate influence on the first prediction result, the second prediction result, and the third prediction result to obtain a target prediction result includes:
performing normalization operation on the first prediction result, the second prediction result and the third prediction result to obtain a standardized multidimensional prediction result;
and executing the prediction operation of the multivariable influence on the multidimensional prediction result to obtain the target prediction result.
Optionally, in a third implementation manner of the first aspect of the present invention, the step of performing a prediction operation of a multivariate influence on the first prediction result, the second prediction result, and the third prediction result to obtain a target prediction result includes:
and calling a fourth pre-set model trained in advance, and performing multivariable influence prediction operation on the first prediction result, the second prediction result and the third prediction result input to obtain a target prediction result.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the invoking a fourth pre-set model trained in advance, and performing a prediction operation of a multivariate influence on the first prediction result, the second prediction result, and the third prediction result input, so as to obtain a target prediction result, before the step of:
generating a deep learning model to be trained, and acquiring parameters of a specific sample as training data;
and executing model training operation on the deep learning model based on the training data to obtain the fourth preset model.
Optionally, in a fifth implementation manner of the first aspect of the present invention, after the step of performing a multivariable influence prediction operation on the first prediction result, the second prediction result, and the third prediction result to obtain the target prediction result corresponding to the Nand Flash, the method further includes:
performing numerical detection on the target prediction result to judge whether the target prediction result exceeds a standard range;
and if the target prediction result exceeds the standard range, outputting prompt information.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the step of performing multiple prediction operations based on the initial Ecc value, the time parameter, the programming frequency, the erasing parameter, and the temperature parameter to obtain a first prediction result, a second prediction result, and a third prediction result includes:
performing prediction operation on the initial Ecc value and the time parameter according to a first pre-trained preset model to obtain a first prediction result;
performing prediction operation on the initial Ecc value, the programming times and the erasure parameters according to a second preset model of preset training to obtain a second prediction result;
and performing prediction operation on the initial Ecc value and the temperature parameter according to a third preset model of preset training to obtain a third prediction result.
Optionally, in a seventh implementation manner of the first aspect of the present invention, before the step of performing a prediction operation on the initial Ecc value and the time parameter according to a first pre-trained preset model to obtain the first prediction result, the method further includes:
executing model training operation on the model to be trained to obtain a target model;
and performing time sequence transformation in the solution space of the target model to obtain the first preset model.
The second aspect of the present invention provides a multivariable Nand Flash ec variation prediction apparatus, comprising: a memory and at least one processor, the memory having instructions stored therein, the memory and the at least one processor being interconnected by a line; the at least one processor invokes the instructions in the memory to cause the multivariable Nand Flash ec variation prediction device to execute the multivariable Nand Flash ec variation prediction method described above.
A third aspect of the present invention provides a computer readable storage medium having instructions stored therein that, when run on a computer, cause the computer to perform the above-described multivariable Nand Flash ec variation prediction method.
In the embodiment of the invention, multiple prediction operations are used, and a plurality of input parameters are combined, so that the influence of a plurality of factors on Nand Flash can be more comprehensively considered, and the accuracy of prediction is improved. The multiple prediction operation can be used for carrying out long-term prediction on the performance of Nand Flash based on information such as time parameters, programming times and the like. By considering the influence of the erasure parameters and the time parameters, the problems can be predicted better, and measures can be taken in advance to repair or adjust. Prediction operations using multivariate influences may take into account correlations and interactions between multiple prediction results. For example, temperature parameters may interact with the effects of initial Ecc values and programming times, and this relationship may be more accurately captured using multivariate predictions, improving prediction accuracy. By performing a prediction operation of a multivariate influence, a plurality of prediction results are integrated, and a more accurate target prediction result can be obtained. Therefore, the advantages of different prediction results can be comprehensively considered, the deviation and error of a single prediction result are reduced, the traditional method can only depend on a small amount of input features or adopts a simple linear model to predict, and the accuracy of prediction is limited. Therefore, compared with the traditional method, the prediction accuracy of Nand Flash ec can be improved.
Drawings
FIG. 1 is a diagram of a first embodiment of a multivariable Nand Flash ec variation prediction method in an embodiment of the present invention;
FIG. 2 is a diagram of a second embodiment of a method for predicting the variation of Nand Flash ec of a multivariable embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a multivariable Nand Flash ec variation prediction device in an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a multivariable Nand Flash ec change prediction method, equipment and a storage medium.
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While the present disclosure has been illustrated in the drawings in some form, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and examples of the present disclosure are for illustrative purposes only and are not intended to limit the scope of the present disclosure.
In describing embodiments of the present disclosure, the term "comprising" and its like should be taken to be open-ended, i.e., including, but not limited to. The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first," "second," and the like, may refer to different or the same object. Other explicit and implicit definitions are also possible below.
For easy understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and an embodiment of a multivariable Nand Flash ec change prediction method in an embodiment of the present invention includes:
101. when a prediction request of Nand Flash is received, analyzing an initial Ecc value, a time parameter, programming times, erasing parameters and temperature parameters carried by the prediction request;
specifically, the embodiment constructs a Nand Flash ec change prediction model based on various deep learning frameworks, and when a prediction request is detected, the initial Ecc value, the time parameter, the programming times, the erasing parameters and the temperature parameters carried by the Nand Flash ec change prediction model can be resolved out and then used as the input of the Nand Flash ec change prediction model.
102. Performing multiple prediction operations based on the initial Ecc value, the time parameter, the programming times, the erasure parameters, and the temperature parameters to obtain a first prediction result, a second prediction result, and a third prediction result;
specifically, a Nand Flash ec change prediction model is built in the multivariable Nand Flash ec change prediction device.
Optionally, performing a prediction operation on the initial Ecc value and the time parameter to obtain the first prediction result; performing a prediction operation on the initial Ecc value, the programming times and the erasure parameters to obtain the second prediction result; and performing prediction operation on the initial Ecc value and the temperature parameter to obtain the third prediction result. The multivariable Nand Flash ec change prediction device calls a Nand Flash ec change prediction model to finish the operation.
Optionally, the Nand Flash ec change prediction model includes a first preset model, a second preset model and a third preset model, and the prediction operation is performed on the initial Ecc value and the time parameter according to the first preset model trained in advance to obtain the first prediction result; performing prediction operation on the initial Ecc value, the programming times and the erasure parameters according to a second preset model of preset training to obtain a second prediction result; and performing prediction operation on the initial Ecc value and the temperature parameter according to a third preset model of preset training to obtain a third prediction result. The Nand Flash ec change prediction model obtains input data, and can simultaneously implement prediction operation, and input corresponding data into a first preset model, a second preset model and a third preset model respectively to obtain a first prediction result, a second prediction result and a third prediction result.
Optionally, executing model training operation on the model to be trained to obtain a target model; and performing time sequence transformation in the solution space of the target model to obtain the first preset model. Specifically, a similar deep learning and interaction model forward process is used for carrying out time sequence transformation in a solution space, so that a general model capable of predicting any time ecc change of a specific model, namely a first preset model, is obtained. In the fields of machine learning and deep learning, the latency space (latent space) refers to a low-dimensional representation in a high-dimensional space. Typically, the original data may be high-dimensional, but by mapping the data to a lower-dimensional subspace, hidden structures and features in the data can be found. Latent space may be considered an abstract representation of data, where each dimension represents a particular feature or attribute. By operating in the latent space, the data can be generated, reconstructed, interpolated and the like, so that the control and understanding of the data are realized.
Alternatively, the generation of the latent space may be implemented by a dimension reduction technique, such as Principal Component Analysis (PCA), self encoder (Autoencoder), and the like. The high-dimensional data can be mapped into a lower-dimensional space while preserving as much of the information of the original data as possible.
Optionally, the method utilizes deep learning methods such as convolution, linear layer transformation, position coding and the like to finish the ecc variation predictor model under specific environments and time, namely a first preset model, of a specific model sample.
Optionally, performing normalization operation on the programming times, the erasing parameters and the temperature parameters to obtain standardized programming times, standardized erasing parameters and standardized temperature parameters; and performing multiple prediction operations based on the initial Ecc value, the time parameter, the standardized programming times, the standardized erasing parameters and the standardized temperature parameters to obtain a first prediction result, a second prediction result and a third prediction result. Specifically, the temperature and PE, READDISTURB influence normalization processing model, namely two preset models and a third preset model, on nand flash ecc is completed by utilizing the deep learning transducer model principle. In deep learning, normalization can help the optimization algorithm converge faster. If the scale (scale) of the features varies greatly, the optimization algorithm (e.g., gradient descent) may require many iterations to find the optimal solution. By normalization, the scale of all features becomes the same, which can accelerate the convergence speed of the optimization algorithm. In the deep neural network, if the scale difference of the data is too large, a problem of gradient disappearance or gradient explosion may be caused, which may affect the learning effect of the model. Normalization can effectively prevent this problem. Normalization allows the features to be consistent in order of magnitude so that the model is not dominated by features of some order of magnitude, thereby improving the performance of the model. After normalization, all the features are on the same scale, so that the importance of different features can be better compared.
Specifically, a deep learning model is used, and the specific sample wafer Ecc time sequence change prediction model is expanded to any sample wafer Ecc prediction model method, namely a Nand Flash Ecc change prediction model.
103. Performing multivariable influence prediction operation on the first prediction result, the second prediction result and the third prediction result to obtain a target prediction result corresponding to the Nand Flash;
specifically, according to a fourth pre-set model trained in advance, a prediction operation of the multi-variable influence is executed on the first prediction result, the second prediction result and the third prediction result, and a target prediction result corresponding to the Nand Flash is obtained.
Optionally, generating a deep learning model to be trained, and acquiring parameters of a specific sample as training data; and executing model training operation on the deep learning model based on the training data to obtain the fourth preset model. Specifically, a data set is collected, wherein each sample contains a plurality of ECCs and corresponding integrated ECCs. A deep learning model is then designed to process the data set. The deep learning model may be a fully connected network, convolutional Neural Network (CNN), recurrent Neural Network (RNN), or a transducer model. The input of the model is a plurality of ECCs and the output is a comprehensive ECC. The model is trained using standard deep learning techniques (e.g., gradient descent). This defines a loss function (e.g., the difference between the predicted and actual ECCs) and an optimization algorithm is used to minimize this loss. Model training completion may be used to perform a multivariate affected prediction operation on the first, second, and third predictions.
In the embodiment of the invention, multiple prediction operations are used, and a plurality of input parameters are combined, so that the influence of a plurality of factors on Nand Flash can be more comprehensively considered, and the accuracy of prediction is improved. The multiple prediction operation can be used for carrying out long-term prediction on the performance of Nand Flash based on information such as time parameters, programming times and the like. By considering the influence of the erasure parameters and the time parameters, the problems can be predicted better, and measures can be taken in advance to repair or adjust. Prediction operations using multivariate influences may take into account correlations and interactions between multiple prediction results. For example, temperature parameters may interact with the effects of initial Ecc values and programming times, and this relationship may be more accurately captured using multivariate predictions, improving prediction accuracy. By performing a prediction operation of a multivariate influence, a plurality of prediction results are integrated, and a more accurate target prediction result can be obtained. Therefore, the advantages of different prediction results can be comprehensively considered, the deviation and error of a single prediction result are reduced, the traditional method can only depend on a small amount of input features or adopts a simple linear model to predict, and the accuracy of prediction is limited. Therefore, compared with the traditional method, the prediction accuracy of Nand Flash ec can be improved.
Referring to fig. 2, fig. 2 is a second embodiment of a method for predicting Nand Flash ec variation of multiple variables according to an embodiment of the invention, after step 103, the following steps may be performed:
104. performing numerical detection on the target prediction result to judge whether the target prediction result exceeds a standard range;
105. and if the target prediction result exceeds the standard range, outputting prompt information.
Specifically, using the conventional machine learning method, the rough trend of Ecc can be predicted, but the special case of each block cannot be classified. Deep learning is introduced, and the obtained target prediction result can explore the change rule of each block. Based on the target prediction result and a preset standard range, whether prompt information needs to be output to the current prediction target or not can be judged.
In the embodiment of the invention, based on the prediction result of the deep learning and the preset standard range, whether the prompt information needs to be output to the current prediction target can be judged in real time. The method can help users to find and process possible problems of the Nand Flash in time, and improve the reliability and stability of the Nand Flash.
Fig. 3 is a schematic structural diagram of a multivariable Nand Flash ec variation prediction device according to an embodiment of the present invention, where the multivariable Nand Flash ec variation prediction device 500 may generate relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing application programs 533 or data 532. Wherein memory 520 and storage medium 530 may be transitory or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations on the Nand Flash ec variation prediction device 500 of the multivariate. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the multivariable Nand Flash ec variation prediction device 500.
The multivariable-based Nand Flash ec variation prediction device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input/output interfaces 560, and/or one or more operating systems 531, such as Windows service, mac OS X, unix, linux, free BSD, and the like. It will be appreciated by those skilled in the art that the multivariable Nand Flash ec variation prediction device structure shown in fig. 3 does not constitute a limitation of the multivariable based Nand Flash ec variation prediction device, and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
The present invention also provides a computer readable storage medium, which may be a nonvolatile computer readable storage medium, or may be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, where the instructions when executed on a computer cause the computer to perform the steps of the multivariable Nand Flash ec variation prediction method.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Moreover, although operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are example forms of implementing the claims.
Claims (10)
1. The multivariable Nand Flash ec change prediction method is characterized by comprising the following steps of:
when a prediction request of Nand Flash is received, analyzing an initial Ecc value, a time parameter, programming times, erasing parameters and temperature parameters carried by the prediction request;
performing multiple prediction operations based on the initial Ecc value, the time parameter, the programming times, the erasure parameters, and the temperature parameters to obtain a first prediction result, a second prediction result, and a third prediction result;
and executing multivariable influence prediction operation on the first prediction result, the second prediction result and the third prediction result to obtain a target prediction result corresponding to the Nand Flash.
2. The method of claim 1, wherein the step of performing multiple prediction operations based on the initial Ecc value, the time parameter, the programming times, the erasure parameters, and the temperature parameters to obtain a first prediction result, a second prediction result, and a third prediction result comprises:
performing a prediction operation on the initial Ecc value and the time parameter to obtain the first prediction result;
performing a prediction operation on the initial Ecc value, the programming times and the erasure parameters to obtain the second prediction result;
and performing prediction operation on the initial Ecc value and the temperature parameter to obtain the third prediction result.
3. The method of claim 1, wherein the step of performing multiple prediction operations based on the initial Ecc value, the time parameter, the programming times, the erasure parameters, and the temperature parameters to obtain a first prediction result, a second prediction result, and a third prediction result comprises:
performing normalization operation on the programming times, the erasing parameters and the temperature parameters to obtain standardized programming times, standardized erasing parameters and standardized temperature parameters;
and performing multiple prediction operations based on the initial Ecc value, the time parameter, the standardized programming times, the standardized erasing parameters and the standardized temperature parameters to obtain a first prediction result, a second prediction result and a third prediction result.
4. The method for predicting the variation of Nand Flash ec of claim 1, wherein the step of performing a multivariable-influenced prediction operation on the first, second and third predictors to obtain a target predictor comprises:
and calling a fourth pre-set model trained in advance, and performing multivariable influence prediction operation on the first prediction result, the second prediction result and the third prediction result input to obtain a target prediction result.
5. The method for predicting the Nand Flash ec variation of the multiple variables according to claim 4, wherein the calling a fourth pre-set model trained in advance performs a prediction operation of multiple variables on the first, second and third prediction result inputs, and before the step of obtaining the target prediction result, the method further comprises:
generating a deep learning model to be trained, and acquiring parameters of a specific sample as training data;
and executing model training operation on the deep learning model based on the training data to obtain the fourth preset model.
6. The method for predicting the Nand Flash ec variation of claim 1, wherein after the step of performing the multivariable-influenced prediction operation on the first, second and third predictors to obtain the target predictor corresponding to the Nand Flash, the method further comprises:
performing numerical detection on the target prediction result to judge whether the target prediction result exceeds a standard range;
and if the target prediction result exceeds the standard range, outputting prompt information.
7. The method of claim 1, wherein the step of performing multiple prediction operations based on the initial Ecc value, the time parameter, the programming times, the erasure parameters, and the temperature parameters to obtain a first prediction result, a second prediction result, and a third prediction result comprises:
performing prediction operation on the initial Ecc value and the time parameter according to a first pre-trained preset model to obtain a first prediction result;
performing prediction operation on the initial Ecc value, the programming times and the erasure parameters according to a second preset model of preset training to obtain a second prediction result;
and performing prediction operation on the initial Ecc value and the temperature parameter according to a third preset model of preset training to obtain a third prediction result.
8. The method for predicting Nand Flash ec variation of claim 7, wherein before the step of performing the predicting operation on the initial Ecc value and the time parameter according to the first pre-trained model to obtain the first predicted result, the method further comprises:
executing model training operation on the model to be trained to obtain a target model;
and performing time sequence transformation in the solution space of the target model to obtain the first preset model.
9. A multivariable Nand Flash ec change prediction device, characterized in that the multivariable Nand Flash ec change prediction device comprises: a memory and at least one processor, the memory having instructions stored therein, the memory and the at least one processor being interconnected by a line;
the at least one processor invoking the instructions in the memory to cause the multivariable Nand Flash ec variation prediction device to perform the multivariable Nand Flash ec variation prediction method of any of claims 1-8.
10. A computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the multivariable Nand Flash ec variation prediction method of any one of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311540158.3A CN117594109A (en) | 2023-11-16 | 2023-11-16 | Multivariable Nand Flash ec change prediction method, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311540158.3A CN117594109A (en) | 2023-11-16 | 2023-11-16 | Multivariable Nand Flash ec change prediction method, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117594109A true CN117594109A (en) | 2024-02-23 |
Family
ID=89917535
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311540158.3A Pending CN117594109A (en) | 2023-11-16 | 2023-11-16 | Multivariable Nand Flash ec change prediction method, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117594109A (en) |
-
2023
- 2023-11-16 CN CN202311540158.3A patent/CN117594109A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ragwitz et al. | Markov models from data by simple nonlinear time series predictors in delay embedding spaces | |
KR102455722B1 (en) | Deep learning based method for estimating output value of power plant and system for performing the same | |
US20230108920A1 (en) | System and method for providing robust artificial intelligence inference in edge computing devices | |
WO2015076084A1 (en) | Method and controller for controlling operation of machine | |
CN112068003A (en) | Method and device for predicting service life of cadmium-nickel storage battery based on linear wiener process | |
CN111104335A (en) | C language defect detection method and device based on multi-level analysis | |
CN111931426A (en) | Method and equipment for determining influence factors of concentration of nitrogen oxides at inlet of SCR (Selective catalytic reduction) reactor | |
US8855969B2 (en) | Frequency guard band validation of processors | |
CN110991124B (en) | Integrated circuit repairing method and device, storage medium and electronic equipment | |
CN113010671B (en) | App classification system | |
CN113537614A (en) | Construction method, system, equipment and medium of power grid engineering cost prediction model | |
CN117272781A (en) | Intelligent sampling semiconductor virtual measurement system based on SLGBM model | |
CN117594109A (en) | Multivariable Nand Flash ec change prediction method, equipment and storage medium | |
CN114417549A (en) | Digital twin target field data processing system based on supercomputer | |
CN111198499A (en) | Synchronous algorithm real-time evaluation method, system and storage medium | |
KR20220028724A (en) | Method and Apparatus for Virtual Measurement for Calculating Predicted Value and Feature Importance Based on Feature Values of Time Series Data | |
US8718809B2 (en) | Comprehensive analysis of queue times in microelectronic manufacturing | |
US20230010252A1 (en) | Semiconductor process modeling system and method | |
WO2019209571A1 (en) | Proactive data modeling | |
CN115099249B (en) | Intelligent optimization method and system based on translation result and storage medium thereof | |
CN110308387B (en) | Testing and automatic correcting method for verifying emptiness of assertion in form, storage medium and terminal | |
US20230367288A1 (en) | Physically-informed multi-system hardware operating windows | |
CN117349084A (en) | Data recovery method, equipment and storage medium for Nand false vth | |
CN117713047A (en) | New energy generated power prediction method, system, equipment and medium | |
CN116149972A (en) | Deep learning model testing method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |