CN116776743A - Computer key parameter degradation prediction method based on domain countermeasure and related equipment - Google Patents
Computer key parameter degradation prediction method based on domain countermeasure and related equipment Download PDFInfo
- Publication number
- CN116776743A CN116776743A CN202310923651.7A CN202310923651A CN116776743A CN 116776743 A CN116776743 A CN 116776743A CN 202310923651 A CN202310923651 A CN 202310923651A CN 116776743 A CN116776743 A CN 116776743A
- Authority
- CN
- China
- Prior art keywords
- computer
- branch model
- input
- domain
- value
- 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 85
- 230000015556 catabolic process Effects 0.000 title claims abstract description 73
- 238000006731 degradation reaction Methods 0.000 title claims abstract description 73
- 238000012549 training Methods 0.000 claims abstract description 60
- 230000000750 progressive effect Effects 0.000 claims abstract description 58
- 230000007774 longterm Effects 0.000 claims abstract description 14
- 238000013528 artificial neural network Methods 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 25
- 238000012512 characterization method Methods 0.000 claims description 17
- 239000000203 mixture Substances 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000008485 antagonism Effects 0.000 claims description 5
- 238000009825 accumulation Methods 0.000 abstract description 6
- 125000004122 cyclic group Chemical group 0.000 abstract description 6
- 238000012423 maintenance Methods 0.000 abstract description 5
- 231100000749 chronicity Toxicity 0.000 abstract description 2
- 238000002360 preparation method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000007423 decrease Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000695274 Processa Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a computer key parameter degradation prediction method based on domain countermeasure and related equipment, belonging to the technical field of embedded computer key parameter prediction, wherein the method adopts a double-branch network structure, namely a true input branch model and a progressive learning branch model; gradually adding the predicted value into a training sample in the progressive learning branch model until the long-term predicted requirement is met; the training mode based on domain countermeasure is improved, the extracted characteristics of the two branch models are ensured to be close to each other, and finally, the accurate prediction of the degradation trend of the key parameters of the computer is finished through the output progressive learning branch model; the method can solve the problem of error accumulation in cyclic prediction, and realize more accurate and long-term trend prediction, thereby reserving longer preparation time for subsequent maintenance work; the method improves the prediction chronicity, is convenient for timely arranging the maintenance work of the electronic system, and ensures the reliability of the computer work.
Description
Technical Field
The invention belongs to the technical field of embedded computer key parameter prediction, and particularly relates to a computer key parameter degradation prediction method based on domain countermeasure and related equipment.
Background
The embedded computer can be flexibly applied to harsh environments such as temperature, use space and the like, including application markets with low power consumption system requirements such as vehicle-mounted, retail, monitoring, electronic billboards, factory control and the like. In order to ensure the operation performance of the embedded computer, it is necessary to predict the degradation of key parameters of the embedded computer.
The conventional model approach uses a fixed degradation model for pseudo-life estimation of embedded computers. Although simple and intuitive, there is a large difference from real-time real data. In the prediction process, the method (for example, LSTM) based on the deep neural network iteratively uses the output predicted value as an input value, and although the short-term prediction effect is relatively accurate, the predicted value is used as the input of the next step, so that error accumulation exists in the cyclic prediction process, and the effect on medium-term and long-term prediction is poor.
Disclosure of Invention
In order to overcome the defects of the technology, the invention provides a computer key parameter degradation prediction method based on domain countermeasure and related equipment, which can solve the technical problem that the prior prediction method cannot ensure the accuracy of medium-long term degradation prediction.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a domain countermeasure based computer key parameter degradation prediction method, comprising:
training a progressive learning branch model according to a real input branch model based on a domain countermeasure learning method;
predicting the degradation trend of the key parameters of the computer by using the trained progressive learning branch model;
the real input branch model adopts a neural network taking a real value as an input value; the progressive learning branch model employs a neural network with a mixture of real and predicted values as input values.
Further, the specific steps of building the true input branch model include:
acquiring key characterization parameters with long-term degradation trend, and preprocessing the acquired key characterization parameters; constructing and training a neural network according to the preprocessed key characterization parameters to obtain a real input branch model; in the training process of the true input branch model, the input values of each iteration all adopt the true values.
Further, the specific steps of building the progressive learning branch model include:
constructing a neural network according to the preprocessed key characterization parameters; in the training process of the progressive learning branch model, a mixed value of a true value and a predicted value is used as an input value of each iteration.
Further, in the training process of the progressive learning branch model, the duty ratio of the predicted value in the mixed value gradually increases along with the iteration times.
Further, in the training process of the progressive learning branch model, the input proportion of the predicted value is gradually increased, the input of the predicted value is gradually increased from 0 to 100%, and the proportion increasing rate is in direct proportion to the iteration times.
Further, in the process of preprocessing the key characterization parameters, the time series data is divided into time series batch data corresponding to the network input length, and the time series batch data are processed in batches.
Further, the key parameter of the computer is a motherboard voltage parameter.
A domain countermeasure-based computer key parameter degradation prediction system for implementing the above-mentioned domain countermeasure-based computer key parameter degradation prediction method, comprising:
the model training module is used for training the progressive learning branch model according to the real input branch model based on the domain countermeasure learning method;
the prediction module is used for predicting the degradation trend of the key parameters of the computer by using the trained progressive learning branch model;
the real input branch model adopts a neural network taking a real value as an input value; the progressive learning branch model employs a neural network with a mixture of real and predicted values as input values.
An apparatus, comprising:
a memory for storing a computer program;
and the processor is used for realizing the steps of the computer key parameter degradation prediction method based on domain countermeasure when executing the computer program.
A computer readable storage medium storing a computer program for implementing the steps of the domain countermeasure-based computer key parameter degradation prediction method described above when executed by a processor.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a computer key parameter degradation prediction method based on domain countermeasure, which adopts a double-branch network structure, namely a true input branch model and a progressive learning branch model; gradually adding the predicted value into a training sample in the progressive learning branch model until the long-term predicted requirement is met; the training mode based on domain countermeasure is improved, the extracted characteristics of the two branch models are ensured to be close to each other, and finally, the accurate prediction of the degradation trend of the key parameters of the computer is finished through the output progressive learning branch model; the method can solve the problem of error accumulation in cyclic prediction, and realize more accurate and long-term trend prediction, thereby reserving longer preparation time for subsequent maintenance work; the method improves the prediction chronicity, is convenient for timely arranging the maintenance work of the electronic system, and ensures the reliability of the computer work.
Drawings
FIG. 1 is a schematic diagram of a dual-branch network structure based on countermeasure learning according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a change in distribution of implicit features in a domain countermeasure network training process according to an embodiment of the present invention; wherein, (a) is an initial distribution state; (b) a training state; (c) training is about to end; (d) a training completion status;
FIG. 3 is a schematic diagram of a progressive learning branch for combined input of predicted values and real values according to an embodiment of the present invention;
FIG. 4 is a flow chart of a method for predicting degradation of key parameters of a computer based on domain antagonism provided by the invention;
fig. 5 is a schematic structural diagram of a domain countermeasure-based computer key parameter degradation prediction system according to the present invention.
Detailed Description
The invention provides a domain countermeasure-based computer key parameter degradation prediction method, which is shown in fig. 4 and comprises the following steps:
a domain countermeasure based computer key parameter degradation prediction method, comprising:
training a progressive learning branch model according to a real input branch model based on a domain countermeasure learning method;
predicting the degradation trend of the key parameters of the computer by using the trained progressive learning branch model;
the real input branch model adopts a neural network taking a real value as an input value; the progressive learning branch model employs a neural network with a mixture of real and predicted values as input values.
Specifically, the specific steps of building the true input branch model include:
acquiring key characterization parameters with long-term degradation trend, and preprocessing the acquired key characterization parameters; constructing and training a neural network according to the preprocessed key characterization parameters to obtain a real input branch model; in the training process of the true input branch model, the input values of each iteration all adopt the true values. In the process of preprocessing the key characterization parameters, the time series data are divided into time series batch data corresponding to the network input length, and the time series batch data are processed in batches.
The specific steps of building the progressive learning branch model include:
constructing a neural network according to the preprocessed key characterization parameters; in the training process of the progressive learning branch model, a mixed value of a true value and a predicted value is used as an input value of each iteration, wherein the ratio of the predicted value in the mixed value is gradually increased along with the iteration number, that is, the input proportion of the predicted value is gradually increased, the input of the predicted value is gradually increased from 0 to 100%, and the proportion increasing rate is in direct proportion to the iteration number.
The key parameter of the computer may be a motherboard voltage parameter, which is one of key parameters of the embedded computer.
As shown in fig. 5, the present invention further provides a domain countermeasure-based computer key parameter degradation prediction system, comprising: the model training module is used for training the progressive learning branch model according to the real input branch model based on the domain countermeasure learning method; the prediction module is used for predicting the degradation trend of the key parameters of the computer by using the trained progressive learning branch model; the real input branch model adopts a neural network taking a real value as an input value; the progressive learning branch model employs a neural network with a mixture of real and predicted values as input values.
The invention also provides an apparatus comprising: a memory for storing a computer program; and the processor is used for realizing the computer key parameter degradation prediction method based on domain countermeasure when executing the computer program.
The processor, when executing the computer program, performs the steps of the above-mentioned domain countermeasure-based computer key parameter degradation prediction, for example: training a progressive learning branch model according to a real input branch model based on a domain countermeasure learning method; predicting the degradation trend of the key parameters of the computer by using the trained progressive learning branch model; the real input branch model adopts a neural network taking a real value as an input value; the progressive learning branch model employs a neural network with a mixture of real and predicted values as input values.
Alternatively, the processor may implement functions of each module in the above system when executing the computer program, for example: the model training module is used for training the progressive learning branch model according to the real input branch model based on the domain countermeasure learning method; the prediction module is used for predicting the degradation trend of the key parameters of the computer by using the trained progressive learning branch model; the real input branch model adopts a neural network taking a real value as an input value; the progressive learning branch model employs a neural network with a mixture of real and predicted values as input values.
The computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor to accomplish the present invention, for example. The one or more modules/units may be a series of computer program instruction segments capable of performing a predetermined function for describing the execution of the computer program in the domain countermeasure-based computer key parameter degradation prediction device. For example, the computer program may be partitioned into a model training module and a prediction module, wherein the true input branch model employs a neural network having a true value as an input value; the progressive learning branch model adopts a neural network taking a mixed value of a true value and a predicted value as an input value; the specific functions of each module are as follows, namely a model training module which is used for training a progressive learning branch model according to a real input branch model based on a domain countermeasure learning method; the prediction module is used for predicting the degradation trend of the key parameters of the computer by using the trained progressive learning branch model; the real input branch model adopts a neural network taking a real value as an input value; the progressive learning branch model employs a neural network with a mixture of real and predicted values as input values.
The domain countermeasure-based computer key parameter degradation prediction device can be a computing device such as a desktop computer, a notebook computer, a palm computer and a cloud server. The domain countermeasure-based computer key parameter degradation prediction device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the foregoing is an example of a domain countermeasure-based computer key parameter degradation prediction device, and is not limiting of the domain countermeasure-based computer key parameter degradation prediction device, and may include more components than those described above, or may combine certain components, or different components, e.g., the domain countermeasure-based computer key parameter degradation prediction device may also include an input output device, a network access device, a bus, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the domain countermeasure-based computer key parameter degradation prediction, and various interfaces and lines are used to connect various parts of the entire domain countermeasure-based computer key parameter degradation prediction device.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the domain-countermeasure-based computer key parameter degradation prediction device by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
The present invention also provides a computer readable storage medium storing a computer program which when executed by a processor implements the steps of the domain countermeasure-based computer key parameter degradation prediction method.
The modules/units integrated with the domain-countermeasure-based computer key parameter degradation prediction system may be stored in a computer-readable storage medium if implemented in the form of software functional units and sold or used as a stand-alone product.
Based on such understanding, the present invention may implement all or part of the above-mentioned process of predicting the degradation of the critical parameter of the domain countermeasure, or may be implemented by instructing the relevant hardware by a computer program, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of the above-mentioned predicting the degradation of the critical parameter of the domain countermeasure when being executed by a processor. The computer program comprises computer program code, and the computer program code can be in a source code form, an object code form, an executable file or a preset intermediate form and the like.
The computer readable storage medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
It should be noted that the computer readable storage medium may include content that is subject to appropriate increases and decreases as required by jurisdictions and by jurisdictions in which such computer readable storage medium does not include electrical carrier signals and telecommunications signals.
Examples
In order to solve the technical problem that the accuracy of medium-long-term degradation prediction cannot be guaranteed due to error accumulation in cyclic prediction in the existing prediction method mentioned in the background art, the embodiment provides a computer key parameter degradation prediction method based on domain countermeasure, the prediction method provided by the embodiment adopts a network structure with two branches, one branch adopts a progressive learning training method, a model is trained by combining a true value input and a predicted value output, and the duty ratio of iterative input of the predicted value is gradually improved in the training process; the other branch is always trained with true value inputs. In order to enable the time sequence features of two branch training to be close, a domain antagonism learning mode is adopted, and the network implicit features of the two branches can be close to each other, so that the branches using the progressive learning method can learn more to the real time sequence value, and the accuracy of prediction is further improved. By the training mode, long-term prediction of the key parameters of the computer can be realized more accurately.
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
the embodiment provides a computer key parameter degradation prediction method based on domain countermeasure, which comprises the following steps:
first, key component selection and data preprocessing: selecting key characterization parameters with long-term degradation tendency, and preprocessing data; the time series data is divided into time series batch data corresponding to the network input length, and the time series batch data are processed in batches.
Secondly, adopting a double-branch network structure (model) in network training, and learning and training from a progressive learning branch model to a real input branch model, wherein the method specifically comprises the following steps:
as shown in fig. 1, in the training process, a branch is trained in a progressive learning mode by adopting mixed input of a true value and a predicted value. The other branch always uses the true value for training. In the training process, the features extracted from the two branches are subjected to domain countermeasure learning, so that the generated features cannot be judged to come from progressive learning branches or true value branches, domain confusion is carried out in hidden layer space, and finally hidden layer distribution of the two branches is similar.
For progressive learning branches, the input of the true value is relatively high and the input of the predicted value is relatively low at the beginning of training. The model is trained by taking the true value y as input at first, and the predicted value is gradually increased in the training processAs the training number increases, the true value duty ratio gradually decreases and the predicted value input duty ratio gradually increases until the branch uses the network predicted value as the loop input. While for the other branch, training is always performed using the true value. In order to avoid overlarge difference between the effect of progressive learning branches in the learning process and the effect of learning by adopting a true value, a domain transfer (domain countermeasure) learning method is adopted, so that the hidden state features in the sequence learning process are close to each other; the process is specifically shown in fig. 3, wherein the RNN layer represents that in the process of progressively learning input data of branch training learning, a predicted value is input according to the probability of p, and a true value is input according to the probability of (1-p). The value range of p is 0-1. As the number of training iterations increases, p gradually increases from 0 until training ends p is set to 1.
As shown in fig. 2, the present figure clearly illustrates the process of domain antagonism of the change in the data distribution in the learning process. The dashed line P (x) is the hidden layer data distribution learned by the real input branch, which remains unchanged during the training process. The solid line G (z) is the data distribution produced by the progressive learning branch in the countermeasure training. The compact dotted line D (x) represents the discriminant function.
In fig. 2 (a) a sample distribution immediately after the start of the countermeasure training is represented, the hidden layer data distribution G (z) of the progressive learning branch and the true input branch P (x) are greatly different. The discriminant function D (x) can accurately output a relatively large value for the true data on the left, while producing a relatively small value for the false data on the right. However, as the number of training increases, it can be seen from fig. 2 (b) and 2 (c) that the G (z) distribution curve is gradually approaching the true distribution P (x). In fig. 2 (d), the sample distribution and the real data distribution generated by the generator have completely overlapped. The discriminant function D (x) outputs the same value for all data (whether true or generated), and cannot be classified correctly. By means of the countermeasure training mode, the progressive learning branch network successfully learns the real data distribution.
In the training process, the gradual learning branch is learned to the true value branch by a domain countermeasure learning method, so that the accumulation of prediction errors under the condition of multi-step prediction is avoided, and the long-term prediction result is more accurate
Thirdly, predicting degradation trend of the key parameters of the computer by using a trained and learned progressive learning branch model:
in the test process, the prediction of the long-term degradation trend can be realized by only using a trained progressive learning branch model. During the test, the true value input branches and the domain countermeasure sub-modules are no longer involved in the operation.
By adopting the domain countermeasure-based computer key parameter degradation prediction method provided by the embodiment, the mainboard voltage change of one of the computer key characterization is analyzed.
And collecting degradation trend of the main board voltage parameters in the embedded computers, and predicting the degradation trend. In the long-term prediction process (taking a day as a unit interval), accurate trend prediction for more than 512 days can be realized, the degradation data estimation accuracy is not less than 90%, the degradation trend is more truly represented, and the problem of low prediction accuracy caused by error accumulation in cyclic iteration prediction is solved.
Compared with the existing prediction measures, the computer key parameter degradation prediction method based on domain countermeasure provided by the embodiment has the following advantages:
the method learns the degradation trend of the parameters of the key parts of the computer, adopts a two-branch structure, gradually adds the predicted value into a training sample in the gradual learning branch, and improves the proportion; by means of domain antagonism, the hidden layer distribution difference of two branches is reduced. In the training process, the real value input branch is always used for guiding the learning of the progressive learning branch, and finally, the degradation trend of the computer is predicted in a cyclic and iterative mode, so that the accumulated error of the predicted value output can be reduced. The prediction method improves the long-term property of prediction, is convenient for timely arranging the maintenance work of the electronic system, and ensures the reliability of the computer work.
The above embodiment is only one of the implementation manners capable of implementing the technical solution of the present invention, and the scope of the claimed invention is not limited to the embodiment, but also includes any changes, substitutions and other implementation manners easily recognized by those skilled in the art within the technical scope of the present invention.
Claims (10)
1. A method for predicting degradation of a key parameter of a computer based on domain countermeasure, comprising:
training a progressive learning branch model according to a real input branch model based on a domain countermeasure learning method;
predicting the degradation trend of the key parameters of the computer by using the trained progressive learning branch model;
the real input branch model adopts a neural network taking a real value as an input value; the progressive learning branch model employs a neural network with a mixture of real and predicted values as input values.
2. The domain countermeasure-based computer key parameter degradation prediction method according to claim 1, wherein the specific step of building the true input branch model comprises the following steps:
acquiring key characterization parameters with long-term degradation trend, and preprocessing the acquired key characterization parameters; constructing and training a neural network according to the preprocessed key characterization parameters to obtain a real input branch model; in the training process of the true input branch model, the input values of each iteration all adopt the true values.
3. The domain countermeasure-based computer key parameter degradation prediction method according to claim 2, wherein the specific step of building a progressive learning branch model comprises:
constructing a neural network according to the preprocessed key characterization parameters; in the training process of the progressive learning branch model, a mixed value of a true value and a predicted value is used as an input value of each iteration.
4. A method for predicting degradation of a key parameter in a computer based on domain antagonism according to claim 3, wherein the ratio of the predicted value in the mixed value is gradually increased with the number of iterations in the training process of the progressive learning branch model.
5. The domain countermeasure-based computer key parameter degradation prediction method according to claim 4, wherein the input ratio of the predicted value is gradually increased in the process of training the progressive learning branch model, the input of the predicted value is gradually increased from 0 to 100%, and the ratio increase rate is proportional to the iteration number.
6. The domain countermeasure-based computer key parameter degradation prediction method of claim 2, wherein in the process of preprocessing key characterization parameters, time series data is divided into time series batch data corresponding to network input lengths, and the time series batch data is processed in batches.
7. The domain countermeasure-based computer key parameter degradation prediction method of claim 1, wherein the computer key parameter is a motherboard voltage parameter.
8. A domain countermeasure-based computer critical parameter degradation prediction system for implementing the steps of the domain countermeasure-based computer critical parameter degradation prediction method as claimed in any of claims 1 to 7, comprising:
the model training module is used for training the progressive learning branch model according to the real input branch model based on the domain countermeasure learning method;
the prediction module is used for predicting the degradation trend of the key parameters of the computer by using the trained progressive learning branch model;
the real input branch model adopts a neural network taking a real value as an input value; the progressive learning branch model employs a neural network with a mixture of real and predicted values as input values.
9. An apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the domain countermeasure-based computer key parameter degradation prediction method of any one of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium storing a computer program, characterized in that the computer program is executed by a processor for implementing the steps of the domain countermeasure based computer key parameter degradation prediction method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310923651.7A CN116776743A (en) | 2023-07-25 | 2023-07-25 | Computer key parameter degradation prediction method based on domain countermeasure and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310923651.7A CN116776743A (en) | 2023-07-25 | 2023-07-25 | Computer key parameter degradation prediction method based on domain countermeasure and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116776743A true CN116776743A (en) | 2023-09-19 |
Family
ID=87987954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310923651.7A Pending CN116776743A (en) | 2023-07-25 | 2023-07-25 | Computer key parameter degradation prediction method based on domain countermeasure and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116776743A (en) |
-
2023
- 2023-07-25 CN CN202310923651.7A patent/CN116776743A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109542399B (en) | Software development method and device, terminal equipment and computer readable storage medium | |
| US20210209410A1 (en) | Method and apparatus for classification of wafer defect patterns as well as storage medium and electronic device | |
| US11372388B2 (en) | Locking error alarm device and method | |
| CN108197652A (en) | For generating the method and apparatus of information | |
| CN111882038A (en) | Model conversion method and device | |
| CN110968339B (en) | Method and device for front-end building tool and electronic equipment | |
| CN111859933A (en) | Training method, recognition method, device and equipment of Malay recognition model | |
| CN116776743A (en) | Computer key parameter degradation prediction method based on domain countermeasure and related equipment | |
| DE112020003537T5 (en) | UNSUPERVISED CONCEPT DEVELOPMENT AND CROSS-MODAL RECOVERY IN TIME SERIES AND TEXT COMMENTS BASED ON CANONICAL CORRELATION ANALYSIS | |
| CN115935822A (en) | Method, system, device and medium for predicting long-term degradation trend of computer parameters | |
| CN115470900A (en) | Pruning method, device and equipment of neural network model | |
| US11442650B2 (en) | Generating predicted usage of storage capacity | |
| CN113627611A (en) | Model training method and device, electronic equipment and storage medium | |
| CN111966592A (en) | Front-end page testing method, device, medium and electronic equipment | |
| CN111768220A (en) | Method and apparatus for generating vehicle pricing models | |
| CN111160969A (en) | Power price prediction method and device | |
| US20220253997A1 (en) | Image defect detection method, electronic device using the same | |
| CN116341640B (en) | Text processing model training method and device | |
| CN118095426B (en) | Click behavior prediction model training method and device, electronic equipment and readable medium | |
| CN113435058B (en) | Data dimension reduction method, system, terminal and medium for distribution network self-healing test model | |
| CN115310616B (en) | Method for measuring quantum disturbance and electronic equipment | |
| CN113791391B (en) | Interference characteristic parameter identification method, device, storage and equipment | |
| CN112952800B (en) | Method and device for acquiring segmentation evaluation indexes of transient stability level of power grid | |
| CN110782942B (en) | Quality control method, device and storage medium in metabonomics | |
| CN111625526A (en) | Fuzzy data processing method and system and terminal equipment |
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 |