CN114004276A - Time feature processing method and processing device - Google Patents
Time feature processing method and processing device Download PDFInfo
- Publication number
- CN114004276A CN114004276A CN202111138437.8A CN202111138437A CN114004276A CN 114004276 A CN114004276 A CN 114004276A CN 202111138437 A CN202111138437 A CN 202111138437A CN 114004276 A CN114004276 A CN 114004276A
- Authority
- CN
- China
- Prior art keywords
- data set
- machine learning
- time characteristics
- classification
- clustering
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a processing method and a processing device of time characteristics, wherein the method comprises the following steps: after converting the time characteristics in the training data set into decimal numerical time characteristics, clustering the training data set by adopting a clustering algorithm, and outputting a clustering result; performing machine learning on the time characteristics and the clustering result by adopting at least one machine learning algorithm for classification; verifying the accuracy of the output result of the machine learning algorithm by adopting a cross verification data set until a classification model meeting the requirements is trained; and converting the time characteristics in the test data set into decimal numerical time characteristics, and inputting the decimal numerical time characteristics into the classification model so that the classification model outputs a classification result. The invention converts the time characteristic data into decimal numerical data and then learns, can solve the problem caused by special form, and learns the time characteristic from the training data set and the test data set in two directions, and can obviously improve the accuracy of the learning model.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a time characteristic processing method and a time characteristic processing device.
Background
Currently, in the industrial field, there are many scenarios in which the corresponding parameters are predicted according to the input feature data by using a machine learning or deep learning algorithm, for example, in the scenario of a wind-solar-energy storage power station, the output of the power station is predicted according to the input feature data by using the machine learning or deep learning algorithm which is most frequently used and studied.
However, in designing machine learning and deep learning algorithms, the input features of many scenes are time features, for example, the input features of energy storage power stations are mostly meteorological features such as wind speed, irradiance, air temperature, air pressure, humidity and the like, the values of the features have large fluctuation and are in a coupling relation with each other, in this case, the only absolutely accurate and quantized feature is the data acquisition time, and the change of other individual features and required predicted values along with time can be reflected.
However, in the data types, the time feature is a very special type, and although the implicit information is more, the date in the time feature is formed by year, month and day, and the time is formed by hour, minute and second, which are not decimal manners adopted by other numerical data. In this case, if the time characteristics are directly input into the machine learning model and the deep learning model as the characteristics for training, the model cannot judge the difference between the time characteristics and other decimal numerical characteristics, so that the model training fails or the prediction accuracy of the model is greatly reduced.
Disclosure of Invention
In order to solve the above technical problems, a first object of the present invention is to provide a method for processing time characteristics, which converts time characteristic data into decimal numerical data and then learns the decimal numerical data, so as to solve the problems caused by the special form of the decimal numerical data, and learns the time characteristics from a training data set and a test data set in a bidirectional manner by using a machine learning model, so as to mine implicit information of the time characteristics in various oriented prediction scenes, and further improve the accuracy of predicting parameters by using machine learning or deep learning according to the time characteristics.
A second object of the invention is to propose a processing device of temporal characteristics.
The technical scheme adopted by the invention is as follows:
an embodiment of the first aspect of the present invention provides a method for processing time characteristics, including the following steps: acquiring a data set, wherein the data set comprises a time characteristic and a parameter predicted value corresponding to the time characteristic, and the time characteristic comprises date and time; dividing the dataset into a training dataset, a cross-validation dataset, and a test dataset; after converting the time characteristics in the training data set into decimal numerical time characteristics, clustering the training data set by adopting a clustering algorithm, and outputting a clustering result; performing machine learning on the time characteristics and the clustering result by adopting at least one machine learning algorithm for classification; verifying the accuracy of the output result of the machine learning algorithm by adopting the cross verification data set, and adjusting the parameters of the machine learning algorithm according to the accuracy until the machine learning algorithm trains a classification model meeting the requirements; and after converting the time characteristics in the test data set into decimal numerical time characteristics, inputting the time characteristics into the classification model so that the classification model outputs a classification result.
The processing method of the time characteristic proposed by the invention can also have the following additional technical characteristics:
according to an embodiment of the present invention, the dividing the data set into a training data set, a cross-validation data set, and a testing data set specifically includes: 60% of the data set was taken as training data set, 20% as cross-validation data set, and 20% as test data set.
According to one embodiment of the invention, the clustering algorithm comprises a K-means clustering algorithm.
According to one embodiment of the present invention, the machine learning algorithm for classification includes three.
According to one embodiment of the invention, the machine learning algorithm for classification comprises: support vector machines, GBDT (Gradient Boosting Decision Tree) classification, and logistic regression.
An embodiment of the second aspect of the present invention provides a processing apparatus for time characteristics, including: the system comprises an acquisition module, a comparison module and a processing module, wherein the acquisition module is used for acquiring a data set and dividing the data set into a training data set, a cross validation data set and a test data set, the data set comprises time characteristics and parameter predicted values corresponding to the time characteristics, and the time characteristics comprise date and time; the conversion module is used for clustering the training data set by adopting a clustering algorithm after converting the time characteristics in the training data set into decimal numerical time characteristics and outputting a clustering result; a machine learning module for machine learning the temporal features and the clustering results using at least one machine learning algorithm for classification; the training module is used for verifying the accuracy of the output result of the machine learning algorithm by adopting the cross verification data set and adjusting the parameters of the machine learning algorithm according to the accuracy until the machine learning algorithm trains a classification model meeting the requirements; and the processing module is used for converting the time characteristics in the test data set into decimal numerical time characteristics and then inputting the time characteristics into the classification model so as to enable the classification model to output a classification result.
The processing device for the time characteristics provided by the invention can also have the following additional technical characteristics:
according to an embodiment of the present invention, the obtaining module is specifically configured to: 60% of the data set was taken as training data set, 20% as cross-validation data set, and 20% as test data set.
According to one embodiment of the invention, the clustering algorithm comprises a K-means clustering algorithm.
According to one embodiment of the present invention, the machine learning algorithm for classification includes three.
According to one embodiment of the invention, the machine learning algorithm for classification comprises: support vector machines, GBDT classification, and logistic regression.
The invention has the beneficial effects that:
the invention converts the time characteristic data into decimal numerical data and then learns, can solve the problem caused by special form, and learns the time characteristic bidirectionally from the training data set and the test data set by adopting a machine learning model, can mine the implicit information of the time characteristic in various oriented prediction scenes, and further can improve the accuracy degree of predicting the parameters by using machine learning or deep learning according to the time characteristic.
Drawings
FIG. 1 is a flow diagram of a method of processing temporal signatures in accordance with one embodiment of the present invention.
FIG. 2 is a functional block diagram of a method of processing temporal signatures according to one embodiment of the present invention;
FIG. 3 is a block schematic diagram of a processing device for temporal characterization according to one embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
FIG. 1 is a flow diagram of a method of processing temporal signatures in accordance with one embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
and S1, acquiring a data set, wherein the data set comprises a time characteristic and a parameter predicted value corresponding to the time characteristic, and the time characteristic comprises date and time.
For example, taking the output data table of a certain energy storage power station as an example, the data set can be shown in table 1 below:
TABLE 1
It is understood that table 1 is only a partial data showing the data set, and the data of the actual application scenario data set should include a large amount of live data. The output in table 1 is the predicted value of the parameter.
S2, the data set is divided into a training data set, a cross validation data set and a test data set.
In one embodiment of the invention, 60% of the data set is taken as the training data set, 20% as the cross-validation data set, and 20% as the test data set.
And S3, converting the time characteristics in the training data set into decimal numerical time characteristics, clustering the training data set by adopting a clustering algorithm, and outputting a clustering result.
Further, in one embodiment of the present invention, the clustering algorithm comprises a K-means clustering algorithm.
Specifically, for the data set of table 1, the data obtained by converting the time characteristics (including the date and time) into decimal numeric data is shown in table 2 below:
TABLE 2
On the basis of converting the time characteristics (including date and time) into decimal numerical data, clustering is carried out on the training data set by adopting a K-means clustering algorithm (K-means), and a column of clustering result columns are added in the test data set to record clustering results, as shown in the following table 3:
TABLE 3
And clustering the training data set according to a K-means clustering algorithm, wherein the data are clustered into 2 types, which respectively represent the conditions of no output and output of the energy storage power station, and preliminarily reflect whether the energy storage power station has output at different moments, the clustering result of 0 represents that the energy storage power station has no output at the moments, and the clustering result of 1 represents that the energy storage power station has output at the moments.
And S4, performing machine learning on the time characteristics and the clustering result by adopting at least one machine learning algorithm for classification.
Further, in one embodiment of the present invention, the machine learning algorithm for classification may include three, for example, the machine learning algorithm for classification includes: support Vector Machines (SVM), GBDT classification, and Logistic Regression.
Specifically, three machine learning algorithms special for classification are adopted to perform machine learning on the time characteristics and the clustering result, and the three machine learning algorithms are respectively a support vector machine, GBDT classification and logistic regression. The three machine learning algorithms can improve the accuracy of judging the relation between the time characteristic and the output result and classifying the time characteristic and the output result.
And S5, verifying the accuracy of the output result of the machine learning algorithm by adopting the cross verification data set, and adjusting the parameters of the machine learning algorithm according to the accuracy until the machine learning algorithm trains a classification model meeting the requirements.
Specifically, the accuracy of output results of the trained three machine learning algorithms is verified respectively by adopting a cross verification data set, and parameters of the three machine learning algorithms are adjusted until the three algorithms can train a classification model meeting requirements.
And S6, converting the time characteristics in the test data set into decimal numerical time characteristics, and inputting the time characteristics into the classification model so that the classification model outputs a classification result.
Specifically, the conversion of the time characteristics of the test data set into decimal numerical data may be as shown in Table 4 below:
TABLE 4
The time characteristics, namely the "time (value)" in table 4 above, are sent to the three trained classification models respectively, the output prediction result is whether there is output, the prediction results output by the three classification models adopt a voting mechanism, the classification with high voting rate is determined classification, wherein the classification result is 0, which means no output, and the classification result is 1, which means output. As shown in table 5 below:
TABLE 5
Therefore, the digitization processing and the classification processing of the time characteristics are completed, the output digitization time data and the classification result can be used for parameter prediction of other scenes, and the classification result is the classification result with the time characteristics.
In the embodiment of the invention, the existence of the output is represented as 0 and 1, and for other scenes, the clustering result of the training data set can be classified more according to the K-means clustering algorithm, so that the time granularity suitable for the predicted value is automatically judged.
In order to make the present invention more clearly understood by those skilled in the art, the following describes the processing method of the time characteristic of the present invention with reference to the block diagram shown in fig. 2.
As shown in fig. 2, after the data set is obtained, the data set is divided into a training data set, a cross validation data set and a test data set, wherein after the time characteristics in the training data set are converted into decimal numerical time characteristics, the training data set is clustered by adopting a K-means clustering algorithm, and a clustering result is output.
The method comprises the steps of performing machine learning on time characteristics and clustering results by three machine learning algorithms which are specially used for classification, namely a support vector machine, a GBDT classification algorithm and a logistic regression algorithm, simultaneously verifying the accuracy of output results of the three machine learning algorithms by adopting a cross verification data set, and adjusting parameters of the three machine learning algorithms until the support vector machine, the GBDT classification algorithm and the logistic regression algorithm can train classification models which meet requirements, namely a support vector machine model, the GBDT model and the logistic regression model which meet the requirements are trained. And converting the time characteristics in the test data set into decimal numerical time characteristics, inputting the decimal numerical time characteristics into the trained classification model, outputting a prediction result output by the classification model by adopting a voting mechanism, classifying the voting height into a determined classification, and outputting a classification result.
In summary, according to the processing method of the time characteristic in the embodiment of the present invention, the time characteristic data is converted into the decimal numerical data and then learned, so that the problem caused by the special form of the time characteristic data can be solved, and the time characteristic is learned bidirectionally from the training data set and the testing data set by using a machine learning model, so that the implicit information of the time characteristic in various oriented prediction scenes can be mined, and the accuracy of predicting the parameter by using machine learning or deep learning according to the time characteristic can be further improved.
Corresponding to the time characteristic processing method, the invention also provides a time characteristic processing device. Since the device embodiment of the present invention corresponds to the method embodiment described above, details that are not disclosed in the device embodiment may refer to the method embodiment described above, and are not described again in the present invention.
FIG. 3 is a block schematic diagram of a processing device for temporal characterization according to one embodiment of the present invention. As shown in fig. 3, the apparatus includes: an acquisition module 1, a transformation module 2, a machine learning module 3, a training module 4 and a processing module 5, wherein,
the acquisition module 1 is used for acquiring a data set and dividing the data set into a training data set, a cross validation data set and a test data set, wherein the data set comprises time characteristics and parameter predicted values corresponding to the time characteristics, the time characteristics comprise dates and moments, and the conversion module 2 is used for clustering the training data set by adopting a clustering algorithm after converting the time characteristics in the training data set into decimal numerical time characteristics and outputting clustering results; the machine learning module 3 is used for performing machine learning on the time characteristics and the clustering result by adopting at least one machine learning algorithm for classification; the training module 4 is used for verifying the accuracy of the output result of the machine learning algorithm by adopting a cross verification data set and adjusting the parameters of the machine learning algorithm according to the accuracy until the machine learning algorithm trains a classification model meeting the requirements; the processing module 5 is used for converting the time characteristics in the test data set into decimal numerical time characteristics and then inputting the decimal numerical time characteristics into the classification model so that the classification model outputs a classification result.
According to an embodiment of the present invention, the obtaining module 1 is specifically configured to: 60% of the data set was taken as the training data set, 20% as the cross-validation data set, and 20% as the test data set.
According to one embodiment of the invention, the clustering algorithm comprises a K-means clustering algorithm.
According to one embodiment of the present invention, the machine learning algorithm for classification includes three.
According to one embodiment of the invention, a machine learning algorithm for classification includes: support vector machines, GBDT classification, and logistic regression.
In summary, according to the processing apparatus for time characteristics in the embodiment of the present invention, the time characteristic data is converted into decimal numerical data and then learned, so that the problem caused by a special form can be solved, and the time characteristics are learned bidirectionally from the training data set and the testing data set by using a machine learning model, so that implicit information of the time characteristics in various oriented prediction scenes can be mined, and the accuracy of predicting parameters by using machine learning or deep learning according to the time characteristics can be further improved.
In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The meaning of "plurality" is two or more unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A processing method of time characteristics is characterized by comprising the following steps:
acquiring a data set, wherein the data set comprises a time characteristic and a parameter predicted value corresponding to the time characteristic, and the time characteristic comprises date and time;
dividing the dataset into a training dataset, a cross-validation dataset, and a test dataset;
after converting the time characteristics in the training data set into decimal numerical time characteristics, clustering the training data set by adopting a clustering algorithm, and outputting a clustering result;
performing machine learning on the time characteristics and the clustering result by adopting at least one machine learning algorithm for classification;
verifying the accuracy of the output result of the machine learning algorithm by adopting the cross verification data set, and adjusting the parameters of the machine learning algorithm according to the accuracy until the machine learning algorithm trains a classification model meeting the requirements;
and after converting the time characteristics in the test data set into decimal numerical time characteristics, inputting the time characteristics into the classification model so that the classification model outputs a classification result.
2. The method for processing temporal features according to claim 1, wherein the dividing of the dataset into a training dataset, a cross-validation dataset, and a test dataset specifically comprises:
60% of the data set was taken as training data set, 20% as cross-validation data set, and 20% as test data set.
3. The method of processing temporal features of claim 1, wherein the clustering algorithm comprises a K-means clustering algorithm.
4. The method of processing temporal features of claim 1, wherein the machine learning algorithm for classification comprises three.
5. The method of processing temporal features of claim 4, wherein the machine learning algorithm for classification comprises: support vector machines, GBDT classification, and logistic regression.
6. A device for processing temporal characteristics, comprising:
the system comprises an acquisition module, a comparison module and a processing module, wherein the acquisition module is used for acquiring a data set and dividing the data set into a training data set, a cross validation data set and a test data set, the data set comprises time characteristics and parameter predicted values corresponding to the time characteristics, and the time characteristics comprise date and time;
the conversion module is used for clustering the training data set by adopting a clustering algorithm after converting the time characteristics in the training data set into decimal numerical time characteristics and outputting a clustering result;
a machine learning module for machine learning the temporal features and the clustering results using at least one machine learning algorithm for classification;
the training module is used for verifying the accuracy of the output result of the machine learning algorithm by adopting the cross verification data set and adjusting the parameters of the machine learning algorithm according to the accuracy until the machine learning algorithm trains a classification model meeting the requirements;
and the processing module is used for converting the time characteristics in the test data set into decimal numerical time characteristics and then inputting the time characteristics into the classification model so as to enable the classification model to output a classification result.
7. The temporal feature processing apparatus according to claim 6, wherein the obtaining module is specifically configured to: 60% of the data set was taken as training data set, 20% as cross-validation data set, and 20% as test data set.
8. The processing apparatus of temporal features according to claim 6, wherein the clustering algorithm comprises a K-means clustering algorithm.
9. The temporal feature processing apparatus according to claim 6, wherein the machine learning algorithm for classification includes three.
10. The temporal feature processing apparatus according to claim 9, wherein the machine learning algorithm for classification comprises: support vector machines, GBDT classification, and logistic regression.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111138437.8A CN114004276A (en) | 2021-09-27 | 2021-09-27 | Time feature processing method and processing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111138437.8A CN114004276A (en) | 2021-09-27 | 2021-09-27 | Time feature processing method and processing device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114004276A true CN114004276A (en) | 2022-02-01 |
Family
ID=79921754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111138437.8A Pending CN114004276A (en) | 2021-09-27 | 2021-09-27 | Time feature processing method and processing device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114004276A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114898484A (en) * | 2022-05-24 | 2022-08-12 | 珠海格力电器股份有限公司 | Method for awakening intelligent door lock, sensor, intelligent door lock and electronic equipment |
-
2021
- 2021-09-27 CN CN202111138437.8A patent/CN114004276A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114898484A (en) * | 2022-05-24 | 2022-08-12 | 珠海格力电器股份有限公司 | Method for awakening intelligent door lock, sensor, intelligent door lock and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11688056B2 (en) | Method for predicting defects in assembly units | |
| CN102792332B (en) | Image management apparatus, image management method and integrated circuit | |
| CN111353555A (en) | Label detection method and device and computer readable storage medium | |
| CN105676670B (en) | For handling the method and system of multi-energy data | |
| CN105070321B (en) | The quick test circuit and method of memory device | |
| EP3690658B1 (en) | Method for detecting repair-necessary motherboards and device using the method | |
| CN111291783A (en) | Intelligent fault diagnosis method, system, terminal and storage medium for gas pressure regulating equipment | |
| CN108985489A (en) | A kind of Risk Forecast Method, risk profile device and terminal device | |
| CN116186548B (en) | Power load prediction model training method and power load prediction method | |
| WO2016195897A1 (en) | System for analytic model development | |
| CN116075733A (en) | Battery management system for classifying battery modules | |
| CN114004276A (en) | Time feature processing method and processing device | |
| CN116453438A (en) | Display screen parameter detection method, device, equipment and storage medium | |
| CN110334720A (en) | Feature extracting method, device, server and the storage medium of business datum | |
| CN113886627A (en) | Mobile communication system based on information synchronization | |
| Huang et al. | Prediction and evaluation of health state for power battery based on Ridge linear regression model | |
| CN110717623B (en) | Photovoltaic power generation power prediction method, device and equipment integrating multiple weather conditions | |
| CN111797195A (en) | Accessory name identification method and device, computer equipment and storage medium | |
| CN114757097B (en) | Line fault diagnosis method and device | |
| CN115423159A (en) | Photovoltaic power generation prediction method and device and terminal equipment | |
| CN115146822A (en) | Photovoltaic power generation prediction method and device and terminal equipment | |
| CN115049374A (en) | Data processing method and device for process equipment | |
| CN113994276A (en) | Method for verifying system parameters of an energy system, method for operating an energy system, and energy management system for an energy system | |
| Al Khafaf et al. | Identification of low voltage distribution transformer–customer connectivity based on unsupervised learning | |
| US20240231300A1 (en) | Automatic optimization framework for safety-critical systems of interconnected subsystems |
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 |