CN114330533A - Equipment screen aging two-classification model training method and equipment screen aging detection method - Google Patents
Equipment screen aging two-classification model training method and equipment screen aging detection method Download PDFInfo
- Publication number
- CN114330533A CN114330533A CN202111601098.2A CN202111601098A CN114330533A CN 114330533 A CN114330533 A CN 114330533A CN 202111601098 A CN202111601098 A CN 202111601098A CN 114330533 A CN114330533 A CN 114330533A
- Authority
- CN
- China
- Prior art keywords
- aging
- attribute information
- screen
- classification model
- data
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a device screen aging two-classification model training method and a device screen aging detection method. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
Description
Technical Field
The invention relates to the technical field of electronic products, in particular to a training method of a two-classification model of equipment screen aging and an equipment screen aging detection method.
Background
With the development of electronic product technology, various intelligent devices such as smart phones, notebook computers, tablet computers, and the like are developed. At present, along with the rapid development of economy and technology, the popularization and the updating speed of intelligent equipment are also faster and faster. Taking a smart phone as an example, the coming of the 5G era accelerates the generation change of the smart phone. In the iterative process of the intelligent equipment, effective recovery is one of effective utilization means of the residual value of the intelligent equipment, and the chemical pollution to the environment and the waste can be reduced.
The screen is used as a display and man-machine interaction part of the intelligent device, and has a remarkable influence on the recycling evaluation of the intelligent device. Especially, the aging of the screen of the device can seriously affect the experience of subsequent users, thereby affecting the recycling value. Therefore, in the process of recovering the smart device, whether the screen of the smart device has an aging phenomenon needs to be detected.
The traditional mode for detecting the screen aging of the equipment is to set a screen display ground color and adjust light, and then carry out image detection on the equipment screen by shooting the equipment screen to identify whether the equipment screen is aged or not. However, if there is a light problem, a camera problem or a device screen becomes dark in the process of detecting and shooting, a missing judgment phenomenon is easily caused, and the accuracy of the device screen aging detection is affected.
Disclosure of Invention
Therefore, it is necessary to provide a device screen aging two-classification model training method and a device screen aging detection method for overcoming the defects of the traditional method for detecting the device screen aging.
A training method for a device screen aging binary model comprises the following steps:
acquiring aging attribute information of each intelligent device; wherein, part of the intelligent equipment is aged, and the other part of the intelligent equipment is not aged;
vectorizing the aging attribute information to obtain vectorized data;
and taking the vectorization data and whether the corresponding intelligent equipment is aged as training data, and training a binary classification model for detecting whether the equipment screen is aged.
According to the device screen aging two-classification model training method, after the aging attribute information of each intelligent device is obtained, the aging attribute information is vectorized to obtain vectorized data, and finally the aging attribute information and whether the corresponding intelligent device is aged or not are used as training data to train a two-classification model for detecting whether the device screen is aged or not. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
In one embodiment, before the process of vectorizing the aging attribute information to obtain vectorized data, the method further includes the steps of:
and carrying out data preprocessing on the aging attribute information.
In one embodiment, the process of performing data preprocessing on the aging attribute information includes the steps of:
and carrying out data cleaning processing, discretization, standardization or digitization on the aging attribute information.
In one embodiment, the classification model comprises a decision tree prediction model or a random forest prediction model.
In one embodiment, the classification model comprises a gradient boosting decision tree model;
in one embodiment, a process for training a binary model for detecting whether aging exists on a device screen by using vectorized data and whether aging exists in a corresponding intelligent device as training data includes the steps of:
setting parameters of a gradient lifting decision tree model, and initializing a weak learner;
calculating residual errors to obtain a best fit value so as to determine a final strong learner;
and substituting the training data into the final strong learner to obtain a two-classification output probability result.
In one embodiment, the process of calculating the residual error to find the best fit value includes the steps of:
and calculating residual errors according to a CART regression tree fitting algorithm to obtain the best fitting value.
In one embodiment, the aging attribute information includes a device factory time, a device type, a device selling price, a device battery use state, a device screen breakage degree, a device size, a device holder gender, or a device holder age.
A device screen aging two-classification model training device comprises:
the training information acquisition module is used for acquiring aging attribute information of each intelligent device; wherein, part of the intelligent equipment is aged, and the other part of the intelligent equipment is not aged;
the first vectorization module is used for vectorizing the aging attribute information to obtain vectorized data;
and the data training module is used for training a binary classification model for detecting whether the screen of the equipment is aged or not by taking the vectorization data and whether the intelligent equipment corresponding to the vectorization data is aged or not as training data.
According to the device screen aging two-classification model training device, after the aging attribute information of each intelligent device is obtained, the aging attribute information is vectorized to obtain vectorized data, and finally, the aging attribute information and whether the corresponding intelligent device is aged or not are used as training data to train the two-classification model for detecting whether the device screen is aged or not. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
A computer storage medium having computer instructions stored thereon, the computer instructions when executed by a processor implement the device screen aging two-classification model training method of any of the above embodiments.
The computer storage medium obtains aging attribute information of each intelligent device, then vectorizes the aging attribute information to obtain vectorized data, and finally trains a binary classification model for detecting whether the screen of the device is aged or not by taking the aging attribute information and whether the corresponding intelligent device is aged or not as training data. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
A computer device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the device screen aging two-classification model training method of any embodiment.
The computer device obtains aging attribute information of each intelligent device, then vectorizes the aging attribute information to obtain vectorized data, and finally trains a binary classification model for detecting whether the screen of the device is aged or not by taking the aging attribute information and whether the corresponding intelligent device is aged or not as training data. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
A method for detecting the aging of a device screen comprises the following steps:
acquiring aging attribute information of the intelligent equipment to be tested;
vectorizing the aging attribute information;
and inputting the vectorization result into a two-classification model to obtain an equipment screen aging detection result.
According to the method for detecting the screen aging of the equipment, after the aging attribute information of the intelligent equipment to be detected is obtained, the aging attribute information is vectorized, and finally the vectorized result is input into the two classification models to obtain the screen aging detection result of the equipment. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
In one embodiment, before the process of vectorizing the aging attribute information, the method further includes the steps of:
and carrying out data preprocessing on the aging attribute information.
An apparatus for detecting screen aging of a device, comprising:
the information acquisition module is used for acquiring aging attribute information of the intelligent equipment to be tested;
the second vectorization module is used for vectorizing the aging attribute information;
and the result output module is used for inputting the vectorization result into the two classification models to obtain an equipment screen aging detection result.
The device screen aging detection device vectorizes the aging attribute information after acquiring the aging attribute information of the intelligent device to be detected, and finally inputs the vectorized result into the two classification models to obtain the device screen aging detection result. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
A computer storage medium having stored thereon computer instructions which, when executed by a processor, implement the device screen degradation detection method of any of the above embodiments.
The computer storage medium is used for vectorizing the aging attribute information after the aging attribute information of the intelligent device to be tested is obtained, and finally inputting the vectorized result into the two classification models to obtain the device screen aging detection result. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
A computer device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the device screen aging detection method of any one of the embodiments.
After the aging attribute information of the intelligent device to be tested is obtained, the aging attribute information is vectorized, and finally the vectorized result is input into the two classification models to obtain the device screen aging detection result. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
Drawings
FIG. 1 is a flowchart of a device screen aging two-class model training method according to an embodiment;
FIG. 2 is a flowchart of a training method of a device screen aging two-class model according to another embodiment;
FIG. 3 is a block diagram of an apparatus screen aging two-class model training device according to an embodiment;
FIG. 4 is a flowchart of a method for detecting screen aging of a device according to an embodiment;
FIG. 5 is a block diagram of an apparatus screen degradation detection device according to an embodiment;
FIG. 6 is a schematic diagram of an internal structure of a computer according to an embodiment.
Detailed Description
For better understanding of the objects, technical solutions and effects of the present invention, the present invention will be further explained with reference to the accompanying drawings and examples. Meanwhile, the following described examples are only for explaining the present invention, and are not intended to limit the present invention.
The embodiment of the invention provides a training method for a two-classification model of equipment screen aging.
Fig. 1 is a flowchart of a training method of an apparatus screen aging two-class model according to an embodiment, and as shown in fig. 1, the training method of the apparatus screen aging two-class model according to an embodiment includes steps S100 to S102:
s100, acquiring aging attribute information of each intelligent device; wherein, part of the intelligent equipment is aged, and the other part of the intelligent equipment is not aged;
s101, vectorizing the aging attribute information to obtain vectorized data;
s102, taking the vectorization data and whether the corresponding intelligent equipment is aged as training data, and training a binary classification model for detecting whether the equipment screen is aged.
The aging attribute information is associated with the aging existence of the screen of the intelligent device, including the existence of the use state of the screen of the intelligent device, the attribute type of the intelligent device or the use habit of a user.
In one embodiment, the aging attribute information includes a device factory time, a device type, a device selling price, a device battery use state, a device screen breakage degree, a device size, a device holder gender, or a device holder age.
Meanwhile, whether the intelligent equipment is aged or not is used as class label data, and whether aged class output exists or not in subsequent two-class model training is carried out. Wherein, whether the intelligent equipment is aged or not refers to whether the screen of the intelligent equipment is aged or not. Such as: data 1 (aged), data 0 (non-aged) as class label data for our model.
In one embodiment, fig. 2 is a flowchart of a device screen aging two-classification model training method according to another embodiment, and as shown in fig. 2, before a process of vectorizing aging attribute information and obtaining vectorized data in step S101, the method further includes step S200:
and S200, performing data preprocessing on the aging attribute information.
And preprocessing the aging attribute information into data meeting the identification requirement of the subsequent binary model data by performing data preprocessing on the aging attribute information.
In one embodiment, the process of performing data preprocessing on the aging attribute information in step S200 includes the steps of:
carrying out data cleaning processing on the aging attribute information for years, comprising the following steps:
missing value processing: for the aging attribute information loss of the equipment factory time, calculating a factory time average value according to the same model of the equipment brand, and filling all missing values of the attribute with the value; for the attribute of age loss, an age mode is obtained to replace an age loss value according to the correlation between the model and the age;
abnormal value processing: for some types of equipment that have been out of stock or have a low sales volume, data for abnormal situations such as age exceeding a hundred digits or negative number may have its information discarded. And only one record is left for deduplication if the aging attribute information is repeated.
In one embodiment, the process of performing data preprocessing on the aging attribute information in step S200 includes the steps of:
and discretizing the aging attribute information.
Discretizing the aging attribute information, for example:
the delivery time of the intelligent equipment is dispersed according to the month which is accurate to the month and is away from the recovery time, and is renamed to the service life; the age of the device holder may be divided into five intervals of 1 (child: 3 to 10 years old), 2 (teenager: 11 to 22 years old), 3 (young: 23 to 35 years old), 4 (middle: 36 to 50 years old), and 5 (old: 51 and over years old). The service state of the equipment battery is divided into four ranges of healthy, good, generally poor and discrete according to the average consumption duration or the average temperature.
In one embodiment, the process of performing data preprocessing on the aging attribute information in step S200 includes the steps of:
the aging attribute information is normalized.
In one embodiment, since the data of the subsequent logistic regression model is numerical, the non-numerical data is mapped to numerical values in order to meet the input specification of the logistic regression model. For example, for the device screen type, which is aging attribute information, OLED is 1, LCD is 2; for the device battery usage status this property, health is 1, good is 2, typically 3, and bad is 4.
Normalization-for example: the attribute range of the equipment in use is large, which affects the calculation time length, so the equipment is standardized to make the interval between (0, 1).
And performing model training by taking the aging attribute information as a data set of the two-classification model. As a preferred embodiment, the data set is divided into a training set, a validation set and a test set according to a 7:1:2 ratio.
The two classification models for class output comprise a decision tree prediction model or a random forest prediction model.
As a better implementation mode, the two classification models adopt a gradient lifting decision tree model, and the gradient lifting decision tree model is improved according to the aging detection requirement.
In one embodiment, as shown in fig. 2, the process of training the binary classification model for detecting whether aging exists on the screen of the device in step S102, which uses the vectorized data and whether aging exists in the corresponding smart device as training data, includes steps S300 to S302:
s300, setting parameters of a gradient lifting decision tree model, and initializing a weak learner;
s301, calculating residual errors to obtain a best fitting value so as to determine a final strong learner;
and S302, substituting the training data into the final strong learner to obtain a two-classification output probability result.
As a preferred embodiment, the process of calculating the residual error to find the best fit value in step S301 includes the steps of:
and calculating residual errors according to a CART regression tree fitting algorithm to obtain the best fitting value.
The following explanation takes specific application examples as step S300 to step S302:
firstly, parameter setting is carried out:
learning rate lr: 0.01;
iteration number epoch: 50;
depth h of tree: 8;
initializing the weak learner as follows:
where P (Y ═ 1| x) is the probability that the sample x (training data) prediction is 1 (i.e., aging), the learner is initialized with a priori probabilities.
Calculating residual errors to obtain a best fit value:
a CART regression tree fitting data is established, a is 1,2.. a (where a is epoch 50), and a negative gradient (i.e., residual) of the loss function of the a-th tree is calculated for each sample i 1,2.. N:
then the residual error r obtained in the last step is usedaiAs a new label for a sample, there is data (x) for each sample i 1,2i，rai) Taking the regression tree as training data of the next iteration, carrying out CART regression fitting to obtain a new regression tree, wherein the corresponding leaf node region is RajJ, where J is 1,2aIs the number of leaf nodes corresponding to the jth tree.
And calculating the best fitting value of the leaf node, wherein the formula is as follows:
after the best fit value is calculated for each iteration, the strong learner is updated:
lr is the learning rate set in the first step, and overfitting of the binary model data is prevented.
Obtaining a final strong learner:
substituting the data of the test set into the final learner to obtain F (x), thereby calculating the class probability:
after the corresponding vectorization data is input into the finally obtained binary classification model, the probability that the output classification data is 1 or 0 is compared, and the type corresponding to the numerical value with higher probability is the output result, including aging and non-aging.
In the method for training the two-classification model for device screen aging according to any embodiment, after the aging attribute information of each intelligent device is obtained, the aging attribute information is vectorized to obtain vectorized data, and finally, the aging attribute information and whether the corresponding intelligent device is aged or not are used as training data to train the two-classification model for detecting whether the device screen is aged or not. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
The embodiment of the invention also provides a device for training the two classification models of equipment screen aging.
Fig. 3 is a block diagram of an apparatus screen aging two-class model training apparatus according to an embodiment, and as shown in fig. 3, the apparatus screen aging two-class model training apparatus according to an embodiment includes:
a training information obtaining module 100, configured to obtain aging attribute information of each intelligent device; wherein, part of the intelligent equipment is aged, and the other part of the intelligent equipment is not aged;
the first vectorization module 101 is configured to vectorize the aging attribute information to obtain vectorized data;
and the data training module 102 is used for training a binary classification model for detecting whether the screen of the device is aged or not by taking the vectorization data and whether the corresponding intelligent device is aged or not as training data.
According to the device screen aging two-classification model training device, after the aging attribute information of each intelligent device is obtained, the aging attribute information is vectorized to obtain vectorized data, and finally, the aging attribute information and whether the corresponding intelligent device is aged or not are used as training data to train the two-classification model for detecting whether the device screen is aged or not. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
The embodiment of the invention also provides a method for detecting the screen aging of the equipment.
Fig. 4 is a flowchart illustrating an apparatus screen degradation detection method according to an embodiment, and as shown in fig. 4, the apparatus screen degradation detection method according to an embodiment includes steps S300 to S302:
s300, acquiring aging attribute information of the intelligent device to be tested;
s301, vectorizing the aging attribute information;
s302, inputting the vectorization result into a two-classification model to obtain an equipment screen aging detection result.
According to the method for detecting the screen aging of the equipment, after the aging attribute information of the intelligent equipment to be detected is obtained, the aging attribute information is vectorized, and finally the vectorized result is input into the two classification models to obtain the screen aging detection result of the equipment. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
In one embodiment, before the process of vectorizing the aging attribute information, the method further includes the steps of:
and carrying out data preprocessing on the aging attribute information.
Through the data preprocessing in step S200, the aging attribute information is processed into output data meeting the data requirement of the binary model, and the class output is performed according to the binary model.
According to the method for detecting the screen aging of the equipment, after the aging attribute information of the intelligent equipment to be detected is obtained, the aging attribute information is vectorized, and finally the vectorized result is input into the two classification models to obtain the screen aging detection result of the equipment. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
The embodiment of the invention also provides a device for detecting the aging of the equipment screen.
Fig. 5 is a block diagram of an apparatus screen degradation detection device according to an embodiment, and as shown in fig. 5, the apparatus screen degradation detection device according to an embodiment includes:
the information acquisition module 200 is used for acquiring aging attribute information of the intelligent device to be tested;
a second vectorization module 201, configured to vectorize the aging attribute information;
and the result output module 202 is used for inputting the vectorization result into the two classification models to obtain the device screen aging detection result.
The device screen aging detection device vectorizes the aging attribute information after acquiring the aging attribute information of the intelligent device to be detected, and finally inputs the vectorized result into the two classification models to obtain the device screen aging detection result. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
The embodiment of the invention also provides a computer storage medium, wherein computer instructions are stored on the computer storage medium, and when the instructions are executed by a processor, the method for training the equipment screen aging two-classification model or the method for detecting the equipment screen aging of any embodiment is realized.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, the computer program can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), memory aging attribute information memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a RAM, a ROM, a magnetic or optical disk, or various other media that can store program code.
Corresponding to the computer storage medium, in an embodiment, there is also provided a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any one of the device screen aging two-classification model training method or the device screen aging detection method in the above embodiments.
The computer device may be a terminal, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a device screen aging two-classification model training method or a device screen aging detection method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
The computer device obtains aging attribute information of each intelligent device, then vectorizes the aging attribute information to obtain vectorized data, and finally trains a binary classification model for detecting whether the screen of the device is aged or not by taking the aging attribute information and whether the corresponding intelligent device is aged or not as training data. Therefore, interference factors encountered by detection by using image recognition are avoided, and the stability of aging detection is ensured. Meanwhile, the two classification models can be continuously trained through the data volume of the intelligent equipment, so that the aging detection accuracy is gradually improved, and the hardware cost of the aging detection is effectively reduced.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show some embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A training method for a two-classification model of equipment screen aging is characterized by comprising the following steps:
acquiring aging attribute information of each intelligent device; wherein part of the intelligent devices have aging, and the other part of the intelligent devices do not have aging;
vectorizing the aging attribute information to obtain vectorized data;
and taking the vectorization data and whether the corresponding intelligent equipment is aged as training data, and training a binary classification model for detecting whether the equipment screen is aged.
2. The device screen aging two-classification model training method according to claim 1, further comprising, before the process of vectorizing the aging attribute information to obtain vectorized data, the steps of:
and carrying out data preprocessing on the aging attribute information.
3. The device screen aging two-classification model training method according to claim 2, wherein the process of performing data preprocessing on the aging attribute information comprises the steps of:
and carrying out data cleaning processing, discretization, standardization or digitization on the aging attribute information.
4. The device screen aging two-classification model training method of claim 1, wherein the two-classification model comprises a decision tree prediction model or a random forest prediction model.
5. The device screen aging two-classification model training method according to claim 4, wherein the two-classification model comprises a gradient boosting decision tree model.
6. The device screen aging two-classification model training method according to claim 5, wherein the process of training the two-classification model for detecting whether aging exists on the device screen by using the vectorization data and whether aging exists on the corresponding smart device as training data comprises the steps of:
setting parameters of the gradient lifting decision tree model and initializing a weak learner;
calculating residual errors to obtain a best fit value so as to determine a final strong learner;
and substituting the training data into the final strong learner to obtain a two-classification output probability result.
7. The device screen aging two-classification model training method according to claim 6, wherein the process of calculating the residual error to find the best fit value comprises the steps of:
and calculating residual errors according to a CART regression tree fitting algorithm to obtain the best fitting value.
8. The device screen aging two-classification model training method according to any one of claims 1 to 7, wherein the aging attribute information includes device factory time, device type, device selling price, device battery use status, device screen breakage degree, device size, device holder gender, or device holder age.
9. A method for detecting the aging of a device screen is characterized by comprising the following steps:
acquiring aging attribute information of the intelligent equipment to be tested;
vectorizing the aging attribute information;
and inputting the vectorization result into a two-classification model to obtain an equipment screen aging detection result.
10. The device screen aging detection method according to claim 9, characterized by, before the process of vectorizing aging attribute information, further comprising the steps of:
and carrying out data preprocessing on the aging attribute information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111601098.2A CN114330533A (en) | 2021-12-24 | 2021-12-24 | Equipment screen aging two-classification model training method and equipment screen aging detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111601098.2A CN114330533A (en) | 2021-12-24 | 2021-12-24 | Equipment screen aging two-classification model training method and equipment screen aging detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114330533A true CN114330533A (en) | 2022-04-12 |
Family
ID=81013683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111601098.2A Pending CN114330533A (en) | 2021-12-24 | 2021-12-24 | Equipment screen aging two-classification model training method and equipment screen aging detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114330533A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681428A (en) * | 2023-08-03 | 2023-09-01 | 天津奇立软件技术有限公司 | Intelligent recycling management system and method for electronic equipment |
| US11989701B2 (en) | 2014-10-03 | 2024-05-21 | Ecoatm, Llc | System for electrically testing mobile devices at a consumer-operated kiosk, and associated devices and methods |
-
2021
- 2021-12-24 CN CN202111601098.2A patent/CN114330533A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11989701B2 (en) | 2014-10-03 | 2024-05-21 | Ecoatm, Llc | System for electrically testing mobile devices at a consumer-operated kiosk, and associated devices and methods |
| CN116681428A (en) * | 2023-08-03 | 2023-09-01 | 天津奇立软件技术有限公司 | Intelligent recycling management system and method for electronic equipment |
| CN116681428B (en) * | 2023-08-03 | 2023-09-29 | 天津奇立软件技术有限公司 | Intelligent recycling management system and method for electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639516B (en) | Analysis platform based on machine learning | |
| CN114330533A (en) | Equipment screen aging two-classification model training method and equipment screen aging detection method | |
| WO2020143301A1 (en) | Training sample validity detection method, computer device, and computer non-volatile storage medium | |
| CN113728321A (en) | Using a set of training tables to accurately predict errors in various tables | |
| CN111209929A (en) | Access data processing method and device, computer equipment and storage medium | |
| CN111723870A (en) | Data set acquisition method, device, equipment and medium based on artificial intelligence | |
| CN115409111A (en) | Training method of named entity recognition model and named entity recognition method | |
| CN113554184A (en) | Model training method and device, electronic equipment and storage medium | |
| CN116484025A (en) | Vulnerability knowledge graph construction method, vulnerability knowledge graph evaluation equipment and storage medium | |
| CN114298345A (en) | Recovery valuation output model training method and recovery valuation output method | |
| CN112433902B (en) | Screen replacement model training method, screen replacement detection method and device | |
| CN114118526A (en) | Enterprise risk prediction method, device, equipment and storage medium | |
| CN114330534A (en) | Equipment screen perspective detection model training method and equipment screen perspective detection method | |
| KR20210080762A (en) | Method for determining a confidence level of inference data produced by artificial neural network | |
| US11609936B2 (en) | Graph data processing method, device, and computer program product | |
| Vanamala et al. | Using Machine Learning To Identify Software Weaknesses From Software Requirement Specifications | |
| CN113887609A (en) | Equipment screen aging detection model training method and equipment screen aging detection method | |
| CN118569738B (en) | Engineering quality auditing method, system and storage medium | |
| US11822564B1 (en) | Graphical user interface enabling interactive visualizations using a meta-database constructed from autonomously scanned disparate and heterogeneous sources | |
| CN116681434B (en) | Behavior management system and method based on annual card anti-theft swiping algorithm | |
| US11928128B2 (en) | Construction of a meta-database from autonomously scanned disparate and heterogeneous sources | |
| CN113868438B (en) | Information reliability calibration method and device, computer equipment and storage medium | |
| US20230368013A1 (en) | Accelerated model training from disparate and heterogeneous sources using a meta-database | |
| EP4383152A1 (en) | Machine learning evaluation for detecting feature bias | |
| CN117171653B (en) | Method, device, equipment and storage medium for identifying information relationship |
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 |