CN112732542A - Information processing method, information processing device and terminal equipment - Google Patents
Information processing method, information processing device and terminal equipment Download PDFInfo
- Publication number
- CN112732542A CN112732542A CN202011626575.6A CN202011626575A CN112732542A CN 112732542 A CN112732542 A CN 112732542A CN 202011626575 A CN202011626575 A CN 202011626575A CN 112732542 A CN112732542 A CN 112732542A
- Authority
- CN
- China
- Prior art keywords
- target
- information
- classifier
- classification
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/302—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a software system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application is applicable to the technical field of artificial intelligence and provides an information processing method, an information processing device, a terminal device and a storage medium, wherein the information processing method comprises the following steps: the method comprises the steps of obtaining model information, equipment blocking information and equipment parameter information of client equipment; inputting the model information and the equipment parameter information into a first classifier to obtain a first classification result of the first classifier for the client equipment; inputting the first classification result and the equipment blockage information into a second classifier to obtain a second classification result of the second classifier aiming at the client equipment; determining a target classification of the client device according to the second classification result; and if the operation to be executed by the target is detected, determining the running mode of the operation to be executed by the target in the client equipment according to the target classification. By the method, the system operation performance of the client device can be optimized to reduce the jamming.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to an information processing method, an information processing apparatus, a terminal device, and a computer-readable storage medium.
Background
Katton is a very common problem for user terminals. Since in practical applications, the system is directly perceived by the user, for example, the reaction of the application program is much delayed from the operation of the user, even the operation of the user directly causes the application program to be unresponsive, and so on. Therefore, the user experience is greatly influenced by the jamming. Therefore, a method for optimizing the system operation performance of the client device to reduce the jamming is needed.
Disclosure of Invention
In view of this, embodiments of the present application provide an information processing method, an information processing apparatus, a terminal device, and a computer-readable storage medium, which can optimize system operation performance of a client device to reduce deadlock.
In a first aspect, an embodiment of the present application provides an information processing method, including:
the method comprises the steps of obtaining model information, equipment blocking information and equipment parameter information of client equipment;
inputting the model information and the equipment parameter information into a first classifier to obtain a first classification result of the first classifier for the client equipment;
inputting the first classification result and the equipment blockage information into a second classifier to obtain a second classification result of the second classifier aiming at the client equipment;
determining a target classification of the client device according to the second classification result, wherein the target classification is used for identifying the device performance of the client device;
and if the operation to be executed by the target is detected, determining the running mode of the operation to be executed by the target in the client equipment according to the target classification.
In a second aspect, an embodiment of the present application provides an information processing apparatus, including:
the acquisition module is used for acquiring the model information, the equipment blockage information and the equipment parameter information of the client equipment;
the first processing module is used for inputting the model information and the equipment parameter information into a first classifier to obtain a first classification result of the first classifier aiming at the client equipment;
the second processing module is used for inputting the first classification result and the equipment blockage information into a second classifier to obtain a second classification result of the second classifier aiming at the client equipment;
a first determining module, configured to determine a target classification of the client device according to the second classification result, where the target classification is used to identify device performance of the client device;
and the second determining module is used for determining the running mode of the target operation to be executed in the client equipment according to the target classification if the target operation to be executed is detected.
In a third aspect, an embodiment of the present application provides a terminal device, which includes a memory, a processor, a display, and a computer program stored in the memory and executable on the processor, where the processor implements the information processing method according to the first aspect when executing the computer program.
In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the information processing method according to the first aspect.
The information processing method provided by the embodiment of the application has the following beneficial effects: in the embodiment of the application, the model information, the equipment blocking information and the equipment parameter information of the client equipment are obtained; inputting the model information and the equipment parameter information into a first classifier to obtain a first classification result of the first classifier for the client equipment; inputting the first classification result and the equipment blockage information into a second classifier to obtain a second classification result of the second classifier aiming at the client equipment; determining a target classification of the client device according to the second classification result, wherein the target classification is used for identifying the device performance of the client device; and if the operation to be executed by the target is detected, determining the running mode of the operation to be executed by the target in the client equipment according to the target classification. As can be seen, in the embodiment of the application, the target classification of the client device can be determined hierarchically according to device information of multiple dimensions, such as model information, device stuck information, device parameter information, and the like of the client device, so as to accurately determine the device performance of the client device, and thus when a target to-be-executed operation is detected, an operation mode of the target to-be-executed operation can be determined according to the target classification, so that the operation mode can match the device performance of the client device, and thereby the occurrence of a stuck phenomenon is reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flowchart of an information processing method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of step S102 according to an embodiment of the present application;
fig. 3 is a schematic flowchart of step S103 according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, fig. 1 is a flowchart illustrating an information processing method according to an embodiment of the present disclosure. The embodiment of the application can be applied to terminal equipment.
The embodiment of the present application does not set any limit to the specific type of the terminal device. Illustratively, the terminal device may be a server, a desktop computer, a mobile phone, a tablet computer, a wearable device, an in-vehicle device, an Augmented Reality (AR)/Virtual Reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), or the like.
It should be noted that the terminal device may be a client device in this embodiment. Alternatively, the client device may be another device other than the client device.
If the terminal device is a device other than the client device, the terminal device may be in communication connection with the client device to obtain model information and the like of the client device, and may obtain indication information including operation information of the target operation to be executed, which is sent by the client device, to detect the target operation to be executed, and then, after determining an operation mode of the target operation to be executed in the client device according to the target classification, the operation mode may be sent to the client device through the communication connection to indicate the client device to operate the target operation to be executed according to the operation mode.
As shown in fig. 1, an information processing method provided in this embodiment may include:
step S101, model information, equipment blocking information and equipment parameter information of the client equipment are obtained.
In this embodiment, the client devices (CPEs) may refer to devices physically placed on the user side, and include devices belonging to the user or devices placed on the user side by a service provider.
The model type may include information about the model of the client device, such as a brand, a corresponding model, a model first time, a model first price, and so on.
The model information may initially reflect the capabilities of the client device. For example, in some examples, the model information may be used to preliminarily evaluate whether the client device is a high-end model or a low-end model, and so on. Of course, the performance of the client device may be expressed by other levels, labels, or values, and is not limited to the performance description manner of the high-end model and the low-end model.
The device stuck information may be pre-counted stuck information associated with the client device. The card pause information can include card pause information of the client device itself, and can also include card pause information of other client devices of the same type as the client device, which is acquired through a cloud.
For example, the card-on information may include at least one Of card-on occurrence rate information, Application Not Responding (ANR) information, Out Of Memory (OOM) information, CPU utilization rate information, and the like.
Among them, the os needs to complete within a certain time range for some events, and if a valid response is not obtained beyond a predetermined time, an application non-response (ANR) event may occur. The memory overflow information includes information that the occupied amount of the memory exceeds the maximum memory allocated by a Virtual Machine (VM).
Through the pause information, whether the pause problem of the client equipment is serious can be known.
The device parameter information may include software parameter information and/or hardware parameter information of the device, and the like. Illustratively, the software parameter information may include at least one of software version information, installed software number information, software size, and the like. The hardware parameter information may include at least one of a CPU core number, a size of an operating memory, a size of a body memory, a chip model, CPU frequency information, and the like.
Step S102, inputting the model information and the equipment parameter information into a first classifier, and obtaining a first classification result of the first classifier aiming at the client equipment.
In the embodiment of the present application, the specific type of the first classifier may be various. Illustratively, the first classifier may be a convolutional neural network-based classifier, a decision tree classifier, a naive bayes classifier, a logistic regression classifier, or a combination thereof, and so on.
The first classifier may be pre-configured in the terminal device. For example, the terminal device may be factory-owned, or obtained by training in advance in the terminal device. Alternatively, the first classifier may be obtained by the terminal device from a designated terminal through a designated communication method.
In the embodiment of the present application, the specific form of the first classification result may be various. For example, the first classification result may be a score or a specific level, which may be specifically determined according to a preset level manner for the performance of the client device. And performing preliminary evaluation on the device performance of the client device in model and device parameter dimensions according to the model information and the device parameter information through the first classification result.
In some embodiments, the first classifier is a decision tree classifier, the decision tree classifier includes at least two decision units, and each decision unit corresponds to a decision rule;
the inputting the model information and the device parameter information into a first classifier to obtain a first classification result of the first classifier for the client device includes:
step S201, processing the model information and the equipment parameter information through the decision tree classifier to obtain a decision score output by at least one decision unit in the decision tree classifier based on a corresponding decision rule;
step S202, obtaining the first classification result according to the decision score and the weight of the decision unit corresponding to the decision score.
In the embodiment of the present application, the decision rule may be described by a specific program statement, for example, an if-else statement, a switch statement, a case statement, and the like, so as to obtain a decision result through the corresponding program statement.
For example, the decision rules involved in the decision tree classifier may be as follows:
1. if the model of the client device is in a preset low-end model list, the model of the client device is a low-end model;
2. if the maximum application available memory of the client device is smaller than a first storage threshold (such as 64M), the model of the client device is a low-end model;
3. if the maximum operation memory of the client device is smaller than a second storage threshold (such as 4G), the model of the client device is a low-end model;
4. if the number of the CPU cores of the client device is less than a first preset number (for example, 4), the model of the client device is a low-end model;
5. if the highest frequency of the CPU of the client device is smaller than a first preset frequency threshold (such as 1.8GHz), the model of the client device is a low-end model;
6. if the operating system version number (such as Android version) of the client equipment is smaller than a first specified version number (such as 6.0), the model of the client equipment is a low-end model;
7. if the model of the client device is in a preset high-end model list, the possibility that the model of the client device is a high-end model is 1;
8. if the operating system version number (such as an Android version) of the client device is within a specified version interval (such as 6.0-9.0), the possibility that the model of the client device is a high-end model is 0.5, and if the Android version of the client device is greater than 9.0, the possibility that the model of the client device is a high-end model is 1;
the first classification result may be obtained according to at least one of the above decision rules.
In the embodiment of the application, the important degrees of the influence of different decision rules on the performance of the machine types are different, so that different weights can be preset for each decision rule, and the first classification result can be obtained according to the decision result of each decision rule and the weight of each decision rule.
In one example, the first classification result may be a probability value in the interval [0, 1], where the higher the probability value is, the better the device performance of the client device is, i.e., the higher the possibility that the client device is a high-end model is.
In some embodiments, the decision rule in each decision unit is described by a conditional judgment statement;
the processing the model information and the equipment parameter information by the decision tree classifier to obtain a decision score output by at least one decision unit in the decision tree classifier based on a corresponding decision rule includes:
for any decision unit, searching key field information matched with the keywords corresponding to the decision unit from the model information and the equipment parameter information, wherein the keywords corresponding to the decision unit are determined according to a decision rule of the decision unit;
and obtaining the decision score output by the decision unit according to the key field information through a condition judgment statement of the corresponding decision rule in the decision unit.
In the embodiment of the application, the conditional judgment statement may be an if-else statement, so that the conditional judgment statement can be efficiently and quickly executed to obtain a corresponding decision score.
The keyword corresponding to the decision unit can be determined according to the decision rule of the decision unit. Specifically, the keyword corresponding to the decision unit may be determined according to a conditional judgment statement describing the decision rule, for example, extracted from the conditional judgment statement by a keyword extraction method and the like. Or, the keyword corresponding to the decision unit may also be a keyword preset by the user according to the decision rule.
The key field information may include parameter information of the client device for the key word, and the like. For example, if the keyword is the number of CPU cores, the key field information may include the specific number of CPU cores of the client device.
By searching the key field information matched with the key word corresponding to the decision unit, the data required by the decision unit for decision can be obtained, so that the decision unit can efficiently obtain a decision score according to the obtained key field information.
Step S103, inputting the first classification result and the equipment blockage information into a second classifier, and obtaining a second classification result of the second classifier aiming at the client equipment.
In the embodiment of the present application, the specific type of the second classifier may be various. Illustratively, the second classifier may be a convolutional neural network-based classifier, a decision tree classifier, a naive bayes classifier, a logistic regression classifier, or a combination thereof, and so on.
The second classifier may be pre-configured in the terminal device. For example, the terminal device may be factory-owned, or obtained by training in advance in the terminal device. Alternatively, the second classifier may be obtained by the terminal device from a specified terminal through a specified communication method.
In the embodiment of the present application, the specific form of the second classification result may be various. For example, the second classification result may be a score or a specific grade, which may be specifically determined according to a preset grade mode for the performance of the client device.
Through the second classification result, the device performance of the client device can be comprehensively evaluated in combination with the model and device parameters and the dimension of the device blocking condition. At the moment, the first classifier and the second classifier are used for evaluating at least two levels, so that the data volume of single processing is small, the identification and application of the data features of a single dimension are sufficient during the single processing, and then the second classifier is used for integrating the equipment information of each dimension, so that a more accurate second classification result is obtained.
Step S104, determining a target classification of the client device according to the second classification result, wherein the target classification is used for identifying the device performance of the client device.
In the embodiment of the present application, the classification manner of the target classification may be determined in advance according to an actual scene requirement, and is not limited herein. For example, the target classification may be determined from at least two performance levels, and the specific setting manner of each performance level may be determined according to the application scenario requirements.
For example, the target classification may include a high-end model, a medium-end model, or a low-end model, and the like, and in this case, it may be determined that the client device is the high-end model, the medium-end model, or the low-end model, and the like, according to the second classification result.
The target classification is not only determined according to the stuck state of the equipment, but also combines equipment information such as model information and equipment parameter information of the client, so that the stuck problem is not only checked and optimized in the application process, and system-level reasons such as system hardware and system performance of the client equipment are comprehensively considered. And combining the first classifier and the second classifier, the device performance of the client device can be comprehensively evaluated in a hierarchical and multidimensional way. Therefore, the target classification can better reflect the device performance of the client device and has higher accuracy.
Step S105, if the target operation to be executed is detected, determining the running mode of the target operation to be executed in the client device according to the target classification.
After determining the target classification, an operation mode of some functions in the client device can be determined according to the target classification, so that the client device can reduce the stagnation when the functions are operated in the determined operation mode. Wherein the function may be a target to-be-executed operation to instruct the client device to execute.
In this embodiment of the application, the target operation to be executed may be a designated operation to be executed, where the target operation to be executed is used to implement a specific function.
For example, the target to-be-executed operation may include a power-on animation operation, an operation of specifying an image rendering operation, and/or an operation of browsing a target file carrying a three-dimensional image, which may require a large amount of device resources. In the embodiment of the present application, the operation mode of the target operation to be executed in the client device may be determined according to the target classification, so that the operation mode of the target operation to be executed may be adjusted. The operation mode is used for determining the operation authority and/or operation mode and the like of some items to be operated in the execution operation, so as to optimize the device performance of the client device when the client device operates the target items to be executed according to the target classification, thereby reducing the occurrence of the device stuck phenomenon.
In some embodiments, after determining the target classification for the client device, the target classification may be stored in a memory of the client device. If the operation to be executed by the target is detected, the target classification can be directly read from a memory, and the operation mode of the operation to be executed by the target is determined according to the read target classification.
In some embodiments, the target to-be-executed operation includes a boot animation operation, an operation of specifying image rendering, and/or an operation of browsing a target file carrying a three-dimensional image;
if the operation to be executed by the target is detected, determining the running mode of the operation to be executed by the target in the client equipment according to the target classification, wherein the running mode comprises the following steps:
if the starting-up animation operation is detected and the target classification is a preset classification, determining the frame rate of the starting-up animation and/or determining the resolution of the starting-up animation according to the preset classification, or updating the starting-up animation operation into an operation for displaying a starting-up image;
if the designated image rendering operation is detected and the target classification is a preset classification, determining the resolution of the designated image rendered by the designated image rendering operation and/or determining the operation strategy of the current background program according to the preset classification;
and if the operation of browsing the target file is detected and the target classification is a preset classification, acquiring a target two-dimensional image of the three-dimensional image and displaying the target two-dimensional image when the target file is browsed.
In this embodiment, the preset classification may be used to indicate that the device performance of the client device is low. The specific type of the preset classification may be determined according to the specific classification type of the target classification.
For example, if the specific types of the target categories include a high-end model, a middle-end model, and a low-end model, the preset category may be the low-end model. And if the specific type of the target classification comprises a 1 st classification, a 2 nd classification and a 3 rd classification which are correspondingly and sequentially improved in equipment performance. . . And the xth category, then the preset categories may be the 1 st, 2 nd, 3 rd categories described above. . . And at least one of the Mth classifications. For example, the preset classification may be the 1 st classification, and may also be the 1 st classification or the 2 nd classification.
When the target classification is the preset classification, because the device performance of the client device is low, for target to-be-executed operations such as a boot animation operation, an operation of specifying an image rendering operation, and/or an operation of browsing a target file carrying a three-dimensional image, the operation mode of the target to-be-executed operation may be determined according to the target classification, so that resource consumption of the client device by the target to-be-executed operation is reduced, and the generation of a pause phenomenon is reduced.
If the target operation to be executed is a boot animation operation, the frame rate of the boot animation and/or the resolution of the boot animation can be determined according to the preset classification, so that the frame rate of the boot animation and/or the resolution of the boot animation can be properly reduced when the equipment performance of the client equipment is low, and the running speed of the boot animation is increased. Or, the boot animation operation may be updated to the operation of displaying the boot image according to the preset classification, so as to simplify the complexity of the boot operation and improve the display speed of the boot display content.
If the target operation to be executed is a designated image rendering operation, determining the resolution of the designated image rendered by the designated image rendering operation according to the preset classification, so that the resolution of the designated image rendered by the designated image rendering operation can be properly reduced when the equipment performance of the client equipment is low, and the running speed of the boot animation is improved. And/or determining the operation strategy of the current background program according to the preset classification. For example, only the application corresponding to the specified image rendering operation (e.g., a large game for rendering a complex game scene, etc.) and the current background program with priority higher than a preset priority (e.g., a system application) may be run, and the current background program with priority not higher than the preset priority (e.g., a music playing application, a social class application, a shopping class application, etc.) may be stopped from running.
If the operation to be executed by the target is an operation of browsing the target file, a target two-dimensional image of the three-dimensional image can be acquired, and the target two-dimensional image is displayed when the target file is browsed. For example, the target two-dimensional image may be an image corresponding to a certain direction of the three-dimensional image.
Since the device resources occupied for rendering the three-dimensional image are often large, if the device performance of the client device is weak, for example, the CPU performance is weak and the memory space is small, it is likely that the three-dimensional image is jammed when rendered. Therefore, if the target classification of the client device is the preset classification, the target two-dimensional image of the three-dimensional image can be acquired and presented in a static form of the target two-dimensional image when the target file is browsed, and the three-dimensional image is not rendered in real time, so that resource consumption of the target to-be-executed operation on the client device can be reduced, and the generation of the karton phenomenon can be reduced.
In some embodiments, after the step of obtaining a target two-dimensional image of the three-dimensional image and displaying the target two-dimensional image when the target file is browsed is detected and the target is classified into a preset classification, the method further includes:
and if the specified trigger operation on the target two-dimensional image is detected when the target file is browsed, rendering the three-dimensional image and displaying.
For example, the specified trigger operation may be a click operation of the target two-dimensional image by a user, or the like. In the embodiment of the application, the three-dimensional rendering of the three-dimensional image is performed only when the specified trigger operation on the target two-dimensional image is detected, so that the rendering is performed only when a user needs to browse the three-dimensional image, and the reasonable allocation of the device resources of the client device is realized.
In some embodiments, the device stuck information includes a model stuck occurrence rate, a model application unresponsive occurrence rate, and/or a model memory overflow occurrence rate corresponding to the client device.
In this embodiment of the application, the model jamming occurrence rate may refer to a jamming occurrence rate of a model corresponding to the client device within a preset time period. The model application unresponsiveness occurrence rate may refer to an application unresponsiveness occurrence rate of a model corresponding to the client device within a preset time period. The occurrence rate of the model memory overflow may refer to the occurrence rate of the memory overflow of the model corresponding to the client device in a preset time period.
The specific obtaining mode of the device blocking information may be determined according to a specific type and a specific application scenario of the terminal device executing the embodiment of the present application. For example, if the terminal device is a client device itself, the occurrence rate of model blockage, the occurrence rate of model application unresponsiveness, and/or the occurrence rate of model memory overflow may be obtained by the client device from a specific terminal such as a server; and if the terminal device is a server in communication connection with the client device, the device stuck information calculated in the server in advance according to big data and the like can be acquired.
In one example, the model stuck occurrence rate may be: (the number of calories per day of the model/the number of daily activities of the model)/(the number of calories per day of the total/the number of daily activities of the model);
the incidence of model application unresponsiveness may be: (number of unresponsives for application per model day/number of active per model day)/(number of unresponsives for application per total day/number of active per total day);
the occurrence rate of the memory overflow of the machine type can be as follows: (the number of machine type single day memory overflows/the number of machine type daily activities)/(the number of total single day memory overflows/total daily activities).
In the embodiment of the application, through the occurrence rate of model blockage, the occurrence rate of model application program non-response and/or the occurrence rate of model memory overflow corresponding to the client device, big data can be referred to obtain some historical blockage information of the model corresponding to the client device, so that the model performance of the client device can be accurately evaluated according to the occurrence rate of model blockage, the occurrence rate of model application program non-response and/or the occurrence rate of model memory overflow corresponding to the client device in the following process, and therefore the running mode of the target operation to be executed is optimized according to the model performance of the client device, the system fluency is improved, and the blockage situation is reduced.
In some embodiments, the second classifier is a logistic regression classifier;
the inputting the first classification result and the device stuck information into a second classifier to obtain a second classification result of the second classifier for the client device includes:
step S301, inputting the first classification result, the model blockage occurrence rate, the model application program unresponsive occurrence rate and the model memory overflow occurrence rate corresponding to the client device into the second classifier, and establishing a likelihood equation according to the first classification result, the model blockage occurrence rate, the model application program unresponsive occurrence rate and the model memory overflow occurrence rate corresponding to the client device through a maximum likelihood function to solve;
and step S302, obtaining a second classification result according to the solving result.
The likelihood equations may be solved in various ways, for example, the likelihood equations may be solved by a Newton-Raphson (Newton-Raphson) iteration method, a Gauss-Seidel (Gauss-Seidel) iteration method, or the like, to obtain the solution result.
In one example, the solution result may be a probability value in the interval of [0, 1], where the higher the probability value is, the better the device performance of the client device is, that is, the higher the possibility that the client device is a high-end model is.
In some embodiments, the obtaining manner of the device morton information may include:
sending request information to a server, wherein the request information is used for requesting to acquire the model blocking occurrence rate, the model application program non-response occurrence rate and/or the model memory overflow occurrence rate of the client equipment, and the request information carries the model information of the client equipment;
and receiving the model blocking occurrence rate, the model application program unresponsive occurrence rate and/or the model memory overflow occurrence rate of the client equipment, which are sent by the server.
At this time, the server may perform big data acquisition and processing to obtain the stuck information of other client devices of the same model as the client device, so as to obtain the model stuck occurrence rate, the model application unresponsive occurrence rate, and/or the model memory overflow occurrence rate of the client device.
In some embodiments, before inputting the model information and the device parameter information into the first classifier, the method further includes: downloading the first classifier and the second classifier from the server.
At this time, the first classifier and the second classifier may be configured in advance in the server, so that the method and the device may be conveniently and efficiently applied to each client device.
In the embodiment of the application, the target classification of the client device can be determined hierarchically according to device information of multiple dimensions, such as model information, device stuck information, device parameter information and the like of the client device through the first classifier and the second classifier, so as to accurately determine the device performance of the client device, and thus when a target to-be-executed operation is detected, an operation mode of the target to-be-executed operation can be determined according to the target classification, so that the operation mode can be matched with the device performance of the client device, and the occurrence of the stuck phenomenon is reduced.
Referring to fig. 4, fig. 4 is a block diagram of an information processing apparatus according to an embodiment of the present disclosure. The terminal device in this embodiment includes units for executing the steps in the above-described information processing method embodiments. Please refer to the related description of the embodiment corresponding to the information processing method. For convenience of explanation, only the portions related to the present embodiment are shown.
Referring to fig. 4, the information processing apparatus 4 includes:
an obtaining module 401, configured to obtain model information, device stuck information, and device parameter information of a client device;
a first processing module 402, configured to input the model information and the device parameter information into a first classifier, and obtain a first classification result of the first classifier for the client device;
a second processing module 403, configured to input the first classification result and the device stuck information into a second classifier, and obtain a second classification result of the second classifier for the client device;
a first determining module 404, configured to determine a target classification of the client device according to the second classification result, where the target classification is used to identify device performance of the client device;
a second determining module 405, configured to determine, according to the target classification, an operation mode of the target operation to be executed in the client device if the target operation to be executed is detected.
Optionally, the first classifier is a decision tree classifier, the decision tree classifier includes at least two decision units, and each decision unit corresponds to a decision rule;
the first processing module 402 comprises:
the first processing unit is used for processing the model information and the equipment parameter information through the decision tree classifier to obtain a decision score output by at least one decision unit in the decision tree classifier based on a corresponding decision rule;
and the second processing unit is used for obtaining the first classification result according to the decision score and the weight of the decision unit corresponding to the decision score.
Optionally, the decision rule in each decision unit is described by a conditional judgment statement;
the first processing unit includes:
the searching subunit is configured to search, for any decision unit, key field information matched with the keyword corresponding to the decision unit from the model information and the device parameter information, where the keyword corresponding to the decision unit is determined according to a decision rule of the decision unit;
and the processing subunit is used for obtaining the decision score output by the decision unit according to the key field information through the condition judgment statement of the corresponding decision rule in the decision unit.
Optionally, the device stuck information includes a model stuck occurrence rate, a model application unresponsive occurrence rate, and/or a model memory overflow occurrence rate corresponding to the client device.
Optionally, the second classifier is a logistic regression classifier;
the second processing module 403 includes:
a third processing unit, configured to input the first classification result, the model blockage occurrence rate, the model application unresponsive occurrence rate, and the model memory overflow occurrence rate corresponding to the client device into the second classifier, so as to establish a likelihood equation according to the first classification result, the model blockage occurrence rate, the model application unresponsive occurrence rate, and the model memory overflow occurrence rate corresponding to the client device through a maximum likelihood function to solve the problem;
and the fourth processing unit is used for obtaining a second classification result according to the solving result.
Optionally, the target operation to be executed includes a boot animation operation, an operation of designating image rendering, and/or an operation of browsing a target file carrying a three-dimensional image;
the second determination module 405 includes:
the first determining unit is used for determining the frame rate of the boot animation and/or determining the resolution of the boot animation according to a preset classification if the boot animation operation is detected and the target classification is the preset classification, or updating the boot animation operation into an operation for displaying a boot image;
a second determining unit, configured to determine, according to a preset classification, a resolution of a specified image rendered by a specified image rendering operation and/or determine an operation policy of a current background program if the specified image rendering operation is detected and the target classification is the preset classification;
and the fifth processing unit is used for acquiring a target two-dimensional image of the three-dimensional image and displaying the target two-dimensional image when the operation of browsing the target file is detected and the target classification is a preset classification.
Optionally, the information processing apparatus 4 further includes:
and the rendering module is used for rendering the three-dimensional image and displaying the three-dimensional image if the specified trigger operation of the target two-dimensional image is detected when the target file is browsed.
In the embodiment of the application, the target classification of the client device can be determined hierarchically according to the device information of multiple dimensions, such as model information, device stuck information, device parameter information and the like of the client device through the first classifier and the second classifier, so as to accurately determine the device performance of the client device, and thus when the target to-be-executed operation is detected, the operation mode of the target to-be-executed operation can be determined according to the target classification, so that the operation mode can be matched with the device performance of the client device, and the occurrence of the stuck phenomenon is reduced.
It should be noted that, for the information interaction, execution process, and other contents between the above-mentioned devices/units, the specific functions and technical effects thereof are based on the same concept as those of the embodiment of the method of the present application, and specific reference may be made to the part of the embodiment of the method, which is not described herein again.
Fig. 5 is a block diagram of a terminal device according to an embodiment of the present application. As shown in fig. 5, the terminal device 5 of this embodiment includes: a processor 51, a memory 52 and a computer program 53, such as a program of an information processing method, stored in said memory 52 and executable on said processor 51. The processor 51 implements the steps in the embodiments of the information processing methods described above, such as S101 to S105 shown in fig. 1, or S201 to S202 shown in fig. 2, or S301 to S302 shown in fig. 3, when executing the computer program 53. Alternatively, when the processor 51 executes the computer program 53, the functions of the modules in the embodiment corresponding to fig. 4, for example, the functions of the modules 401 to 405 shown in fig. 4, are implemented, for which reference is specifically made to the relevant description in the corresponding embodiment, which is not repeated herein.
Illustratively, the computer program 53 may be divided into one or more units, which are stored in the memory 52 and executed by the processor 51 to accomplish the present application. The one or more units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 53 in the terminal device 50. For example, the computer program 53 may be divided into a first acquisition unit, a first determination unit, a first adjustment unit, a second adjustment unit, and an execution unit, each unit functioning specifically as described above.
The terminal device may include, but is not limited to, a processor 51, a memory 52. It will be appreciated by those skilled in the art that fig. 5 is merely an example of a terminal device 5 and does not constitute a limitation of the terminal device 5 and may include more or less components than shown, or combine certain components, or different components, e.g. the turntable device may also include input output devices, network access devices, buses, etc.
The Processor 51 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 52 may be an internal storage unit of the terminal device 5, such as a hard disk or a memory of the terminal device 5. The memory 52 may also be an external storage device of the terminal device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 5. Further, the memory 52 may also include both an internal storage unit and an external storage device of the terminal device 5. The memory 52 is used for storing the computer program and other programs and data required by the turntable device. The memory 52 may also be used to temporarily store data that has been output or is to be output.
In this embodiment, when the processor 50 executes the computer program 52 to implement the steps in any of the above information processing method embodiments, the target classification of the client device may be determined hierarchically according to device information of multiple dimensions, such as model information, device stuck information, and device parameter information, of the client device through the first classifier and the second classifier, so as to accurately determine the device performance of the client device, so that when a target operation to be executed is detected, an operation manner of the target operation to be executed may be determined according to the target classification, so that the operation manner can match the device performance of the client device, and thereby the occurrence of a stuck phenomenon is reduced.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program can implement the steps in the information processing method embodiments.
The embodiments of the present application provide a computer program product, which, when running on a terminal device, enables the terminal device to implement the steps in the above-mentioned information processing method embodiments when executed.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. An information processing method characterized by comprising:
the method comprises the steps of obtaining model information, equipment blocking information and equipment parameter information of client equipment;
inputting the model information and the equipment parameter information into a first classifier to obtain a first classification result of the first classifier for the client equipment;
inputting the first classification result and the equipment blockage information into a second classifier to obtain a second classification result of the second classifier aiming at the client equipment;
determining a target classification of the client device according to the second classification result, wherein the target classification is used for identifying the device performance of the client device;
and if the operation to be executed by the target is detected, determining the running mode of the operation to be executed by the target in the client equipment according to the target classification.
2. The information processing method according to claim 1, wherein the first classifier is a decision tree classifier, the decision tree classifier includes at least two decision units, and each decision unit corresponds to a decision rule;
the inputting the model information and the device parameter information into a first classifier to obtain a first classification result of the first classifier for the client device includes:
processing the model information and the equipment parameter information through the decision tree classifier to obtain a decision score output by at least one decision unit in the decision tree classifier based on a corresponding decision rule;
and obtaining the first classification result according to the decision score and the weight of the decision unit corresponding to the decision score.
3. The information processing method according to claim 2, wherein the decision rule in each of the decision units is described by a conditional judgment statement;
the processing the model information and the equipment parameter information by the decision tree classifier to obtain a decision score output by at least one decision unit in the decision tree classifier based on a corresponding decision rule includes:
for any decision unit, searching key field information matched with the keywords corresponding to the decision unit from the model information and the equipment parameter information, wherein the keywords corresponding to the decision unit are determined according to a decision rule of the decision unit;
and obtaining the decision score output by the decision unit according to the key field information through a condition judgment statement of the corresponding decision rule in the decision unit.
4. The information processing method according to claim 1, wherein the device stuck information includes a model stuck occurrence rate, a model application unresponsive occurrence rate, and/or a model memory overflow occurrence rate corresponding to the client device.
5. The information processing method according to claim 4, wherein the second classifier is a logistic regression classifier;
the inputting the first classification result and the device stuck information into a second classifier to obtain a second classification result of the second classifier for the client device includes:
inputting the first classification result, the model blockage occurrence rate, the model application program unresponsive occurrence rate and the model memory overflow occurrence rate corresponding to the client device into the second classifier, and establishing a likelihood equation according to the first classification result, the model blockage occurrence rate, the model application program unresponsive occurrence rate and the model memory overflow occurrence rate corresponding to the client device through a maximum likelihood function to solve;
and obtaining a second classification result according to the solving result.
6. The information processing method according to any one of claims 1 to 5, wherein the target operation to be executed includes a boot animation operation, a specified image rendering operation, and/or an operation of browsing a target file carrying a three-dimensional image;
if the operation to be executed by the target is detected, determining the running mode of the operation to be executed by the target in the client equipment according to the target classification, wherein the running mode comprises the following steps:
if the starting-up animation operation is detected and the target classification is a preset classification, determining the frame rate of the starting-up animation and/or determining the resolution of the starting-up animation according to the preset classification, or updating the starting-up animation operation into an operation for displaying a starting-up image;
if the designated image rendering operation is detected and the target classification is a preset classification, determining the resolution of the designated image rendered by the designated image rendering operation and/or determining the operation strategy of the current background program according to the preset classification;
and if the operation of browsing the target file is detected and the target classification is a preset classification, acquiring a target two-dimensional image of the three-dimensional image and displaying the target two-dimensional image when the target file is browsed.
7. The information processing method according to claim 6, wherein, after acquiring a target two-dimensional image of the three-dimensional image and displaying the target two-dimensional image while browsing the target file if an operation of browsing the target file is detected and the target classification is a preset classification, further comprising:
and if the specified trigger operation on the target two-dimensional image is detected when the target file is browsed, rendering the three-dimensional image and displaying.
8. An information processing apparatus characterized by comprising:
the acquisition module is used for acquiring the model information, the equipment blockage information and the equipment parameter information of the client equipment;
the first processing module is used for inputting the model information and the equipment parameter information into a first classifier to obtain a first classification result of the first classifier aiming at the client equipment;
the second processing module is used for inputting the first classification result and the equipment blockage information into a second classifier to obtain a second classification result of the second classifier aiming at the client equipment;
a first determining module, configured to determine a target classification of the client device according to the second classification result, where the target classification is used to identify device performance of the client device;
and the second determining module is used for determining the running mode of the target operation to be executed in the client equipment according to the target classification if the target operation to be executed is detected.
9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the information processing method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the information processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011626575.6A CN112732542A (en) | 2020-12-30 | 2020-12-30 | Information processing method, information processing device and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011626575.6A CN112732542A (en) | 2020-12-30 | 2020-12-30 | Information processing method, information processing device and terminal equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112732542A true CN112732542A (en) | 2021-04-30 |
Family
ID=75609896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011626575.6A Pending CN112732542A (en) | 2020-12-30 | 2020-12-30 | Information processing method, information processing device and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732542A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763137A (en) * | 2021-11-10 | 2021-12-07 | 山东派盟网络科技有限公司 | Information pushing method and computer equipment |
-
2020
- 2020-12-30 CN CN202011626575.6A patent/CN112732542A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763137A (en) * | 2021-11-10 | 2021-12-07 | 山东派盟网络科技有限公司 | Information pushing method and computer equipment |
| CN113763137B (en) * | 2021-11-10 | 2022-10-14 | 山东派盟网络科技有限公司 | Information pushing method and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11687645B2 (en) | Security control method and computer system | |
| US20220198289A1 (en) | Recommendation model training method, selection probability prediction method, and apparatus | |
| KR102180495B1 (en) | Automatic detection of fraudulent ratings/comments related to an application store | |
| US9411872B1 (en) | Management of application state data | |
| US20080120276A1 (en) | Systems and Methods Using Query Patterns to Disambiguate Query Intent | |
| US11966687B2 (en) | Modifying a document content section of a document object of a graphical user interface (GUI) | |
| CN107092678B (en) | Method, device and equipment for acquiring application activity degree | |
| CN114257551A (en) | Distributed current limiting method and system and storage medium | |
| CN112988185A (en) | Cloud application updating method, device and system, electronic equipment and storage medium | |
| CN107103490B (en) | Data processing method, network server and terminal | |
| CN112732542A (en) | Information processing method, information processing device and terminal equipment | |
| CN110019813A (en) | Life insurance case retrieving method, retrieval device, server and readable storage medium storing program for executing | |
| US11436412B2 (en) | Predictive event searching utilizing a machine learning model trained using dynamically-generated event tags | |
| US20230188437A1 (en) | Methods and apparatus to determine main pages from network traffic | |
| CN114398094B (en) | Applet starting method, device, equipment and computer readable storage medium | |
| US20220114451A1 (en) | Methods and apparatus for data enhanced automated model generation | |
| US10282482B2 (en) | Data provision device, data provision method, and data provision program | |
| US10831795B2 (en) | Method and system for providing target information using application list | |
| US20220300822A1 (en) | Forgetting data samples from pretrained neural network models | |
| CN109889584B (en) | Operation scheme pushing method, device and system and server | |
| CN114461909A (en) | Information processing method, information processing apparatus, electronic device, and storage medium | |
| CN109033469B (en) | Ranking method and device of search results, terminal and computer storage medium | |
| CN113515701A (en) | Information recommendation method and device | |
| CN111507471A (en) | Model training method, device, equipment and storage medium | |
| CN115203194A (en) | Metadata information generation method, related device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |