CN113031982A - Application program operation prediction method and device and electronic equipment - Google Patents
Application program operation prediction method and device and electronic equipment Download PDFInfo
- Publication number
- CN113031982A CN113031982A CN201911357776.8A CN201911357776A CN113031982A CN 113031982 A CN113031982 A CN 113031982A CN 201911357776 A CN201911357776 A CN 201911357776A CN 113031982 A CN113031982 A CN 113031982A
- Authority
- CN
- China
- Prior art keywords
- application program
- application
- running
- information
- running information
- 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
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
Abstract
The embodiment of the application discloses an application program operation prediction method and device and electronic equipment. The method comprises the following steps: obtaining application program running information based on the trained machine model prediction, wherein the application program running information comprises application programs which are predicted to run at a target time; updating the application program running information according to a target condition to obtain updated application program running information, wherein the target condition represents a specified application program running rule; and configuring the running environment based on the updated running information of the application program. Therefore, the application program which can be predicted to run at the target time and is predicted by the trained machine model can be adjusted according to the specified application program running rule, the accuracy of the finally predicted application program which can be predicted to run at the target time is improved, and meanwhile, the running environment can be more accurately configured.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for predicting application program operation, and an electronic device.
Background
As the number of applications installed in an electronic device increases, more applications have a higher demand for a running environment. However, the running efficiency of the related applications in the electronic device still needs to be improved.
Disclosure of Invention
In view of the foregoing problems, the present application provides an application program operation prediction method, an application program operation prediction apparatus, and an electronic device, so as to improve the foregoing problems.
In a first aspect, the present application provides an application program operation prediction method applied to an electronic device, the method including: obtaining application program running information based on the trained machine model prediction, wherein the application program running information comprises application programs which are predicted to run at a target time; updating the application program running information according to a target condition to obtain updated application program running information, wherein the target condition represents a specified application program running rule; and configuring the running environment based on the updated running information of the application program.
In a second aspect, the present application provides an application program operation prediction apparatus, which is operated in an electronic device, and includes: the operation prediction unit is used for predicting and obtaining application program operation information based on the trained machine model, and the application program operation information comprises application programs which are predicted to operate at the target time; the prediction result updating unit is used for updating the application program running information according to a target condition to obtain updated application program running information, and the target condition represents a specified application program running rule; and the running environment configuration unit is used for carrying out running environment configuration based on the updated application program running information.
In a third aspect, the present application provides an electronic device comprising one or more processors and a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the methods described above.
In a fourth aspect, the present application provides a computer-readable storage medium having program code stored therein, wherein the method described above is performed when the program code is executed.
According to the application program operation prediction method, the application program operation prediction device and the electronic equipment, after the application program operation information including the predicted application program which can be operated at the target time is obtained based on the machine model prediction of the training, the application program operation information is further updated according to the target condition representing the specified application program operation rule to obtain the updated application program operation information, and then the operation environment configuration is carried out based on the updated application program operation information, so that the application program which can be operated at the target time and is predicted by the machine model prediction of the training can be adjusted according to the specified application program operation rule, and the accuracy of the application program which can be operated at the target time and is finally predicted is further improved, meanwhile, more accurate configuration of the operating environment can be realized.
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 description of the embodiments are briefly introduced 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 creative efforts.
Fig. 1 is a flowchart illustrating an application operation prediction method according to an embodiment of the present application;
FIG. 2 is a flow chart illustrating a method for predicting application program operation according to another embodiment of the present application;
FIG. 3 is a flow chart illustrating a method for predicting application program operation according to yet another embodiment of the present application;
FIG. 4 is a flow chart illustrating a method for predicting application program operation according to another embodiment of the present application;
fig. 5 is a block diagram illustrating an application operation prediction apparatus according to the present application;
fig. 6 is a block diagram showing another application operation prediction apparatus proposed in the present application;
fig. 7 shows a block diagram of an electronic device for executing an application program operation prediction method according to an embodiment of the present application.
Fig. 8 is a storage unit for storing or carrying program codes for implementing an application program operation prediction method according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
As more functions can be implemented by software, more and more applications are installed in electronic devices. And the operating environment required during operation may vary from application to application. For example, the memory required may be different for applications in the video class and applications in the ticket purchase class. Specifically, for the application program of the video class, there is a high probability that the video is cached in the running process, and for the application program of the ticket class, only the resource of the text class is cached. Therefore, in order to adapt to the operating characteristics of the application program of the video class, the electronic device may allocate more memory than the application program of the ticket class to the application program of the video class so as to adapt to the operating environment of the application program of the video class.
The inventor finds that the running sequence of the plurality of application programs in the running process of the electronic equipment can be regular by researching the running process of the plurality of application programs in the electronic equipment. Therefore, if the application program to be run in the future can be predicted in advance, the running environment can be configured in advance to improve the running efficiency. For example, if it is predicted that the application program to be run in the future is a video-class application program, the electronic device may detect whether the current remaining memory is enough to be allocated to the video-class application program predicted to be started, and if not, may perform memory recovery in advance, so as to avoid performing memory recovery again in the starting process of the video-class application program, thereby improving the running efficiency of the video-class application program.
Further, the inventor finds that a prediction model can be obtained through a machine learning mode, and the running sequence of the application program in a certain time period is predicted through the prediction model. However, after intensive research on a manner of predicting the operation order of the application program in a certain period of time by using the prediction model, the inventor finds that the prediction model obtained by using the machine learning method is not very related to the difference of the actual usage habits of users of each electronic device, and further, the prediction result obtained when the electronic device operates the prediction model cannot express the actual requirement of the user. If a prediction result more meeting the user requirement needs to be obtained, a more complicated training process is needed, and higher cost is consumed in a later upgrading process.
Therefore, the inventor provides the application program operation prediction method, the application program operation prediction device and the electronic device provided in the embodiment of the application, so that for the application program predicted by the trained machine model to operate at the target time, the predicted application program to operate at the target time can be adjusted according to the specified application program operation rule, the accuracy of the finally predicted application program to operate at the target time is further improved, and meanwhile, the more accurate configuration of the operation environment can be realized.
Embodiments in the present application will be described in detail below with reference to the accompanying drawings.
Referring to fig. 1, an application operation prediction method provided in an embodiment of the present application is applied to an electronic device, and the method includes:
step S110: application run information is derived based on the trained machine model predictions, the application run information including predicted applications that will run at the target time.
It should be noted that, before step S110 is executed, the machine model may be trained through the training data, so that the trained machine model may predict an application program that will be run at a future time or at a target time. The training data may be a sequence of sequential operations of the plurality of applications, and a power state, a network state, a connection state of the external device, and the like during the operation of the applications.
In the embodiment of the present application, the target time may be understood as a time after the current application finishes running, or may be understood as a time after the current time.
Step S120: and updating the application program running information according to the target condition to obtain updated application program running information, wherein the target condition represents the specified application program running rule.
In the embodiment of the application, besides the training data is collected to train the machine model, the operation rule of the application program in the electronic device is acquired in a statistical manner. The application run rules may include the number of times the application runs, to which other applications the application will specifically jump to, and the number of times it jumps to other applications. For example, the application operation rule can be characterized in a matrix mode. Specifically, the statistical application program operation rule is as follows: application A- > application B- > application C- > application A- > application D- > application B- > application C- > application A. Then it can be found by statistics that for the above application operation rule, the kind of the application is 4, and then a matrix including four elements can be correspondingly established. The matrix established may be M ═ M0, M1, M2, M3], where M0 indicates information that application a jumps to another application (i.e., application a jumps to a subsequent application), M1 indicates information that application B jumps to another application (i.e., application B jumps to a subsequent application), M2 indicates information that application C jumps to another application (i.e., application C jumps to a subsequent application), and M3 indicates information that application D jumps to another application (i.e., application D jumps to a subsequent application).
And M0, M1, M2 and M3 can also be one-dimensional matrixes. Taking M0 as an example, M0 may be [ M00, M01, M02, M03], where M00 indicates the number of times that application a jumps to application a (i.e., whether application a is used, then application a is next), M00 indicates the number of times that application a jumps to application B (i.e., after application a, then application B is next), M00 indicates the number of times that application a jumps to application C (i.e., after application a, then application C is next), and M00 indicates the number of times that application a jumps to application D (i.e., after application a, then application D is next). The other M1, M2 and M3 are similar and will not be described in detail.
Then, after acquiring the application rule as the target condition, the electronic device may update the application running information obtained based on the trained machine model based on the application rule, so as to obtain updated application running information.
Step S130: and configuring the running environment based on the updated running information of the application program.
As one mode, after acquiring the updated application running information, the electronic device may prepare, in advance, resources required by the application in the updated application running information in the process of configuring the running environment. The resource may be a memory resource, a processor resource, or the like. Illustratively, in the case that the application running information predicted based on the trained machine model includes application a, application B, application C, and application E running sequentially, the further electronic device updates the application running information according to the target condition, and the updated application running information includes application a, application D, and application C. If the currently running application is the application a, it can be determined that the electronic device predicts that the application D will run subsequently, and further, the running environment required by the application D in the running process can be prepared in advance. Optionally, if the application program D needs to consume a relatively large memory in the running process, the electronic device may perform memory recovery in advance in the process of configuring the running environment needed by the application program D in advance, and further improve the running efficiency of the application program by performing memory recovery in advance. Optionally, if the application D needs to consume a large amount of processing resources during the running process, the electronic device may kill an idle process in advance to recover the processing resources, so that the application D has sufficient processing resources during the running process.
According to the application program operation prediction method, after application program operation information including the predicted application program which can be operated at the target time is obtained based on the prediction of the trained machine model, the application program running information is further updated according to the target condition representing the specified application program running rule to obtain updated application program running information, and then, performing running environment configuration based on the updated running information of the application program, thereby realizing the application program which is predicted to run at the target time by the trained machine model, the predicted application program which can be operated at the target time can be adjusted according to the specified application program operation rule, therefore, the accuracy of the finally predicted application program which can be operated at the target time is improved, and meanwhile, the more accurate configuration of the operation environment can be realized.
Referring to fig. 2, an application operation prediction method provided in the embodiment of the present application is applied to an electronic device, and the method includes:
step S210: application run information is derived based on the trained machine model predictions, the application run information including predicted applications that will run at the target time.
Step S211: whether the application program which does not meet the target condition exists in the application programs which can run at the target time is detected.
Step S220: and if the application programs which can be operated at the target time do not meet the target conditions, processing the application program operation information to remove the application programs which do not meet the target conditions to obtain updated application program operation information, wherein the target conditions represent the specified application program operation rules.
Optionally, the application programs used by the user and corresponding to the previous time period include application programs that are sorted in the historical use times of the application programs corresponding to the previous time period and meet the specified order. Optionally, there are a plurality of applications that will run at the target time, and the target condition represents a jump relationship between a plurality of conventional applications.
In the embodiment of the present application, one of the purposes of predicting the application to be executed subsequently is to perform configuration of a required execution environment in advance so as to improve the execution efficiency. If there are applications that are not actually run in the predicted applications, it may cause an inapplicable running environment to be configured and waste of resources.
For example, if the application running information obtained based on the trained machine model prediction includes application B, application C, and application D, and the currently running application is application B, it may be determined that application C will run after the current application B runs, and preparation of an adaptive running environment for application C may begin. If the consumption of the processor resource by the application program C is large, the electronic device can adaptively kill more idle processes, and further recover enough processor resource used by the application program C. However, the process of jumping from the application B to the application C does not conform to the usage habit of the current user of the electronic device, i.e. the application C is not run after the application B is currently run, the process of preparing the running environment adapted to the application C by the electronic device is wasted, and the running environment configured in advance for the application C may not be adapted to the running requirement of the application actually run after the application B.
Unnecessary configuration of the operating environment of the electronic device can be avoided by removing the applications that do not satisfy the target condition and are included in the application operating information predicted based on the trained machine model. For example, the application running information includes application B, application C, and application D, and application C does not meet the target condition. Then application C may be deleted from the application run information in the event that application C is detected as not meeting the aforementioned target condition.
In addition, the target condition can characterize the jump relationship among a plurality of application programs and what application programs are used by the user. For example, a plurality of applications running a higher number of times may be configured as applications that are familiar to the user.
Furthermore, after the application program deleting operation which does not meet the target condition is carried out, the jump-turn relationship may be different from the actual jump of the user. For example, if the application running information obtained based on the trained machine model prediction includes application B, application C, and application D, the running order that can be characterized is to jump from application B to application C, and then from application C to application D. And if the application program C is deleted, the jump relation is that the application program B jumps to the application program D. However, there should be another application between the application B and the application D according to the usage habit of the user.
As one mode, in order to avoid invalid operating environment configuration and to better fit the usage habit of the user, the step of processing the application operating information to remove the application that does not satisfy the target condition, and obtaining updated application operating information includes: processing the application program running information to remove the application program which does not meet the target condition to obtain the application program running information to be supplemented; and adding an application program which accords with the use habit of the user in the application program running information to be supplemented to obtain updated application program running information.
In the embodiment of the present application, the application program conforming to the use habit of the user is obtained based on a statistical method, and may have different contents from the application program training information obtained based on the trained model. Moreover, the application program according with the use habit of the user can be obtained by counting the use habit of the user by the electronic equipment, so that the application program according with the use habit of the user can be realized by aiming at a single user. However, the machine model for obtaining the application running information may be trained by the server according to different application usage records of a plurality of users, and thus, may not be well adapted to a specific usage habit of a certain user. Therefore, the application program according with the use habit of the user is added in the application program running information to be supplemented, so that the invalid running environment configuration can be avoided, and the use habit of the user can be better fitted.
Furthermore, optionally, the habit of the user of the electronic device to use the application may be staged, and the user may use the same plurality of applications in different order at different stages. For example, in the morning, a user may prefer to know some real-time news first, and then may open an information browsing application (e.g., a microblog, a browser client, etc.) first and then see whether there is a message in the social software after the electronic device is started. However, during the afternoon hours, the user may prefer to communicate some information through social software and then may primarily use a social-type application or then go to a view of an information-browsing-type application.
Therefore, as a finer granularity and at the same time, in order to more accurately update the application information output by the machine model, the electronic device may divide a plurality of time periods, and count the applications that conform to the usage habits of the user for the plurality of time periods. For example, in 24 hours a day, the electronic device may divide the day into 24 time periods, and separately perform statistics of applications that conform to the usage habits of the user for each time period. In this case, after each time period starts, the electronic device may newly count the number of times of operation of each application program in the current time period, and determine the application programs with the top-ranked number of times of operation or the application program with the largest number of times of operation as the application program that meets the usage habit of the user.
Correspondingly, the aforementioned target condition characterization is a mutual jump relationship between a plurality of application programs. Further, the target condition may be statistically obtained by a time-division manner. In this case, the foregoing target conditions may represent different operation rules of the application program in different time periods, and the electronic device may re-count the target conditions corresponding to each time period after the start of each time period. For example, the same time period division manner as the aforementioned statistics of the application program conforming to the usage habit of the user may be divided based on the target condition. In this case, optionally, the electronic device divides the time of day into a plurality of time periods, and then the electronic device needs to count the operation times of each application program for each time period, and needs to count the mutual jump relationship and times of the application programs for each time period at the same time.
Then, in this case based on the time slot, as a manner, the step of processing the application running information to remove the application not meeting the target condition to obtain the application running information to be supplemented includes: processing the application program running information to remove the application programs which do not meet the target conditions corresponding to the current time period to obtain the application program running information to be supplemented; the step of adding the application program conforming to the use habit of the user in the application program running information to be supplemented to obtain the updated application program running information comprises the following steps: and adding the application program which accords with the use habit of the user corresponding to the current time period in the running information of the application program to be supplemented.
It should be noted that the application program running information obtained based on the trained machine model may include not only a plurality of application programs but also running precedence relationships of the plurality of application programs, and then as a manner, an application program conforming to the use habit of the user is added to the application program running information to be supplemented, and in the process of obtaining updated application program running information, the application programs may be supplemented according to the original arrangement order of the application programs in the application program running information generated based on the machine model, or the application programs may be supplemented according to the target conditions and the application programs conforming to the use habit of the user.
For example, if the application running information obtained based on the trained machine model sequentially includes application a, application B, application C, application D, and application E, and it is defined that the predicted running order is also application a, application B, application C, application D, and application E. Then, when it is detected that the application B and the application E do not meet the target condition, the electronic device deletes the application B and the application E from the running information, and the obtained running information of the application to be supplemented includes the application a, the application C, and the application D. And in the application programs according with the use habits of the users, the application programs F and the application programs G which are more frequently operated in the current time period are counted. As a supplementary manner, the missing position in the application running information (i.e. the original sorting position of the deleted application) may be supplemented only with reference to the application conforming to the use habit of the user, and the updated application running information obtained by the supplementation is the application a, the application F, the application C, the application D, and the application G.
In order to better fit the actual usage habit of the user, the target conditions corresponding to the time period to which the current time belongs may be collected to supplement the missing position. For example, the application program F and the application program G still sequentially run for a relatively large number of times in the current time period, but the electronic device determines, according to the target condition of the current time period, that the application program a more directly jumps to the application program G, and then jumps to the application program F (the application program G directly jumps to the application program F, or other application programs run after the application program G jump to the application program F), so that when the electronic device performs missing position supplement, the application program G may be sorted after the application program a, the application program F may be sorted after the application program D, and then the updated content of the application program run is: application a, application G, application C, application D, and application F.
It should be noted that, in the embodiment of the present application, if the application is triggered to perform foreground operation, the application may be identified by the electronic device to perform false operation once. Illustratively, as in a certain day 9 o ' clock to 10 o ' clock period, the operation in the user's electronic device is as follows: unlocking the mobile phone- > opening the application program A- > returning to the desktop- > opening the application program B- > returning to the desktop- > opening the application program A- > returning to the desktop. Then the number of uses of application a is 2 and the number of uses of application B is 1 during this period.
Step S230: and configuring the running environment based on the updated running information of the application program.
According to the application program operation prediction method, after application program operation information including the predicted application program which can be operated at the target time is obtained based on the prediction of the trained machine model, the application program running information is further updated according to the target condition representing the specified application program running rule to obtain updated application program running information, and then, performing running environment configuration based on the updated running information of the application program, thereby realizing the application program which is predicted to run at the target time by the trained machine model, the predicted application program which can be operated at the target time can be adjusted according to the specified application program operation rule, therefore, the accuracy of the finally predicted application program which can be operated at the target time is improved, and meanwhile, the more accurate configuration of the operation environment can be realized.
In addition, in the embodiment of the application, in the specific application running information updating process, the application not meeting the target condition is removed, or the application meeting the use habit of the user is added to the application running information of the application not meeting the target condition, so that the application running information more fitting the use habit of the user is obtained, and the electronic device can more accurately configure the environment in advance. In addition, in this embodiment, the target condition and the application program that meets the use habit of the user corresponding to the current time period may be configured for each time period by dividing the time periods, so that the running order of the application program in the current time period may be predicted more accurately.
Referring to fig. 3, an application program operation prediction method provided in the embodiment of the present application is applied to an electronic device, and the method includes:
step S310: and acquiring the application program which is currently running.
Step S320: and predicting the application program to be operated after the application program which is currently operated is obtained based on the trained machine model.
Step S330: and taking the application program which is operated after the application program which is currently operated as the application program operation information.
Step S340: and updating the application program running information according to the target condition to obtain updated application program running information, wherein the target condition represents the specified application program running rule.
Step S350: and configuring the running environment based on the updated running information of the application program.
The application program operation prediction method comprises the steps of firstly obtaining an application program which is currently running, using the application program which is to be run after the application program which is currently running as application program operation information after the application program which is currently running is obtained through prediction based on a trained machine model, further updating the application program operation information according to a target condition representing a specified application program operation rule to obtain updated application program operation information, and then configuring an operation environment based on the updated application program operation information, so that the application program which is predicted to run at a target time by a trained machine model can be adjusted according to the specified application program operation rule, therefore, the accuracy of the finally predicted application program which can be operated at the target time is improved, and meanwhile, the more accurate configuration of the operation environment can be realized.
Referring to fig. 4, a method for predicting application program operation according to an embodiment of the present application includes:
step S410: training a machine model to be trained based on the historical application program running record to obtain a trained machine model; the historical application program running record comprises a plurality of pieces of record information, and each piece of record information at least comprises running time information corresponding to an application program, identifications of a previously running application program and a subsequently running application program corresponding to the application program, a charging state in the running process of the application program, a connection state of external equipment in the running process of the application program and a network state in the running process of the application program.
It should be noted that, during research, the inventors found that applications running in the electronic device may be different according to different power states, network states, and peripheral connection states of the electronic device. For example, typically in a low battery state and not in a charging state, the user may not be inclined to use a more power consuming application such as a game or video. As another example, a user of the electronic device may be less likely to use an application that requires network functionality while the data communication link is currently disconnected.
As one way, in this embodiment of the application, step S410 may be executed by a server in the cloud, and then the server performs training of the machine model and distributes the training result to the electronic device used by the user. In this way, the electronic device used by different users can upload the running records of the application program, and upload data can be generated according to a given data format in the uploading process.
Optionally, the electronic device may define the data format as:
[t，d，AC，A1，A2，c，e，n]
wherein t represents the current time and has a value range of [0,23 ]]In units of one hour; d represents the day of the week and has a value range of [0,6 ]]7 values are taken from Monday to Sunday; a. theCIndicating an application running, A1And A2Respectively represent ACThe first two applications previously used; c represents the current charging state, the value is {0,1}, 0 represents uncharged, and 1 represents charging; e represents the current earphone state, the value is {0,1}, 0 represents that the earphone is not connected, and 1 represents that the earphone is connected; n represents the current network state, the value is {0,1}, 0 represents the unconnected network, and 1 represents the connected network.
And the server may begin training the machine model after collecting a running record of a target time period (e.g., 10 days, 20 days, or even longer) uploaded by a certain electronic device. Before training, a training set may be constructed, and optionally, a part of the collected operation records may be used as data in the training set.
In this embodiment, the machine model to be trained may be trained in a variety of ways.
As one approach, a logistic regression algorithm may be employed to train the machine model to be trained. In this manner, the logistic regression algorithm uses a loss function of:
wherein: m is the total number of training set data, yiAnd the real label of the ith data is represented, and y' represents a label calculated by a logistic regression algorithm. It should be noted that the real tag represents the next application actually used by the user after the currently running application. Illustratively, among the aforementioned collected usage records are the following:
record 1: the 9:10 user has used application B.
Record 2: application C was used 9: 15.
Record 3: application D was used for 9: 40.
Then for record 1, its corresponding real tag is application C. For record 2, its real label is application D. The same is true for the labels computed by the logistic regression algorithm therein.
Furthermore, as another way, a random forest algorithm may be used to train the machine model to be trained. In this way, the division of the training samples is performed by the calculation of the entropy of the information. The information entropy formula is as follows:
wherein: n represents the number of classes of labels in the training set data, and pi represents the probability that the training sample label belongs to the second class.
Step S420: application run information is derived based on the trained machine model predictions, the application run information including predicted applications that will run at the target time.
Step S430: and updating the application program running information according to the target condition to obtain updated application program running information, wherein the target condition represents the specified application program running rule.
Step S440: and configuring the running environment based on the updated running information of the application program.
According to the application program operation prediction method, the application program which can be predicted to run at the target time and is predicted by the trained machine model can be adjusted according to the specified application program operation rule, so that the accuracy of the finally predicted application program which can be run at the target time is improved, and meanwhile, the running environment can be more accurately configured.
Referring to fig. 5, an application operation prediction apparatus 500 provided by an embodiment of the present application, which is operated on an electronic device, includes:
and an operation prediction unit 510, configured to predict, based on the trained machine model, application operation information that includes an application that is predicted to be operated at the target time.
As one way, the operation prediction unit 510 is specifically configured to obtain an application currently running; predicting an application program to be operated after the application program which is currently operated is obtained based on the trained machine model; and taking the application program which is operated after the application program which is currently operated as the application program operation information.
The prediction result updating unit 520 is configured to update the application program running information according to a target condition, so as to obtain updated application program running information, where the target condition represents a specified application program running rule.
As one mode, the prediction result updating unit 520 is specifically configured to, if there is an application that does not satisfy the target condition among the applications that will be run at the target time, process the application running information to remove the application that does not satisfy the target condition, so as to obtain updated application running information.
In this manner, the prediction result updating unit 520 is specifically configured to process the application program running information to remove the application program that does not satisfy the target condition, so as to obtain application program running information to be supplemented; and adding an application program which accords with the use habit of the user in the application program running information to be supplemented to obtain updated application program running information.
Further, the prediction result updating unit 520 is specifically configured to process the application program running information to remove the application program that does not satisfy the target condition corresponding to the current time period, so as to obtain application program running information to be supplemented; and adding the application program which accords with the use habit of the user corresponding to the current time period in the running information of the application program to be supplemented.
An execution environment configuration unit 530, configured to perform execution environment configuration based on the updated application execution information.
In one mode, the application programs used by the user and corresponding to the previous time period comprise application programs which are sorted in the historical use times of the application programs corresponding to the previous time period and meet the specified sequence.
In one approach, there are multiple applications that will run at a target time, and the target condition characterizes a jump relationship between the multiple applications that are conventionally used.
As shown in fig. 6, the apparatus 500 further includes:
the model training unit 540 is configured to train the machine model to be trained based on the historical application program operation records to obtain a trained machine model; the historical application program running record comprises a plurality of pieces of record information, and each piece of record information at least comprises running time information corresponding to an application program, identifications of a previously running application program and a subsequently running application program corresponding to the application program, a charging state in the running process of the application program, a connection state of external equipment in the running process of the application program and a network state in the running process of the application program.
It should be noted that, in the present application, it is a prior art that can be specifically applied to how to encode audio data according to the audio encoding type, and the present application will not be described in detail.
An electronic device provided by the present application will be described with reference to fig. 7.
Referring to fig. 7, based on the image processing method and apparatus, another electronic device 200 capable of executing the application operation prediction method is further provided in the embodiment of the present application. The electronic device 200 includes one or more processors 102 (only one shown), a memory 104, a network module 106, and an acceleration sensor 108 coupled to each other. The memory 104 stores programs that can execute the content of the foregoing embodiments, and the processor 102 can execute the programs stored in the memory 104.
The Memory 104 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 104 may be used to store instructions, programs, code sets, or instruction sets. The memory 104 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The storage data area may also store data created by the terminal 100 in use, such as a phonebook, audio-video data, chat log data, and the like.
The network module 106 is configured to receive and transmit electromagnetic waves, and achieve interconversion between the electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices, such as a wireless access point. The network module 106 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and so forth. The network module 106 may also be used as a network adapter for the electronic device 200 to access the network directly through a line connection. The network may comprise a cellular telephone network, a wireless local area network, or a metropolitan area network.
The acceleration sensor 108 may include a gravitational acceleration sensor, a gyro sensor, and the like.
Referring to fig. 8, a block diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer-readable medium 800 has stored therein a program code that can be called by a processor to execute the method described in the above-described method embodiments.
The computer-readable storage medium 800 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium 800 includes a non-volatile computer-readable storage medium. The computer readable storage medium 800 has storage space for program code 810 to perform any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program code 810 may be compressed, for example, in a suitable form.
In summary, according to the application program operation prediction method, device and electronic device provided by the present application, after obtaining application program operation information including a predicted application program that will be operated at a target time based on a trained machine model prediction, the application program operation information is further updated according to a target condition representing a specified application program operation rule to obtain updated application program operation information, and then operation environment configuration is performed based on the updated application program operation information, so that for the application program that will be operated at the target time predicted by the trained machine model, the predicted application program that will be operated at the target time can be adjusted according to the specified application program operation rule, and the accuracy of the finally predicted application program that will be operated at the target time is further improved, meanwhile, more accurate configuration of the operating environment can be realized.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will 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 necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (11)
1. An application program operation prediction method, applied to an electronic device, the method comprising:
obtaining application program running information based on the trained machine model prediction, wherein the application program running information comprises application programs which are predicted to run at a target time;
updating the application program running information according to a target condition to obtain updated application program running information, wherein the target condition represents a specified application program running rule;
and configuring the running environment based on the updated running information of the application program.
2. The method of claim 1, wherein the step of updating the application running information according to the target condition to obtain updated application running information comprises:
and if the application programs which can be operated at the target time do not meet the target conditions, processing the application program operation information to remove the application programs which do not meet the target conditions, and obtaining updated application program operation information.
3. The method of claim 2, wherein the step of processing the application running information to remove the application not meeting the target condition to obtain updated application running information comprises:
processing the application program running information to remove the application program which does not meet the target condition to obtain the application program running information to be supplemented;
and adding an application program which accords with the use habit of the user in the application program running information to be supplemented to obtain updated application program running information.
4. The method according to claim 3, wherein the step of processing the application running information to remove the application not meeting the target condition to obtain the application running information to be supplemented comprises: processing the application program running information to remove the application programs which do not meet the target conditions corresponding to the current time period to obtain the application program running information to be supplemented;
the step of adding the application program conforming to the use habit of the user in the application program running information to be supplemented to obtain the updated application program running information comprises the following steps: and adding the application program which accords with the use habit of the user corresponding to the current time period in the running information of the application program to be supplemented.
5. The method according to claim 4, wherein the application programs used by the user and corresponding to the previous time period comprise application programs which are sorted in the historical use times of the application programs corresponding to the previous time period and meet the specified sequence.
6. The method of claim 2, wherein there are a plurality of applications that will run at a target time, and wherein the target condition characterizes a jump relationship between a plurality of commonly used applications.
7. The method of claim 1, wherein the step of deriving application run information based on trained machine model prediction comprises:
acquiring an application program which is currently running;
predicting an application program to be operated after the application program which is currently operated is obtained based on the trained machine model;
and taking the application program which is operated after the application program which is currently operated as the application program operation information.
8. The method of claim 1, wherein the step of deriving application run information based on trained machine model prediction is preceded by the step of:
training a machine model to be trained based on the historical application program running record to obtain a trained machine model;
the historical application program running record comprises a plurality of pieces of record information, and each piece of record information at least comprises running time information corresponding to an application program, identifications of a previously running application program and a subsequently running application program corresponding to the application program, a charging state in the running process of the application program, a connection state of external equipment in the running process of the application program and a network state in the running process of the application program.
9. An apparatus for predicting application program operation, the apparatus being operable on an electronic device, the apparatus comprising:
the operation prediction unit is used for predicting and obtaining application program operation information based on the trained machine model, and the application program operation information comprises application programs which are predicted to operate at the target time;
the prediction result updating unit is used for updating the application program running information according to a target condition to obtain updated application program running information, and the target condition represents a specified application program running rule;
and the running environment configuration unit is used for carrying out running environment configuration based on the updated application program running information.
10. An electronic device comprising one or more processors and memory;
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-8.
11. A computer-readable storage medium, having program code stored therein, wherein the method of any of claims 1-8 is performed when the program code is run.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911357776.8A CN113031982A (en) | 2019-12-25 | 2019-12-25 | Application program operation prediction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911357776.8A CN113031982A (en) | 2019-12-25 | 2019-12-25 | Application program operation prediction method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113031982A true CN113031982A (en) | 2021-06-25 |
Family
ID=76458252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911357776.8A Pending CN113031982A (en) | 2019-12-25 | 2019-12-25 | Application program operation prediction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113031982A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117111997A (en) * | 2023-10-08 | 2023-11-24 | 西安大合智能科技有限公司 | FPGA configuration file remote upgrading and updating method |
-
2019
- 2019-12-25 CN CN201911357776.8A patent/CN113031982A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117111997A (en) * | 2023-10-08 | 2023-11-24 | 西安大合智能科技有限公司 | FPGA configuration file remote upgrading and updating method |
| CN117111997B (en) * | 2023-10-08 | 2024-03-22 | 西安大合智能科技有限公司 | FPGA configuration file remote upgrading and updating method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108076224B (en) | Application program control method and device, storage medium and mobile terminal | |
| CN109324902B (en) | Method for adjusting working frequency of mobile terminal, mobile terminal and storage medium | |
| CN107632697B (en) | Processing method, device, storage medium and the electronic equipment of application program | |
| CN104808892A (en) | Application icon ordering method, device, system and associated equipment | |
| CN107402808B (en) | Process management method, device, storage medium and electronic equipment | |
| CN111160624B (en) | User intention prediction method, user intention prediction device and terminal equipment | |
| CN107870810B (en) | Application cleaning method and device, storage medium and electronic equipment | |
| CN110727697A (en) | Data processing method and device, storage medium and electronic device | |
| CN112069195A (en) | Database-based message transmission method and device, electronic equipment and storage medium | |
| CN115408696A (en) | Application identification method and electronic equipment | |
| EP3506599A1 (en) | Method for synchronizing contact information, apparatus, medium, electronic device and system | |
| CN114995791A (en) | API (application program interface) polymerization method and device, electronic equipment and storage medium | |
| CN107748697B (en) | Application closing method and device, storage medium and electronic equipment | |
| CN113031982A (en) | Application program operation prediction method and device and electronic equipment | |
| CN111311014B (en) | Service data processing method, device, computer equipment and storage medium | |
| CN110727605B (en) | Memory recovery method and device and electronic equipment | |
| CN114402313A (en) | Label updating method and device, electronic equipment and storage medium | |
| CN107870811B (en) | Application cleaning method and device, storage medium and electronic equipment | |
| CN110086835B (en) | Application program control method, terminal, server and system | |
| CN113050783A (en) | Terminal control method and device, mobile terminal and storage medium | |
| CN111045507B (en) | List management and control method, device, mobile terminal and storage medium | |
| CN115037654A (en) | Flow statistical method and device, electronic equipment and readable storage medium | |
| CN113055984B (en) | Terminal control method and device, mobile terminal and storage medium | |
| CN112988706A (en) | Data management method and device and electronic controller | |
| CN107870809B (en) | Application closing method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |