CN114860331A - Application resource preloading method and device, electronic equipment and storage medium - Google Patents
Application resource preloading method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114860331A CN114860331A CN202210334225.5A CN202210334225A CN114860331A CN 114860331 A CN114860331 A CN 114860331A CN 202210334225 A CN202210334225 A CN 202210334225A CN 114860331 A CN114860331 A CN 114860331A
- Authority
- CN
- China
- Prior art keywords
- application
- function
- application program
- user
- application function
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 230000006870 function Effects 0.000 claims abstract description 315
- 230000008569 process Effects 0.000 claims description 48
- 238000012549 training Methods 0.000 claims description 36
- 238000004891 communication Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000036316 preload Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012905 input function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44521—Dynamic linking or loading; Link editing at or after load time, e.g. Java class loading
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Stored Programmes (AREA)
Abstract
The embodiment of the invention provides a preloading method and device of application resources, electronic equipment and a storage medium, wherein the method comprises the following steps: before a user uses an application program, application function prediction is carried out through application function use information generated when the user uses the application program, the tendency application function of the user when the user uses the application program is determined, application resources of the application function which the user tends to use are preloaded, and then the resources can be loaded according to needs before the user uses the application program, especially the resources of the application function which the user tends to use are preloaded, the downloading of the application resources is reduced while good use experience is provided for the user through preloaded contents, and the flow consumption and the memory volume of an application program data packet are effectively reduced.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method for preloading application resources, an apparatus for preloading application resources, an electronic device, and a computer-readable storage medium.
Background
With the rapid development of mobile internet, intelligent terminals are becoming the main platform of human-computer interaction. In real life, the intelligent terminal becomes necessary for everyone, is also a window for people to interact with the world every day, and plays an important role for everyone. Various application programs can be operated in the intelligent terminal, and various functions provided by the application programs can meet different requirements of users in life. For an application program, in the development process, not only the normal business logic needs to be completed, but also the problems of user experience, system performance and the like in the use process of a user need to be considered. For an application program, the application functions that can be provided by the application program are rich and diverse, and in order to provide better use experience for users, for example, guarantee page loading smoothness, loading speed, audio and video playing smoothness and the like, the application program is often processed in a large resource preloading mode in the development process. However, for such a processing method, on one hand, the memory volume of the application data packet is increased, which brings great inconvenience to the user in downloading or using, and on the other hand, even if the resource is removed from the application data packet, the user needs to download the whole amount of resource when using the application, which undoubtedly brings more traffic consumption and wastes network bandwidth resources.
Disclosure of Invention
Embodiments of the present invention provide a method and an apparatus for preloading application resources, an electronic device, and a computer-readable storage medium, so as to solve or partially solve the problems that when processing resources of an application program, an application data packet is large in size, and a resource download needs to consume a large amount of traffic.
The embodiment of the invention discloses a preloading method of application resources, which comprises the following steps:
responding to the starting operation of the application program, and acquiring application function use information generated in the process of using the application program by a user history;
determining a target application function which is inclined to be used by a user from preset application functions provided by the application program according to the application function use information;
and preloading application resources corresponding to the target application function.
Optionally, the obtaining application function usage information generated in a process of using the application program by a user in history in response to the start operation of the application program includes:
responding to the starting operation of the application program, and acquiring user account information logged in the application program;
and if the user account information is old user account information, acquiring application function use information generated in the process of using the application program by the old user account information in history.
Optionally, the determining, according to the application function usage information, a target application function that a user tends to use from preset application functions provided by the application program includes:
and inputting the application function use information into a function identification model corresponding to the application program, and screening preset application functions provided by the application program to obtain a target application function corresponding to the old user account information.
Optionally, the application function usage information at least includes a target application function used historically by the old user account information, a first usage duration of the target application function, and a first total usage duration of the old user account information used historically by the application program, and the inputting the application function usage information into a function identification model corresponding to the application program filters preset application functions provided by the application program to obtain the target application function corresponding to the old user account information includes:
and inputting the target application function, the first using time length and the first using total time length into a function identification model corresponding to the application program to screen preset application functions provided by the application program, and obtaining at least one target application function corresponding to the old user account information.
Optionally, the method further comprises:
if the user account information is new user account information, displaying an application function page, wherein the application function page comprises a preset application label corresponding to the preset application function;
responding to the selection operation aiming at least one preset application label, and determining a target application label;
and determining a target application function corresponding to the target application label from a preset application terminal provided by the application program.
Optionally, the function recognition model is generated by:
acquiring application use data generated in the running process of the application program, wherein the application use data at least comprises the preset application functions, second use duration of each preset application function and total second use duration of the application program used by different account information;
and performing model training according to the preset application functions, the second use duration of each preset application function and the second total use duration to generate a function recognition model corresponding to the application program.
Optionally, the acquiring application usage data generated in the running process of the application program includes:
if the fact that the version of the application program is updated is detected, determining a current version of the application program and a historical version corresponding to the current version, wherein the historical version is a previous version of the current version;
acquiring first updating time of the historical version and second updating time of the current version;
obtaining application usage data of the application program between the first update time and the second update time.
The embodiment of the invention also discloses a preloading device of application resources, which comprises:
the information acquisition module is used for responding to the starting operation of the application program and acquiring application function use information generated in the process of using the application program by a user in history;
the application function prediction module is used for determining a target application function which is inclined to be used by a user from preset application functions provided by the application program according to the application function use information;
and the application resource loading module is used for preloading the application resources corresponding to the target application functions.
Optionally, the information obtaining module is specifically configured to:
responding to the starting operation of the application program, and acquiring user account information logged in the application program;
and if the user account information is old user account information, acquiring application function use information generated in the process of using the application program by the old user account information in history.
Optionally, the application function prediction module is specifically configured to:
and inputting the application function use information into a function identification model corresponding to the application program, and screening preset application functions provided by the application program to obtain a target application function corresponding to the old user account information.
Optionally, the application function usage information at least includes a target application function used by the old user account information history, a first usage duration of the target application function, and a first total usage duration of the application used by the old user account information history, and the application function prediction module is specifically configured to:
and inputting the target application function, the first using time length and the first using total time length into a function identification model corresponding to the application program to screen preset application functions provided by the application program, and obtaining at least one target application function corresponding to the old user account information.
Optionally, the method further comprises:
the function page display module is used for displaying an application function page if the user account information is new user account information, and the application function page comprises a preset application tag corresponding to the preset application function;
the application tag determining module is used for responding to selection operation aiming at least one preset application tag and determining a target application tag;
and the application function determining module is used for determining the target application function corresponding to the target application label from a preset application terminal provided by the application program.
Optionally, the function recognition model is generated by:
the application use data acquisition module is used for acquiring application use data generated in the running process of the application program, and the application use data at least comprises the preset application functions, second use duration of each preset application function and second total use duration of the application program used by different account information;
and the model training module is used for carrying out model training according to the preset application functions, the second use duration of each preset application function and the second total use duration to generate a function recognition model corresponding to the application program.
Optionally, the usage data acquiring module is specifically configured to:
if the fact that the version of the application program is updated is detected, determining a current version of the application program and a historical version corresponding to the current version, wherein the historical version is a previous version of the current version;
acquiring first updating time of the historical version and second updating time of the current version;
obtaining application usage data of the application program between the first update time and the second update time.
The embodiment of the invention also discloses electronic equipment which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory finish mutual communication through the communication bus;
the memory is used for storing a computer program;
the processor is configured to implement the method according to the embodiment of the present invention when executing the program stored in the memory.
Also disclosed is a computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform a method according to an embodiment of the invention.
The embodiment of the invention has the following advantages:
in the embodiment of the invention, in the process of using the application program by a user, a terminal can respond to the starting operation of the application program to acquire application function use information generated in the process of using the application program by the user in history, then can determine a target application function which is inclined to be used by the user from preset application functions provided by the application program according to the application function use information, and then can pre-load application resources corresponding to the target application function, so that before the user uses the application program, application function prediction is carried out according to the application function use information generated when the user uses the application program, the inclined application function of the user when using the application program is determined, the application resources of the inclined application function of the user are pre-loaded, and further the resource can be loaded as required before the user uses the application program, particularly the resource pre-loading is carried out on the application function which the user tends to use, the method and the device have the advantages that the downloading of application resources is reduced while good use experience is provided for users through the pre-loaded content, and the flow consumption and the memory volume of the application program data packet are effectively reduced.
Drawings
Fig. 1 is a flowchart illustrating steps of a method for preloading application resources according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of model training and application provided in an embodiment of the present invention;
fig. 3 is a block diagram of a preloading device for application resources provided in an embodiment of the present invention;
FIG. 4 is a block diagram of an electronic device provided in an embodiment of the invention;
fig. 5 is a schematic diagram of a computer-readable medium provided in an embodiment of the invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As an example, with the rapid development of the mobile internet, the mobile terminal gradually becomes a main platform for human-computer interaction, and in the application development process, a developer needs to complete normal business logic and needs to consider the problems of user experience, system performance and the like. For an application program, the application functions that can be provided by the application program are rich and diverse, and in order to provide better use experience for users, for example, guarantee page loading smoothness, loading speed, audio and video playing smoothness and the like, the application program is often processed in a large resource preloading mode in the development process. However, for this processing method, on one hand, the memory volume of the application data packet is increased, which brings great inconvenience to the user in downloading or using, on the other hand, even if the resource is removed from the application data packet, the background full-amount downloading needs to be performed when the user opens the application for the first time, and in the actual using process, part of the functional users in the application may never use, which undoubtedly brings more traffic consumption, and wastes network bandwidth resources.
In view of the above, one of the core invention points of the present invention is that, in the process of using an application program by a user, a terminal can respond to the starting operation of the application program to obtain application function use information generated in the process of using the application program by the user historically, then can determine a target application function which is intended to be used by the user from preset application functions provided by the application program according to the application function use information, and then can preload application resources corresponding to the target application function, so that before the application program is used by the user, application function prediction is performed according to the application function use information generated when the user uses the application program, the intended application function when the user uses the application program is determined, the application resources of the application function which is intended by the user are preloaded, and further, the resources can be loaded as required before the user uses the application program, especially, the resource preloading is carried out on the application functions which are prone to be used by the user, the downloading of the application resources is reduced while good use experience is provided for the user through the preloading content, and the flow consumption and the memory volume of the application program data packet are effectively reduced.
Specifically, referring to fig. 1, a flowchart of steps of a method for preloading application resources provided in the embodiment of the present invention is shown, and the method specifically includes the following steps:
optionally, the embodiment of the present invention may be applied to a user terminal, where a corresponding application program may be run in the user terminal, and an application interface is displayed through a graphical user interface of the user terminal, so that a user may perform a corresponding operation in the application interface. The user terminal may be a desktop computer, a notebook computer, a tablet computer, a mobile terminal, and the like, and the application program may include a life application program, an audio application program, a game application program, a job hunting application program, and the like.
For the starting of the application program, the starting may include running the application program for the first time after the user downloads and installs the application program in the terminal, cold starting of the application program, background starting of the application program, and the like.
In specific implementation, the terminal may respond to the starting operation of the application program, and obtain application function use information generated in the process of historical use of the application program by the user, so as to predict the application functions that the user tends to use according to the application function use information, and judge the tendency of the user to a certain application function or certain application functions in the application program, where the tendency may be a preference degree representing the user to some application functions in the application program, for example, for a certain application program, the terminal has functions of short video, text reading, and the like, and when the user only uses the short video function in daily life, the terminal indicates that the user prefers to use the short video function of the application program; for another application program, the function of finding rooms, finding cars, searching for jobs and the like is provided, and the user only uses the application program to find rooms on line in daily life, which indicates that the user prefers to use the room finding function of the application program.
The application function usage information may include an application function, a usage duration of the application function, a total usage duration of the application program, and the like. For the application function, the service content which can be provided for the user by the application program can be the application function such as online house watching, online car finding, online job hunting, short video browsing and the like; for the use duration, the use duration can be the duration of the user staying at a page of a certain application function of the application program (in the page staying process, the user can perform browsing, clicking, commenting, collecting, praising, forwarding and other operations), and by counting the use duration of each application function of the user using the application program, the main intention of the user using the application program can be effectively reflected, and the statistical dimension interference caused by the user mistakenly touching in the use process is reduced; for the total usage duration, it may be a duration that the user stays on a page of the application (i.e. a duration that the application runs in the foreground), which may reflect a user's patience value for using the application, and a longer total usage duration of a user on the application indicates that the user is more inclined to use the application, etc., which is not limited in the present invention.
It should be noted that all the application data acquisition related to the application program proposed in the present example is performed under the premise of complying with the corresponding data protection regulation policy of the country of the location and obtaining the authorization given by the corresponding terminal owner.
In an optional embodiment, for the acquisition of the application function use information, the terminal may respond to a start operation of the application program to acquire user account information logged in the application program, and if the user account information is old user account information, acquire application function use information generated in a process of historical use of the application program by the old user account information; if the user account information is new user account information, the terminal can display an application function page, the application function page comprises application tags corresponding to application functions of the application programs, then, the selection operation aiming at least one application tag is responded, the target application tag is determined, different user requirement obtaining modes are provided aiming at different users, the application functions can be predicted according to the data of the application programs used by the old users in advance, the new users can be positioned according to the application tags selected by the users in real time, and the flexibility of application function identification is effectively improved.
In a specific implementation, a user can log in corresponding user account information in an application program, a terminal can judge whether the user is a new user or not through the total use duration of the user account information in the application program, and if the user is an old user and represents that the user uses the application program, the application function use information corresponding to the user account information can be obtained, so that the application function tendency can be predicted according to the historical behavior of the user; if the user is a new user, the application function page can be displayed after the user logs in the application program, the application function page can include application tags corresponding to the application functions of the application program, the user can select at least one application tag according to the requirements, the preferences and the like of the user, and therefore the terminal can determine a target application tag according to the selection operation of the user so as to pre-load application resources for the corresponding application function.
102, determining a target application function which is inclined to be used by a user from preset application functions provided by the application program according to the application function use information;
for the application tag, each application function of the application program can correspond to one application tag, and when the user is identified to belong to a new user through the user account information, the terminal can directly determine the target application function which is inclined to be used by the user according to the target application tag selected by the user in the application function page.
For the old user, after the terminal acquires the application function use information corresponding to the account information, the application function use information can be input into the function identification model corresponding to the application program to screen the preset application function provided by the application program, and at least one target application function corresponding to the account information of the old user is obtained, so that the application function of user tendency is predicted in a model identification mode, the application program running on the terminal can download related application resources as required, and the application resources of the application program are prevented from being downloaded in full.
Optionally, the application information may include a target application function used historically by the old user account information, a first usage duration of the target application function, and a first total usage duration of the old user account information used historically by the application program, and then the target application function, the first usage duration, and the first total usage duration may be input into a function recognition model corresponding to the application program for application function prediction, so as to obtain at least one target application function corresponding to the old user account information. For example, assuming that the application includes an application a, an application B, an application C, an application D, an application E, and the like, where the user has used the application a, the application C, and the application E in advance, and the usage duration of the application a is T1, the usage duration of the application C is T2, and the usage duration of the application E is T3, then the total usage duration Δ T of the application by the user is T1+ T2+ T3, and then the user history may be filtered for the preset application functions provided by the application in the application usage information input function recognition model used by the application, so as to obtain at least one target application function that the user prefers to use the application, so as to preload the application resources for the target application function.
In addition, for a new user, because the application function use information generated in the process of using the application program historically by the user cannot be acquired, the application function page of the application program can be displayed through the graphical user interface of the terminal under the condition that the user is judged to belong to the new user, and the new user can select a favorite application label in the application function page in real time, so that the terminal can determine at least one target application function which is preferentially used by the user for the application program according to the application label selected by the user.
In the above process, the application program needs to be logged in by the user as an example, and in the case that the user does not need to log in, the application resource corresponding to the relevant application function may also be preloaded by providing the application function page to the user and in the process of using the application program at the present time according to the application tag selected by the user.
In an alternative embodiment, for the above function recognition model, it may be generated as follows: acquiring application use data generated in the running process of the application program, wherein the application use data at least comprises each preset application function of the application program, second use duration of each preset application function and second total use duration of different account information for using the application program, and then performing model training according to the application function, the second use duration of each application function and the second total use duration to generate a function identification model corresponding to the application program.
In addition, after the function identification model is obtained, the function identification model can be integrated into the application program and continuously updated iteratively in the process that the user uses the application program, specifically, the model can be updated when the version of the application program is updated, or the model can be updated by setting a corresponding update period, and the like. For example, if it is detected that the version of the application program is updated, the current version of the application program and a historical version corresponding to the current version are determined, the historical version is a previous version of the current version, then a first update time of the historical version and a second update time of the current version are obtained, and then application use data of the application program between the first update time and the second update time are obtained.
In specific implementation, the application use data is closely related to the personal behavior of the user, and the application program can acquire, count, analyze and the like the user behavior data under the condition that the user obtains the user authorization in the process of using the application program by the user. For application usage data, it may be usage data of an application program for different users, after the application usage data is obtained, in order to ensure validity of the data, the data may be cleaned first to obtain training sample data, specifically, the application usage data includes second usage duration of application functions of the application program used by different users and total usage duration of the application program, and then the data such as the application functions, the second usage duration, the total usage duration, and the like may be used as a piece of training data to implement data cleaning, for example, the training sample data may include:
application function A, use duration T1, use total duration DeltaT 1;
application function A, use duration T2, use total duration DeltaT 2;
an application function B, a use duration T3 and a total use duration delta T3;
an application function C, a use duration T4, and a total use duration DeltaT 4;
application function D, usage duration T5, total usage duration Δ T5, and so on.
After the training sample data is determined, feature extraction can be performed on the application functions in the training sample data to obtain functional training features, feature extraction is performed on the second use duration to obtain functional use training features, feature extraction is performed on the total use duration to obtain application use training features, and then the functional training features, the functional use training features and the application use training features are adopted to train to obtain a functional recognition model corresponding to the application program.
Optionally, the function recognition model may include an input layer, a mapping layer, and an output layer, where the output layer may include a plurality of output nodes, and in the process of model training, feature extraction may be performed on a preset class name attribute through the input layer to obtain a class name training feature, and feature extraction may be performed on an application function to obtain a function training feature, feature extraction may be performed on the second usage duration to obtain a function usage training feature, and feature extraction may be performed on the total usage duration to obtain an application usage training feature; and inputting the function training characteristics, the function using training characteristics and the application using training characteristics into a mapping layer, mapping through an activation function of each neuron in the mapping layer, outputting a mapping result to an output layer to generate a corresponding predicted value, comparing the predicted value with a preset reference value, and performing reverse training on the function recognition model according to the comparison result.
The reference value may be a value set by a developer for an ideal training result of the model, and may correspond to a loss function, where the smaller the loss function is, the better the model training result is, the class name training feature and the page training feature may be input into a preset function recognition model for iteration, and a plurality of loss functions of the function recognition model after each iteration are calculated, and when the plurality of loss functions of the function recognition model after iteration are minimized, the iteration is stopped, and the function recognition model is generated.
Specifically, whether the multiple gradient values meet the preset threshold condition or not can be judged through the output nodes of the models; if not, updating the parameters of the activation function of each neuron according to the plurality of gradient values, and continuing to iterate the function identification model; and if so, generating a function recognition model.
For the parameter update of the activation function, the parameter may be updated in the target gradient direction based on a gradient descent strategy. In a specific implementation, a learning rate can be preset, and the updating step length of the parameters in each iteration is controlled, so that the function identification model is finally obtained. In addition, in practice, because the minimum value of the loss function is often difficult to achieve, model iteration can be controlled by setting iteration times, and the model training can be considered to be finished when the loss function reaches an expected value or is basically kept unchanged.
The application resources for the application functions can include pictures, videos, audios, texts and the like, after the target application function which is preferentially used by the user is determined, the application resources corresponding to the target application function can be obtained, and the application resources are pre-loaded, so that in the process that the user uses the determined target application program, due to the fact that the application resources are pre-loaded, the time for the terminal to obtain the resources and load the resources can be greatly reduced, good use experience is provided for the user, meanwhile, the application resources are downloaded according to needs, and flow consumption and the memory volume of an application program data packet are effectively reduced.
In the embodiment of the invention, in the process of using the application program by a user, a terminal can respond to the starting operation of the application program to acquire application function use information generated in the process of using the application program by the user in history, then can determine a target application function which is inclined to be used by the user from preset application functions provided by the application program according to the application function use information, and then can pre-load application resources corresponding to the target application function, so that before the user uses the application program, application function prediction is carried out according to the application function use information generated when the user uses the application program, the inclined application function of the user when using the application program is determined, the application resources of the inclined application function of the user are pre-loaded, and further the resource can be loaded as required before the user uses the application program, particularly the resource pre-loading is carried out on the application function which the user tends to use, the method and the device have the advantages that the downloading of application resources is reduced while good use experience is provided for users through the pre-loaded content, and the flow consumption and the memory volume of the application program data packet are effectively reduced.
In order to make those skilled in the art better understand the technical solutions of the embodiments of the present invention, the following is an exemplary description.
Referring to fig. 2, a schematic diagram of model training and application provided in the embodiment of the present invention is shown, which specifically includes:
1. initial model: according to the data standard, sample data is prepared, and preliminary training of a data model is carried out based on an algorithm, a basic model is trained, the model prediction effect of the basic model cannot be accurately predicted, and the basic model needs to be updated subsequently.
2. Updating the model: the basic model is integrated into the application program, data related to user habits are collected in the using process of a user, data cleaning and filtering are carried out on the data according to rules, a data set meeting the standards is obtained, the obtained data is used for updating the model, the accuracy of the model for the personalized prediction of the user is further improved, and the continuous updating and iteration process is achieved.
3. Model prediction: through updating and iterating the model, the iterated model can achieve certain personalized accuracy, a prediction result is output, and the scene preloaded with resources is intelligently downloaded according to the result and the requirement.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 3, a block diagram of a structure of a preloading device for application resources provided in an embodiment of the present invention is shown, and specifically, the structure may include the following modules:
an information obtaining module 301, configured to, in response to an application program starting operation, obtain application function usage information generated in a process of using the application program by a user historically;
an application function prediction module 302, configured to determine, according to the application function usage information, a target application function that a user tends to use from preset application functions provided by the application program;
an application resource loading module 303, configured to preload an application resource corresponding to the target application function.
In an optional embodiment, the information obtaining module 301 is specifically configured to:
responding to the starting operation of the application program, and acquiring user account information logged in the application program;
and if the user account information is old user account information, acquiring application function use information generated in the process of using the application program by the old user account information in history.
In an optional embodiment, the application function prediction module 302 is specifically configured to:
and inputting the application function use information into a function identification model corresponding to the application program, and screening preset application functions provided by the application program to obtain a target application function corresponding to the old user account information.
In an optional embodiment, the application function usage information at least includes a target application function used by the old user account information history, a first usage duration of the target application function, and a first total usage duration of the application used by the old user account information history, and the application function prediction module 302 is specifically configured to:
and inputting the target application function, the first using time length and the first using total time length into a function identification model corresponding to the application program to screen preset application functions provided by the application program, and obtaining at least one target application function corresponding to the old user account information.
In an alternative embodiment, further comprising:
the function page display module is used for displaying an application function page if the user account information is new user account information, and the application function page comprises a preset application tag corresponding to the preset application function;
the application tag determining module is used for responding to selection operation aiming at least one preset application tag and determining a target application tag;
and the application function determining module is used for determining the target application function corresponding to the target application label from a preset application terminal provided by the application program.
In an alternative embodiment, the function recognition model is generated by:
the application use data acquisition module is used for acquiring application use data generated in the running process of the application program, and the application use data at least comprises the preset application functions, second use duration of each preset application function and second total use duration of the application program used by different account information;
and the model training module is used for carrying out model training according to the preset application functions, the second use duration of each preset application function and the second total use duration to generate a function recognition model corresponding to the application program.
In an optional embodiment, the usage data obtaining module is specifically configured to:
if the fact that the version of the application program is updated is detected, determining a current version of the application program and a historical version corresponding to the current version, wherein the historical version is a previous version of the current version;
acquiring first updating time of the historical version and second updating time of the current version;
obtaining application usage data of the application program between the first update time and the second update time.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
In addition, an electronic device is further provided in the embodiments of the present invention, as shown in fig. 4, and includes a processor 401, a communication interface 402, a memory 403, and a communication bus 404, where the processor 401, the communication interface 402, and the memory 403 complete mutual communication through the communication bus 404,
a memory 403 for storing a computer program;
the processor 401, when executing the program stored in the memory 403, implements the following steps:
responding to the starting operation of the application program, and acquiring application function use information generated in the process of using the application program by a user history;
determining a target application function which is inclined to be used by a user from preset application functions provided by the application program according to the application function use information;
and preloading application resources corresponding to the target application function.
In an optional embodiment, the obtaining application function usage information generated during a user's historical usage of the application program in response to a start operation of the application program includes:
responding to the starting operation of the application program, and acquiring user account information logged in the application program;
and if the user account information is old user account information, acquiring application function use information generated in the process of using the application program by the old user account information in history.
In an optional embodiment, the determining, according to the application function usage information, a target application function that a user tends to use from preset application functions provided by the application program includes:
and inputting the application function use information into a function identification model corresponding to the application program, and screening preset application functions provided by the application program to obtain a target application function corresponding to the old user account information.
In an optional embodiment, the application function usage information at least includes a target application function used by the old user account information in history, a first usage duration of the target application function, and a first total usage duration of the old user account information in history for using the application program, and the inputting the application function usage information into a function identification model corresponding to the application program filters preset application functions provided by the application program to obtain the target application function corresponding to the old user account information includes:
and inputting the target application function, the first using time length and the first using total time length into a function identification model corresponding to the application program to screen preset application functions provided by the application program, and obtaining at least one target application function corresponding to the old user account information.
In an alternative embodiment, further comprising:
if the user account information is new user account information, displaying an application function page, wherein the application function page comprises a preset application label corresponding to the preset application function;
responding to the selection operation aiming at least one preset application label, and determining a target application label;
and determining a target application function corresponding to the target application label from a preset application terminal provided by the application program.
In an alternative embodiment, the function recognition model is generated by:
acquiring application use data generated in the running process of the application program, wherein the application use data at least comprises the preset application functions, second use duration of each preset application function and total second use duration of the application program used by different account information;
and performing model training according to the preset application functions, the second use duration of each preset application function and the second total use duration to generate a function recognition model corresponding to the application program.
In an alternative embodiment, the acquiring application usage data generated during the running of the application program includes:
if the fact that the version of the application program is updated is detected, determining a current version of the application program and a historical version corresponding to the current version, wherein the historical version is a previous version of the current version;
acquiring first updating time of the historical version and second updating time of the current version;
obtaining application usage data of the application program between the first update time and the second update time.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In another embodiment provided by the present invention, as shown in fig. 5, a computer-readable storage medium 501 is further provided, which stores instructions that, when executed on a computer, cause the computer to execute the preloading method of application resources described in the above embodiments.
In a further embodiment of the present invention, there is also provided a computer program product containing instructions, which when run on a computer, causes the computer to execute the preloading method of application resources described in the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A method for preloading application resources is characterized by comprising the following steps:
responding to the starting operation of the application program, and acquiring application function use information generated in the process of using the application program by a user history;
determining a target application function which is inclined to be used by a user from preset application functions provided by the application program according to the application function use information;
and preloading application resources corresponding to the target application function.
2. The method according to claim 1, wherein the obtaining application function usage information generated during the historical usage of the application program by the user in response to the starting operation of the application program comprises:
responding to the starting operation of an application program, and acquiring user account information logged in the application program;
and if the user account information is old user account information, acquiring application function use information generated in the process of using the application program by the old user account information in history.
3. The method according to claim 2, wherein the determining, according to the application function usage information, a target application function that a user tends to use from preset application functions provided by the application program comprises:
and inputting the application function use information into a function identification model corresponding to the application program, and screening preset application functions provided by the application program to obtain a target application function corresponding to the old user account information.
4. The method according to claim 3, wherein the application function usage information at least includes a target application function historically used by the old user account information, a first usage duration of the target application function, and a first total usage duration of the application program historically used by the old user account information, and the inputting the application function usage information into a function recognition model corresponding to the application program filters preset application functions provided by the application program to obtain the target application function corresponding to the old user account information comprises:
and inputting the target application function, the first using time length and the first using total time length into a function identification model corresponding to the application program to screen preset application functions provided by the application program, and obtaining at least one target application function corresponding to the old user account information.
5. The method of claim 2, further comprising:
if the user account information is new user account information, displaying an application function page, wherein the application function page comprises a preset application label corresponding to the preset application function;
responding to the selection operation aiming at least one preset application label, and determining a target application label;
and determining a target application function corresponding to the target application label from a preset application terminal provided by the application program.
6. The method according to claim 3 or 4, wherein the functional recognition model is generated by:
acquiring application use data generated in the running process of the application program, wherein the application use data at least comprises the preset application functions, second use duration of each preset application function and total second use duration of the application program used by different account information;
and performing model training according to the preset application functions, the second use duration of each preset application function and the second total use duration to generate a function recognition model corresponding to the application program.
7. The method of claim 6, wherein the obtaining application usage data generated during the running of the application program comprises:
if the fact that the version of the application program is updated is detected, determining a current version of the application program and a historical version corresponding to the current version, wherein the historical version is a previous version of the current version;
acquiring first updating time of the historical version and second updating time of the current version;
obtaining application usage data of the application program between the first update time and the second update time.
8. An apparatus for preloading application resources, comprising:
the information acquisition module is used for responding to the starting operation of the application program and acquiring application function use information generated in the process of using the application program by a user in history;
the application function prediction module is used for determining a target application function which is inclined to be used by a user from preset application functions provided by the application program according to the application function use information;
and the application resource loading module is used for preloading the application resources corresponding to the target application functions.
9. An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;
the memory is used for storing a computer program;
the processor, when executing a program stored on the memory, implementing the method of any of claims 1-7.
10. A computer-readable storage medium having stored thereon instructions, which when executed by one or more processors, cause the processors to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210334225.5A CN114860331A (en) | 2022-03-31 | 2022-03-31 | Application resource preloading method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210334225.5A CN114860331A (en) | 2022-03-31 | 2022-03-31 | Application resource preloading method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114860331A true CN114860331A (en) | 2022-08-05 |
Family
ID=82629995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210334225.5A Pending CN114860331A (en) | 2022-03-31 | 2022-03-31 | Application resource preloading method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114860331A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666497A (en) * | 2020-06-16 | 2020-09-15 | 腾讯科技（上海）有限公司 | Application program loading method and device, electronic equipment and readable storage medium |
| CN113051005A (en) * | 2021-03-30 | 2021-06-29 | 联想(北京)有限公司 | Loading method and device |
-
2022
- 2022-03-31 CN CN202210334225.5A patent/CN114860331A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666497A (en) * | 2020-06-16 | 2020-09-15 | 腾讯科技（上海）有限公司 | Application program loading method and device, electronic equipment and readable storage medium |
| CN113051005A (en) * | 2021-03-30 | 2021-06-29 | 联想(北京)有限公司 | Loading method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108319723B (en) | Picture sharing method and device, terminal and storage medium | |
| CN111144937B (en) | Advertisement material determining method, device, equipment and storage medium | |
| US9622016B2 (en) | Invisiblemask: a tangible mechanism to enhance mobile device smartness | |
| US20150006442A1 (en) | Facilitating machine learning in an online social network | |
| CN110782043B (en) | Model optimization method, device, storage medium and server | |
| CN113392237A (en) | Classified label display method, server and display equipment | |
| CN114896454B (en) | Short video data recommendation method and system based on label analysis | |
| CN110597965B (en) | Emotion polarity analysis method and device for article, electronic equipment and storage medium | |
| CN107678800A (en) | Background application method for cleaning, device, storage medium and electronic equipment | |
| CN105335498A (en) | Method and system for information recommendation based on voice information | |
| US10062101B2 (en) | Maximizing the propensity of content consumption according to content complexity and content consumption time | |
| CN117235586B (en) | Hotel customer portrait construction method, system, electronic equipment and storage medium | |
| CN116383521B (en) | Subject word mining method and device, computer equipment and storage medium | |
| CN111680218B (en) | User interest identification method and device, electronic equipment and storage medium | |
| CN108268507A (en) | A kind of processing method based on browser, device and electronic equipment | |
| CN110555135B (en) | Content recommendation method, content recommendation device and electronic equipment | |
| CN111309706A (en) | Model training method and device, readable storage medium and electronic equipment | |
| CN107741867B (en) | Application program management method and device, storage medium and electronic equipment | |
| CN114860331A (en) | Application resource preloading method and device, electronic equipment and storage medium | |
| CN112912832A (en) | Application pushing method and device, mobile terminal and storage medium | |
| CN114661950A (en) | Video recommendation method and device | |
| CN111353052B (en) | Multimedia object recommendation method and device, electronic equipment and storage medium | |
| CN106817383B (en) | Access cycle management method and device based on data statistics reporting | |
| WO2018137170A1 (en) | User information recording method and apparatus, and electronic device | |
| CN114840785A (en) | Data processing method and device, electronic 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 |