CN110020310A - Method, apparatus, terminal and the storage medium of resource load - Google Patents
Method, apparatus, terminal and the storage medium of resource load Download PDFInfo
- Publication number
- CN110020310A CN110020310A CN201711268145.XA CN201711268145A CN110020310A CN 110020310 A CN110020310 A CN 110020310A CN 201711268145 A CN201711268145 A CN 201711268145A CN 110020310 A CN110020310 A CN 110020310A
- Authority
- CN
- China
- Prior art keywords
- url
- address
- web page
- status data
- page resources
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9566—URL specific, e.g. using aliases, detecting broken or misspelled links
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
Abstract
This application discloses a kind of resource loading method, device, terminal and storage mediums, belong to Internet technical field.This method comprises: obtaining status data；By the status data input prediction model, the prediction address URL is obtained；The web page resources for predicting that the address URL is stored are stored to pre-set space；When receiving the resource load request of client generation, whether detection pre-set space is stored with the requested web page resources of resource load request；When pre-set space is stored with the requested web page resources of resource load request, web page resources are fed back into client.The application can solve the Network status between operating system and the address URL it is poor when, the lower problem of the loading efficiency of web page resources；Since the efficiency of web page resources that client load is locally stored is higher, and the web page resources in the address URL that user may access can be stored in advance in local by operating system, it is thus possible to improve the efficiency of client load web page resources.
Description
Technical field
The invention relates to Internet technical field, in particular to a kind of resource loading method, device, terminal and deposit
Storage media.
Background technique
Client, which has, loads net according to the uniform resource locator address (Uniform Resource Locator, URL)
The function of page resource.
Client firstly generates resource load request when needing to load web page resources, which carries
The address URL；After operating system receives the resource load request, by the communication connection between the address URL from the URL
Web page resources are loaded in address；Then, the web page resources being loaded into are fed back to client by operating system.
When Network status between operating system and the address URL is poor, operating system loads the process meeting of web page resources
Very slowly, at this point, the duration that web page resources are fed back to client by operating system is longer, lead to client load web page resources
It is delayed larger.
Summary of the invention
Resource loading method, device, terminal and storage medium provided by the embodiments of the present application can solve resource load and prolong
When larger problem.The technical solution is as follows:
In a first aspect, providing a kind of resource loading method, which comprises
Status data is obtained, the status data is used to indicate the operating status of operating system；
By the status data input prediction model, prediction uniform resource position mark URL address, the prediction model are obtained
It is to be determined according to sample status data and the address sample URL；
The web page resources that the prediction address URL is stored are stored to pre-set space；
When receiving the resource load request of client generation, detect whether the pre-set space is stored with the resource
The requested web page resources of load request；
When the pre-set space is stored with the requested web page resources of the resource load request, by the web page resources
Feed back to the client.
Second aspect, provides a kind of resource loading device, and described device includes:
Data capture unit, for obtaining status data, the status data is used to indicate the operating status of operating system；
Address prediction unit, for obtaining prediction uniform resource position mark URL for the status data input prediction model
Address, the prediction model are determined according to sample status data and the address sample URL；
Resource storage unit, the web page resources for being stored the prediction address URL are stored to pre-set space；
Resources measurement unit, for detecting the pre-set space when receiving the resource load request of client generation
Whether the resource load request requested web page resources are stored with；
Resource feedback unit, for being stored with the requested web page resources of resource load request in the pre-set space
When, the web page resources are fed back into the client.
The third aspect, provides a kind of terminal, and the terminal includes processor, the memory that is connected with the processor,
And it is stored in the program instruction on the memory, the processor realizes that first aspect provides when executing described program instruction
Resource loading method.
Fourth aspect, a kind of computer-readable medium are stored thereon with program instruction, and described program instruction is held by processor
The resource loading method that first aspect provides is realized when row.
Technical solution provided by the embodiments of the present application has the benefit that
By predicting that each client can by prediction model before the resource load request for receiving client transmission
The address URL that can be accessed in advance stores the web page resources that the address URL stores to local pre-set space；So that operation system
The web page resources being locally stored directly can be fed back to visitor in the corresponding web page resources in the client request address URL by system
Family end, without downloading the web page resources from the server that the address URL indicates, avoid operating system and the address URL it
Between Network status it is poor when, the lower problem of the loading efficiency of web page resources；Since client loads the webpage being locally stored
The efficiency of resource is higher, it is thus possible to improve the efficiency of client load web page resources.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the structural schematic diagram for the resource loading system that the application one embodiment provides；
Fig. 2 is the flow chart for the resource loading method that one exemplary embodiment of the application provides；
Fig. 3 is the schematic diagram for the sample database that one exemplary embodiment of the application provides；
Fig. 4 is the schematic diagram for the prediction address URL that one exemplary embodiment of the application provides；
Fig. 5 is the schematic diagram for the prediction address URL that another exemplary embodiment of the application provides；
Fig. 6 is the schematic diagram for the resource loading procedure that one exemplary embodiment of the application provides；
Fig. 7 is the structural block diagram for the resource loading device that the application one embodiment provides；
Fig. 8 is the structural block diagram for the terminal that the application one embodiment provides.
Specific embodiment
To keep the purposes, technical schemes and advantages of the application clearer, below in conjunction with attached drawing to the application embodiment party
Formula is described in further detail.
Firstly, to this application involves several nouns be introduced.
Prediction model: being a kind of for predicting the mathematical model of the address URL according to the input data.
Prediction model is determined according to sample status data and the address sample URL.Wherein, the address sample URL, which refers to, goes through
The address URL of history access.Sample status data refers to the status data got at the access-sample address URL.
Optionally, sample status data and the address sample URL are stored in sample database.Sample database includes at least one set of sample,
Every group of sample includes collected sample status data and the address sample URL simultaneously.
Wherein, status data is used to indicate the operating status of operating system.
Optionally, status data includes but is not limited to following at least one of several:
For indicate whether access wireless network data, such as: 1 indicate operating system access wireless network, 0 indicate behaviour
Make system and does not access wireless network.It is of course also possible to indicate whether the data of access wireless network, the application by other data
This is not construed as limiting.
For indicating the data of the application program of front stage operation, such as: 1 indicates xx browser, and 2 indicate xx social applications, 3
Indicate xx shopping application etc..It is of course also possible to indicate that application program, the application are not construed as limiting this by other data.
For indicating the data of period locating for current time, such as: by 24 hours in one day every 10 minutes points
Be one section, then obtain 144 periods, wherein i indicate current time locating for the period be i-th of period, 1≤i≤
144, i be integer.It is of course also possible to divide the period otherwise, the duration between the different periods can be identical,
It can also be different, this implementation is not construed as limiting this.
For indicating whether current time belongs to the data of working time section, such as: when 1 expression current time belongs to work
Between section, 0 expression current time be not belonging to working time section.
For indicating whether current time belongs to the data of time of having a rest section, such as: 1 expression current time is when belonging to rest
Between section, 0 expression current time be not belonging to the time of having a rest section.
For indicating whether battery is in the data of charged state, such as: 1 expression battery be in charged state, and 0 indicates electric
Pond is not in charged state.
For indicating the data of the remaining capacity of battery, such as: remaining capacity, 1-100 are being indicated in the form of hundred-mark system
In any number be remaining capacity data.
Optionally, the format of status data is the format of the data of input prediction model.Such as: status data is vector
Format.
Optionally, prediction model includes but is not limited to: logistic regression (Logistic Regression, LR) model and shellfish
At least one of Ye Si (Bayesian) model.
Logic Regression Models refer on the basis of linear regression, apply the model of logical function foundation.Optionally,
In the application, Logic Regression Models are for classifying to status data and the address URL.
Schematically, Logic Regression Models are indicated by following mathematical model:
Wherein, x1、x2……xnIt is different types of status data；σ (z)=1/ (e-z)；θ1、θ2……θ2nIt is that logic is returned
Return the model parameter of model, θ0、θ1、θ2……θ2nIt can be developer's setting, alternatively, being also possible to according to sample state
What data and the training of the address sample URL obtained.
Bayesian model is a kind of using dynamic model as the time series predicting model of research object.Optionally, the application
In, Bayesian model is used to predict the probability that the address URL is accessed.
Schematically, Bayesian model is indicated by following mathematical model:
P (A)=N (A)/N
P (B)=N (B)/N
……
P (X)=N (X)/N
P (A | J)=N (A, J)/N (J)
P (B | J)=N (B, J)/N (J)
……
P (X | J)=N (X, J)/N (J)
Wherein, A, B ... X are different types of status datas.N (A) is sum, the N in sample database including status data A
(B) be in sample database including status data B sum ... N (X) be in sample database including status data X sum.N is sample
The group number of sample in library, every group of sample include collected sample status data and the address sample URL simultaneously.N (A, J) is same
Organize the total group of number that sample status data is A and sample load address is J in sample, N (B, J) is sample state in same group of sample
Total group of number ... the N (X, J) that data are B and sample load address is J is that sample status data is X and sample in same group of sample
Load address is the total group of number of J.N (J) is the number that the address URL is J in sample database.
Certainly, prediction model can also be other models, such as: deep neural network (Deep Neural Network,
DNN) model, Recognition with Recurrent Neural Network (Recurrent Neural Networks, RNN) model, insertion (embedding) model,
Gradient promotes decision tree (Gradient Boosting Decision Tree, GBDT) model etc., and the present embodiment is not another herein
One enumerates.
DNN model is a kind of deep learning frame.DNN model includes input layer, at least one layer of hidden layer (or middle layer)
And output layer.Optionally, input layer, at least one layer of hidden layer (or middle layer) and output layer include at least one neuron,
Neuron is for handling the data received.Optionally, the quantity of the neuron between different layers can be identical；Or
Person can also be different.
RNN model is a kind of neural network with feedback arrangement.In RNN model, the output of neuron can be under
One timestamp is applied directly to itself, that is, input of the i-th layer of neuron at the m moment, in addition to (i-1) layer neuron this when
It further include its own output at (m-1) moment outside the output at quarter.
Embedding model is shown based on entity and relationship distribution vector table, by the relationship in each triple example
Regard the translation from entity head to entity tail as.Wherein, triple example includes main body, relationship, object, and triple example can be with table
It is shown as (main body, relationship, object)；Main body is entity head, and object is entity tail.Such as: the father of Xiao Ming be it is big bright, then pass through three
Tuple example is expressed as (Xiao Ming, father are big bright).
GBDT model is a kind of decision Tree algorithms of iteration, which is made of more decision trees, and the result of all trees is tired
It adds up as final result.Each node of decision tree can obtain a predicted value, and by taking the age as an example, predicted value is to belong to
The average value at owner's age of age corresponding node.
Fig. 1 is the structural schematic diagram of the resource loading system shown in the exemplary embodiment of the application, the system packet
Include at least one terminal 110 and server 120.
Terminal 110 has communication function, and terminal 110 includes but is not limited to: mobile phone, tablet computer, wearable device, intelligence
At least one of energy robot, smart home device, pocket computer on knee and desktop computer.
Operating system 111 and client 112 are installed in terminal 110.
Optionally, operating system 111 includes but is not limited to: IOS (iPhone OS) system, Android (Android) system,
WindowPhone system.
Client 112 generates resource load request when needing to access web page resources, which carries webpage
The address URL of resource.Correspondingly, operating system 111 can add when receiving the resource load request according to the address URL
Corresponding web page resources are carried, then, which are fed back into client.
Optionally, in the application, operating system 111 can also obtain current when client request accesses the address URL
The status data of operating status stores the status data and the address URL to sample database.
Optionally, in the application, operating system 111 can also predict the address URL that client 112 will access, and pre-
First the web page resources that the address URL stores are stored from server 120 to pre-set space.
Optionally, terminal 110 is connected by wireless network or cable network with server 120.
Server 120 can be independent a server host；Alternatively, being also possible to multiple servers host composition
Server cluster.
Server 120 is for providing the corresponding web page resources in the address URL that client 112 requests access to.
Optionally, same server 120 is directed toward in the different addresses URL；Alternatively, different clothes are directed toward in the different addresses URL
Business device 120.
Optionally, the quantity of above-mentioned terminal 110 can be at least one, and the quantity of server 120 may be at least one
A, the present embodiment is not construed as limiting this.
Optionally, in the application, wireless network or cable network use standard communication techniques and/or agreement.Network is usual
For internet, it may also be any network, including but not limited to local area network (Local Area Network, LAN), Metropolitan Area Network (MAN)
(Metropolitan Area Network, MAN), wide area network (Wide Area Network, WAN), mobile, wired or nothing
Any combination of gauze network, dedicated network or Virtual Private Network).In some embodiments, using including hypertext markup
Language (HyperText Mark-up Language, HTML), extensible markup language (Extensible Markup
Language, XML) etc. technology and/or format represent the data by network exchange.It additionally can be used such as safe
Socket layer (Secure Socket Layer, SSL), Transport Layer Security (Trassport Layer Security, TLS), void
Quasi- dedicated network (Virtual Private Network, VPN), Internet Protocol Security (Internet Protocol
Security, IPsec) etc. conventional encryption techniques encrypt all or some links.In further embodiments, can also make
Replace or supplement above-mentioned data communication technology with customization and/or the exclusive data communication technology.
Optionally, the executing subject of each step is the operating system in terminal in the application, which can be Fig. 1
Shown in operating system 111 in resource loading system.
Fig. 2 is the flow chart of the resource loading method shown in the exemplary embodiment of the application.The resource load side
Method includes following steps.
Step 201, status data is obtained, which is used to indicate the operating status of operating system.
Optionally, operating system acquires basic data every the first preset duration, and pre-processes to the basic data
Obtain status data.First preset duration is operating system default setting；Alternatively, the first preset duration is that operating system passes through
What man-machine interactive interface received.The present embodiment does not limit the value of the first preset duration, schematically, first it is default when
A length of 1 minute.
Optionally, operating system acquires basic data when client starts in front stage operation, and to the basic data into
Row pretreatment obtains status data.
Optionally, operating system current time within a preset period of time when, acquire basic number every the second preset duration
According to, and the basic data is pre-processed to obtain status data.Preset time period is operating system default setting；Alternatively,
It is that operating system is received by man-machine interactive interface.Such as: during the sleep of user (23:00~6:00), the user
It is not usually required to access the address URL by client, at this point it is possible to set preset time for the period of 23:00~6:00
Section.Second it is default be operating system default setting；Alternatively, the first preset duration is that operating system is connect by man-machine interactive interface
It receives.Second preset duration can be identical as the first preset duration；Alternatively, the second preset duration can also with first it is default when
It is long different.The present embodiment does not limit the value of the second preset duration, and schematically, the second preset duration is 1 minute.
Optionally, basic data pre-process and refer to the number that the format of basic data is converted to input prediction model
According to format.
Optionally, basic data be operating system be directly obtained from currently running component, untreated number
According to.
Optionally, basic data includes but is not limited to following several: the program of the application program of operating system front stage operation
Mark, current time, battery charging circuit whether start, the remaining capacity of battery and operating system access network type
At least one of.
Wherein, program identification can be the icon information of the title of application program, the packet name of application program, application program
Deng the present embodiment is not construed as limiting this.
Optionally, when basic data includes the program identification of the application program of front stage operation, program identification is carried out pre-
Processing includes: to convert first state number for program identification according to the corresponding relationship between program identification and first state data
According to.First state data refer to the status data obtained after program identification conversion, and first state data indicate front stage operation
The data of application program.Such as: program identification is xx browser, and the first state data after conversion are 1；Program identification is xx society
Application is handed over, the first state data after conversion are 2；Program identification is xx shopping application, and the first state data after conversion are 3.
Optionally, when basic data includes current time, pretreatment is carried out to current time and comprises determining that current time
Which period belonged to, the second status data is converted for current time according to definitive result.Second status data, which refers to, works as
The status data obtained after preceding time conversion, the second status data is the data for indicating the period locating for current time.Such as:
24 hours in one day were divided into one section every 10 minutes, then obtain 144 periods, wherein i is indicated locating for current time
Period is i-th of period, and 1≤i≤144, i are integer.If current time is 10:09, the affiliated period is the 60th
A period, the second status data are 60.
Optionally, when basic data includes current time, current time is pre-processed further include: when detecting current
Between whether belong to working time section, convert third state data for current time according to testing result.Third state data are
Refer to the status data obtained after current time conversion, third state data indicate whether current time belongs to working time section
Data.Working time section is operating system default setting；Alternatively, working time section is that operating system passes through man-machine interactive interface
It receives.Such as: working time section is the 9:00-12:00 and 13:00-18:00 of Mon-Fri, and current time is week
Four 10:29, then current time belongs to working time section, and third state data are 1；If current time is the 10:29 of Saturday,
Current time is not belonging to working time section, and third state data are 0.
Optionally, when basic data includes current time, current time is pre-processed further include: when detecting current
Between whether belong to the time of having a rest section, convert the 4th status data for current time according to testing result.4th status data is
Refer to that the status data obtained after current time conversion, the 4th status data indicate whether current time belongs to time of having a rest section
Data.Time of having a rest section is operating system default setting；Alternatively, time of having a rest section is that operating system passes through man-machine interactive interface
It receives.Such as: time of having a rest section is 00:00-9:00,12:00-13:00, the 18:00-00:00, Saturday of Mon-Fri
And Sunday, and current time is the 10:29 of Thursday, then current time is not belonging to time of having a rest section, and the 4th status data is 0；If
Current time is the 10:29 of Saturday, then current time belongs to time of having a rest section, and the 4th status data is 1.
Optionally, when whether the charging circuit that basic data includes battery starts, whether the charging circuit of battery is opened
If dynamic carry out the charging circuit starting that pretreatment includes: battery, it is determined that battery is in charged state, by charged state with the 5th
Status data quantization means；If the charging circuit of battery is inactive, it is determined that battery is in uncharged state, by uncharged state
With the 5th status data quantization means.5th status data is to indicate whether battery is in the data of charged state.Such as: battery
In charged state, then the 5th status data is 1；Battery is in uncharged state, then the 5th status data is 0.
Optionally, when basic data includes the remaining capacity of battery, to remaining capacity carry out pretreatment include: will be remaining
Electricity obtains the 6th status data with hundred-mark system fraction representation.6th status data is the data for indicating battery dump energy.Than
Such as: when the remaining half electricity of battery, the 6th status data is 50.
Optionally, when basic data includes the type of the network of operating system access, to the network of operating system access
Type carry out pretreatment include: by operating system access network type with the 7th status data quantization means.7th shape
State data are to indicate whether operating system accesses the data of wireless network.Such as: the type of the network of operating system access is nothing
Gauze network, then the 7th status data is 1；The type of the network of operating system access is data network, then the 7th status data is
0。
Step 202, by status data input prediction model, the prediction address URL is obtained.
Prediction model is determined according to sample status data and the address sample URL.
Optionally, sample database has been locally stored in operating system, which includes at least one set of sample, and every group of sample includes
Collected sample status data and the address sample URL simultaneously.
Schematically, with reference to sample database shown in Fig. 3, in the sample database, belong to the sample status data and sample of same a line
The address this URL is one group of sample.
With reference to Fig. 4, by taking prediction model is Logic Regression Models as an example, if status data includes indicating belonging to current time
The data x of period1, indicate whether current time belongs to the data x of working time section2, indicate battery whether belong to charged state
Data x3, indicate whether access wireless network data x4With the data x for the application program for indicating front stage operation5；Then by x1、
x2、x3、x4And x5Input logic regression model obtains the prediction address URL after Logic Regression Models are handled.
Optionally, the quantity of the prediction address URL of each Logic Regression Models output is 1, and prediction model may include
Multiple Logic Regression Models, to obtain multiple addresses prediction URL.
With reference to Fig. 5, by taking prediction model is Bayesian model as an example, if status data includes when indicating belonging to current time
Between section data x1, indicate whether current time belongs to the data x of working time section2, indicate battery whether belong to charged state
Data x3, indicate whether access wireless network data x4With the data x for the application program for indicating front stage operation5；Then by x1、x2、
x3、x4And x5Bayesian model is inputted, after Bayesian model is handled, obtains the prediction address URL.
Optionally, the accessed probability in the address each sample URL, pattra leaves in the available sample database of each Bayesian model
The prediction address URL that this model obtains can be sample URL address of the probability ranking at first n.The present embodiment is not to the quantity of n
It limits, schematically, n can be 10,8 etc..
Step 203, the web page resources for predicting that the address URL is stored are stored to pre-set space.
Optionally, the web page resources that the prediction address URL is stored are stored in the form of a file to pre-set space.That is, operation
One file is set in system, and this document is used to record the storage address of web page resources.Optionally, record has prediction in this document
Corresponding relationship between the address URL and the storage address of web page resources.
Optionally, pre-set space is the space of file instruction, which is spatial cache.
Step 204, when receiving the resource load request of client generation, whether detection pre-set space is stored with resource
The requested web page resources of load request.
Optionally, client generates resource load when receiving the address URL of user's input by man-machine interactive interface
Request, operating system receive the resource load request；Alternatively, client is received to URL by man-machine interactive interface
Resource load request is generated when the trigger action of location, operating system receives the resource load request.
Optionally, client is the application program of front stage operation.
Optionally, the URL connection component in operating system call operation system；Default sky is detected by URL connection component
Between whether include the requested web page resources of resource load request.
Wherein, URL connection component has the function that communication connection is established with the address URL entrained by resource load request.
Optionally, URL connection component is the object that operating system is pre-created, for indicating logical between application program and the address URL
Letter connection, schematically, the URL connection component are the URL Connection object in operating system.
In the present embodiment, by improving to the URL connection component created, ask that it with resource load in addition to having
It asks the entrained address URL to establish except the function of communication connection, also has whether detection pre-set space is stored with resource load
The function of requesting requested web page resources additionally creates new component without operating system, saves the resource of operating system.
Optionally, when detecting that pre-set space is stored with the requested web page resources of resource load request, step is executed
205；When detecting that pre-set space is not stored there are the requested web page resources of resource load request, built by URL connection component
The web page resources that the address URL stores are fed back to client by the vertical communication connection between the address URL.
Step 205, when pre-set space is stored with the requested web page resources of resource load request, web page resources are fed back
To client.
Optionally, which is transferred to the corresponding process of client from URL connection component by operating system.
Schematically, with reference to resource loading procedure shown in fig. 6, client generates resource load request, resource load
Request carries the address URL.After operating system receives the resource load request, the default sky of URL connection component detection is called
Between whether be stored with the corresponding web page resources in the address URL；When being stored with the web page resources, which is fed back into visitor
Family end.Wherein, the corresponding webpage in the address prediction URL that operating system is obtained by prediction model is stored in pre-set space to provide
Source.
In conclusion resource loading method provided in this embodiment, by being loaded in the resource for receiving client transmission
Before request, the address URL that each client may access is predicted by prediction model, the net in advance storing the address URL
Page resource is stored to local pre-set space；So that operating system is in the corresponding web page resources in the client request address URL,
The web page resources being locally stored directly can be fed back into client, it should without the downloading from the server that the address URL indicates
Web page resources, avoid Network status between operating system and the address URL it is poor when, the loading efficiency of web page resources is lower
The problem of；Since the efficiency that client loads the web page resources being locally stored is higher, it is thus possible to improve client loads webpage
The efficiency of resource.
In addition, when being based on the user's history access address URL due to Logic Regression Models or Bayesian model, operation system
What the rule of the status data of system was established, it is therefore, current according to operating system by Logic Regression Models or Bayesian model
Status data come to predict the address URL that each client may access, the obtained address prediction URL be that user needs to access
The probability of the address URL is larger, it is thus possible to improve the accuracy of the operating system prediction address URL.
In addition, detecting whether pre-set space includes resource by using the URL connection component created in operating system
The requested web page resources of load request, so that operating system is saved without creating new component additionally to detect web page resources
Resource consumed by operating system.
Optionally, in the present embodiment, the executing subject of each step can be the URL connection component in operating system；
Or, or other components of the creation in operating system, the present embodiment are not construed as limiting this.
Optionally, after step 203, that is, operating system stores the web page resources for predicting that the address URL is stored to pre-
If after space, can also be parsed to obtain the association address URL to web page resources, the association address URL refers to the prediction address URL
The other addresses URL linked；Other web page resources that the address URL is stored will be associated with to store to pre-set space.
Such as: the web page resources of the prediction address URL storage are news web page resource, which includes at least one
The address association URL of news, and the web page resources of the address association URL storage may be the practical webpage money that think access of user
Source, therefore, operating system can also store the web page resources that the address association URL stores to pre-set space.
Optionally, the corresponding web page resources in the association address URL are stored in the form of a file to pre-set space.
It may include the association address URL in some web page resources, the purpose that user accesses the web page resources is usually to visit
Ask the address the association URL storage web page resources, therefore, the present embodiment pass through by association the address URL web page resources store to
The efficiency of the web page resources of the client load association address URL can be improved in pre-set space.
Optionally, in the application, pre-set space only saves the net for the prediction address URL that prediction model the last time predicts
Page resource；Alternatively, pre-set space only saves the web page resources and the net for the prediction address URL that prediction model the last time predicts
The web page resources of the association address URL in page resource.Since the address prediction URL that the last time predicts is according to operating system
What nearest status data was determined, therefore, the accuracy of the address prediction URL is higher.In this way, operating system both can be improved
The web page resources of storage are the probability for the web page resources that user it is expected access, but also can save storage resource.
Optionally, in the web page resources of the prediction address URL, and/or, the web page resources of the association address URL occupy default
When space is greater than capacity-threshold, operating system will store web page resources of the duration greater than preset duration and delete, this way it is possible to avoid
The storage resource that pre-set space occupies is larger, influences the problem of other application program operates normally.
Optionally, when prediction model is Logic Regression Models, operating system adds in the resource for receiving client generation
After carrying request, the logic can also be updated according to the address URL that the resource load request carries and the status data got
Regression model.
Optionally, which can be gets when receiving the resource load request of client generation；Or
Person, the status data are also possible to before the resource load request for receiving client generation, what the last time got.
Operating system update Logic Regression Models, comprising: using status data as sample status data, resource load is asked
It asks the address URL of middle carrying as the address sample URL, prediction model is trained, the prediction model after being trained.
Prediction model after training is used to predict the corresponding address prediction URL according to the subsequent status data got.
Wherein, operating system is trained prediction model according to sample status data and the address sample URL, including following
Several steps:
1, by least one set of sample status data input prediction model, training result is obtained.
The associated description of this step calculating process shown in Figure 4, therefore not to repeat here for the present embodiment.
2, loss function value is determined according to training result and every group of address sample status data corresponding sample URL.
Schematically, loss function is indicated by following data models:
Cost(hθ(x(i)),y(i))=- y(i)loghθ(x(i))-(1-y(i))log(1-hθ(x(i))
Wherein, N is the group number of sample in sample database, and i is i-th group of sample.hθ(x)(i)It is Logic Regression Models according to i-th
The training result that group sample status data obtains, y(i)For the address i-th group of sample status data corresponding i-th group of sample URL.
3, the model parameter in Logic Regression Models is updated according to loss function value by gradient descent algorithm, is updated
Model parameter afterwards.
Schematically, gradient descent algorithm is indicated by following mathematical models:
Wherein, J (θ) is loss function value, θjFor the weight of jth kind status data, xj iFor in i-th group of sample status data
Jth kind status data.
Schematically, the process of the model parameter in Logic Regression Models is updated according to the mathematical model of gradient descent algorithm
It is indicated by following formula:
……
Wherein, α is Learning Step, and α is constant, and the value of α can be operating system default setting；Alternatively, being also possible to use
Family setting.The present embodiment does not limit the value of α, schematically, α 0.5.
Optionally, { θ0、θ1、θ2……θ2nInitial value can be default setting in operating system.
4, whether the difference between model parameter before detecting updated model parameter and updating is less than preset threshold；?
When the difference is less than preset threshold, training terminates, the Logic Regression Models after being trained；It is greater than or equal in difference breath pre-
If when threshold value, continuing to train Logic Regression Models since step 1.
In the present embodiment, by prediction model be Logic Regression Models when, according to the address URL in resource load request
Logic Regression Models are trained in real time with status data；So that the Logic Regression Models can adapt to user with accessing URL
The habit of location improves the accuracy that the address URL is predicted by Logic Regression Models.
Optionally, when prediction model is Bayesian model, operating system is in the resource load for receiving client generation
After request, the address URL which carries can also be stored with the status data got to sample database, be obtained
It is updated according to this when needing to predict the address URL according to the status data got next time to updated sample database
Sample database establishes Bayesian model.That is, operating system will be taken using status data as sample status data in resource load request
Updated prediction model is established as the address sample URL in the address URL of band, and updated prediction model is used for according to next
The secondary status data got predicts the corresponding address prediction URL.
In the present embodiment, by establishing Bayesian model according to updated sample database, enable the Bayesian model
The habit that user accesses the address URL is adapted to, the accuracy for predicting the address URL by Bayesian model is improved.
Optionally, in the application, the address sample URL in sample database is the address URL for accessing duration and being greater than preset duration；
And/or the address sample URL is the address URL that access times are greater than preset times.
Optionally, preset duration is default setting in operating system；Alternatively, preset duration is to pass through man-machine interactive interface
It receives.The present embodiment does not limit the value of preset duration, and schematically, preset duration is 2 minutes.
Optionally, preset times are default setting in operating system；Alternatively, preset times are to pass through man-machine interactive interface
It receives.The present embodiment does not limit the value of preset times, and schematically, preset times are 10 times.
For the URL address less for access duration and/or access times, user it is expected to access the address URL
Probability it is lower, therefore, in the present embodiment, by will access duration greater than preset duration the address URL as sample URL
Location；And/or access times are greater than the addresses URL of preset times as the address sample URL, so that prediction model is from the sample
The prediction address URL determined in the address URL is that user it is expected that the address the URL probability of access is larger, and it is defeated to improve prediction model
The accuracy of the prediction address URL out.
Following is the application Installation practice, can be used for executing the application embodiment of the method.It is real for the application device
Undisclosed details in example is applied, the application embodiment of the method is please referred to.
Referring to FIG. 7, the structural block diagram of the resource loading device provided it illustrates the application one embodiment, the money
Source loading device being implemented in combination with as some or all of of resource loading equipemtn by software, hardware or both.It should
Device may include: data capture unit 710, address prediction unit 720, resource storage unit 730, resources measurement unit 740
With resource feedback unit 750.
Data capture unit 710, for obtaining status data, the status data is used to indicate the operation shape of operating system
State；
Address prediction unit 720, for obtaining prediction uniform resource locator for the status data input prediction model
The address URL, the prediction model are determined according to sample status data and the address sample URL；
Resource storage unit 730, the web page resources for being stored the prediction address URL are stored to pre-set space；
Resources measurement unit 740, for detecting the default sky when receiving the resource load request of client generation
Between whether be stored with the requested web page resources of resource load request；
Resource feedback unit 750, for being stored with the requested webpage of resource load request in the pre-set space
When resource, the web page resources are fed back into the client.
Optionally, the status data includes at least one of following several data:
For indicating whether the data of access wireless network；
For indicating the data of the application program of front stage operation；
For indicating the data of period locating for current time；
For indicating whether current time belongs to the data of working time section；
For indicating whether current time belongs to the data of time of having a rest section；
For indicating whether battery is in the data of charged state；
For indicating the data of the remaining capacity of battery.
Optionally, described device further include: resolution unit.
Resolution unit, the web page resources for being stored the prediction address URL are cached to default file, to institute
It states web page resources to be parsed to obtain the association address URL, the association address URL refers to what the prediction address URL was linked
Other addresses URL；
Resource storage unit is also used to cache other web page resources that the association address URL is stored to described pre-
If space.
Optionally, resources measurement unit 740, is used for:
The URL connection component in the operating system is called, the URL connection component has and the resource load request
The function of communication connection is established in the entrained address URL；
Detect whether the pre-set space includes the requested net of resource load request by the URL connection component
Page resource.
Optionally, the prediction model is Logic Regression Models, and the Logic Regression Models are used for status data and URL
Classify address；Described device further include: model training unit.
Model training unit, for using the status data as the sample status data, resource load to be asked
It asks the address URL of middle carrying as the address the sample URL, the prediction model is trained, the prediction after being trained
Model；Prediction model after the training is used to predict the corresponding address prediction URL according to the subsequent status data got.
Optionally, the prediction model is Bayesian model；The Ye Beisi model is used to predict what the address URL was accessed
Probability；Described device further include: model foundation unit.
Model foundation unit, for using the status data as the sample status data, resource load to be asked
It asks the address URL of middle carrying as the address the sample URL, establishes updated prediction model, the updated prediction mould
Type is used to predict the corresponding address prediction URL according to the status data got next time.
Optionally, the address the sample URL is the address URL for accessing duration and being greater than preset duration；And/or the sample
The address URL is the address URL that access times are greater than preset times.
The application also provides a kind of computer-readable medium, is stored thereon with program instruction, and program instruction is held by processor
The resource loading method that above-mentioned each embodiment of the method provides is realized when row.
Present invention also provides a kind of computer program products comprising instruction, when run on a computer, so that
Computer executes the resource loading method that above-mentioned each embodiment of the method provides.
With reference to Fig. 8, it illustrates the structural block diagrams for the terminal that one exemplary embodiment of the application provides.In the application
Terminal may include one or more such as lower component: processor 810 and memory 820.
Processor 810 may include one or more processing core.Processor 810 utilizes various interfaces and connection
Various pieces in entire terminal, by running or executing the instruction being stored in memory 820, program, code set or instruction
Collection, and the data being stored in memory 820 are called, execute the various functions and processing data of terminal.Optionally, processor
810 can use Digital Signal Processing (Digital Signal Processing, DSP), field programmable gate array
(Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic
Array, PLA) at least one of example, in hardware realize.Processor 810 can integrating central processor (Central
Processing Unit, CPU) and one or more of modem etc. combination.Wherein, the main processing operation system of CPU
System and application program etc.；Modem is for handling wireless communication.It is understood that above-mentioned modem can not also
It is integrated into processor 810, is realized separately through chip piece.
Optionally, above-mentioned each embodiment of the method mentions under realizing when processor 810 executes the program instruction in memory 820
The resource loading method of confession.
Memory 820 may include random access memory (Random Access Memory, RAM), also may include read-only
Memory (Read-Only Memory).Optionally, which includes non-transient computer-readable medium (non-
transitory computer-readable storage medium).Memory 820 can be used for store instruction, program, generation
Code, code set or instruction set.Memory 820 may include storing program area and storage data area, wherein storing program area can store
Instruction for realizing operating system, the instruction at least one function, for realizing the finger of above-mentioned each embodiment of the method
Enable etc.；Storage data area, which can be stored, uses created data etc. according to terminal.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely the preferred embodiments of the application, not to limit the application, it is all in spirit herein and
Within principle, any modification, equivalent replacement, improvement and so on be should be included within the scope of protection of this application.
Claims (10)
1. a kind of resource loading method, which is characterized in that the described method includes:
Status data is obtained, the status data is used to indicate the operating status of operating system；
By the status data input prediction model, prediction uniform resource position mark URL address is obtained, the prediction model is root
It is determined according to sample status data and the address sample URL；
The web page resources that the prediction address URL is stored are stored to pre-set space；
When receiving the resource load request of client generation, detect whether the pre-set space is stored with the resource load
Request requested web page resources；
When the pre-set space is stored with the requested web page resources of the resource load request, the web page resources are fed back
To the client.
2. the method according to claim 1, wherein the status data include in following several data at least
It is a kind of:
For indicating whether the data of access wireless network；
For indicating the data of the application program of front stage operation；
For indicating the data of period locating for current time；
For indicating whether current time belongs to the data of working time section；
For indicating whether current time belongs to the data of time of having a rest section；
For indicating whether battery is in the data of charged state；
For indicating the data of the remaining capacity of battery.
3. the method according to claim 1, wherein the webpage that the prediction address URL is stored provides
After source cache to default file, further includes:
The web page resources are parsed to obtain the association address URL, the address association URL refers to the address prediction URL
The other addresses URL linked；
Other web page resources that the association address URL is stored are cached to the pre-set space.
4. method according to any one of claims 1 to 3, which is characterized in that whether the detection pre-set space stores
There are the requested web page resources of resource load request, comprising:
The URL connection component in the operating system is called, the URL connection component has to be taken with the resource load request
The function of communication connection is established in the address URL of band；
Detect whether the pre-set space includes the requested webpage money of the resource load request by the URL connection component
Source.
5. method according to any one of claims 1 to 3, which is characterized in that the prediction model is Logic Regression Models, institute
Logic Regression Models are stated for classifying to status data and the address URL；The method also includes:
Using the status data as the sample status data, using the address URL carried in the resource load request as
The address the sample URL, is trained the prediction model, the prediction model after being trained；Prediction after the training
Model is used to predict the corresponding address prediction URL according to the subsequent status data got.
6. method according to any one of claims 1 to 3, which is characterized in that the prediction model is Bayesian model；It is described
Leaf bass model is used to predict the probability that the address URL is accessed；The method also includes:
Using the status data as the sample status data, using the address URL carried in the resource load request as
The address the sample URL, establishes updated prediction model, and the updated prediction model is used for basis and gets next time
Status data predict the corresponding address prediction URL.
7. method according to any one of claims 1 to 3, which is characterized in that the address the sample URL is that access duration is greater than
The address URL of preset duration；And/or the address the sample URL is the address URL that access times are greater than preset times.
8. a kind of resource loading device, which is characterized in that described device includes:
Data capture unit, for obtaining status data, the status data is used to indicate the operating status of operating system；
Address prediction unit, for by the status data input prediction model, obtaining with predicting uniform resource position mark URL
Location, the prediction model are determined according to sample status data and the address sample URL；
Resource storage unit, the web page resources for being stored the prediction address URL are stored to pre-set space；
Resources measurement unit, for whether detecting the pre-set space when receiving the resource load request of client generation
It is stored with the requested web page resources of resource load request；
Resource feedback unit, for when the pre-set space is stored with the requested web page resources of the resource load request,
The web page resources are fed back into the client.
9. a kind of terminal, which is characterized in that the terminal includes processor, the memory that is connected with the processor, Yi Jicun
The program instruction on the memory is stored up, the processor is realized when executing described program instruction as claim 1 to 7 is any
The resource loading method.
10. a kind of computer readable storage medium, which is characterized in that be stored thereon with program instruction, described program instruction is located
Manage the resource loading method realized as described in claim 1 to 7 is any when device executes.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711268145.XA CN110020310A (en) | 2017-12-05 | 2017-12-05 | Method, apparatus, terminal and the storage medium of resource load |
| PCT/CN2018/116248 WO2019109798A1 (en) | 2017-12-05 | 2018-11-19 | Method, device, terminal and storage medium for loading resource |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711268145.XA CN110020310A (en) | 2017-12-05 | 2017-12-05 | Method, apparatus, terminal and the storage medium of resource load |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110020310A true CN110020310A (en) | 2019-07-16 |
Family
ID=66750773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711268145.XA Pending CN110020310A (en) | 2017-12-05 | 2017-12-05 | Method, apparatus, terminal and the storage medium of resource load |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110020310A (en) |
| WO (1) | WO2019109798A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110691125A (en) * | 2019-09-24 | 2020-01-14 | 上海富数科技有限公司 | System and method for realizing browser loading control based on heuristic algorithm |
| 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 |
| WO2021104132A1 (en) * | 2019-11-29 | 2021-06-03 | 华为技术有限公司 | Cloud virtual machine-based data access method and device |
| CN115827947A (en) * | 2023-02-03 | 2023-03-21 | 北京匠数科技有限公司 | Method and device for collecting paging website data and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6925485B1 (en) * | 2002-05-24 | 2005-08-02 | Sun Microsystems, Inc. | Proxy cache preloader |
| CN103139278A (en) * | 2011-12-05 | 2013-06-05 | 北京网康科技有限公司 | Network resource pre-fetching and cache accelerating method and device thereof |
| CN103729438A (en) * | 2013-12-30 | 2014-04-16 | 优视科技有限公司 | Webpage preloading method and device |
| CN103905439A (en) * | 2014-03-25 | 2014-07-02 | 重庆邮电大学 | Webpage browsing accelerating method based on home gateway |
| CN104298780A (en) * | 2014-11-05 | 2015-01-21 | 百纳（武汉）信息技术有限公司 | Method and system for pre-obtaining browser webpage information |
| CN104361067A (en) * | 2014-11-05 | 2015-02-18 | 百纳（武汉）信息技术有限公司 | Method and system for intelligent loading of browser webpage information |
| CN104536787A (en) * | 2014-12-26 | 2015-04-22 | 小米科技有限责任公司 | Resource preloading method and device |
| CN104657183A (en) * | 2015-03-09 | 2015-05-27 | 联想(北京)有限公司 | Information processing method, information processing device and electronic equipment |
| CN104794004A (en) * | 2015-03-17 | 2015-07-22 | 中国石油天然气集团公司 | Information pre-loading method |
| CN105610909A (en) * | 2015-12-21 | 2016-05-25 | 北京大学 | Mobile browser resource loading optimization method based on cloud-side cooperation |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102438045B (en) * | 2011-12-07 | 2015-07-08 | 深圳市深信服电子科技有限公司 | Method and system for pre-fetching web page, and method for accessing web page |
| CN103440276A (en) * | 2013-08-08 | 2013-12-11 | 星云融创（北京）信息技术有限公司 | Method and device for improving webpage display speed |
| CN106611032A (en) * | 2015-10-27 | 2017-05-03 | 广州市动景计算机科技有限公司 | Webpage pre-loading method and device |
-
2017
- 2017-12-05 CN CN201711268145.XA patent/CN110020310A/en active Pending
-
2018
- 2018-11-19 WO PCT/CN2018/116248 patent/WO2019109798A1/en active Application Filing
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6925485B1 (en) * | 2002-05-24 | 2005-08-02 | Sun Microsystems, Inc. | Proxy cache preloader |
| CN103139278A (en) * | 2011-12-05 | 2013-06-05 | 北京网康科技有限公司 | Network resource pre-fetching and cache accelerating method and device thereof |
| CN103729438A (en) * | 2013-12-30 | 2014-04-16 | 优视科技有限公司 | Webpage preloading method and device |
| CN103905439A (en) * | 2014-03-25 | 2014-07-02 | 重庆邮电大学 | Webpage browsing accelerating method based on home gateway |
| CN104298780A (en) * | 2014-11-05 | 2015-01-21 | 百纳（武汉）信息技术有限公司 | Method and system for pre-obtaining browser webpage information |
| CN104361067A (en) * | 2014-11-05 | 2015-02-18 | 百纳（武汉）信息技术有限公司 | Method and system for intelligent loading of browser webpage information |
| CN104536787A (en) * | 2014-12-26 | 2015-04-22 | 小米科技有限责任公司 | Resource preloading method and device |
| CN104657183A (en) * | 2015-03-09 | 2015-05-27 | 联想(北京)有限公司 | Information processing method, information processing device and electronic equipment |
| CN104794004A (en) * | 2015-03-17 | 2015-07-22 | 中国石油天然气集团公司 | Information pre-loading method |
| CN105610909A (en) * | 2015-12-21 | 2016-05-25 | 北京大学 | Mobile browser resource loading optimization method based on cloud-side cooperation |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110691125A (en) * | 2019-09-24 | 2020-01-14 | 上海富数科技有限公司 | System and method for realizing browser loading control based on heuristic algorithm |
| WO2021104132A1 (en) * | 2019-11-29 | 2021-06-03 | 华为技术有限公司 | Cloud virtual machine-based data access method and device |
| 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 |
| CN111666497B (en) * | 2020-06-16 | 2023-06-06 | 腾讯科技（上海）有限公司 | Application program loading method and device, electronic equipment and readable storage medium |
| CN115827947A (en) * | 2023-02-03 | 2023-03-21 | 北京匠数科技有限公司 | Method and device for collecting paging website data and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019109798A1 (en) | 2019-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Edge intelligence: Architectures, challenges, and applications | |
| Jauro et al. | Deep learning architectures in emerging cloud computing architectures: Recent development, challenges and next research trend | |
| TWI620075B (en) | Server and cloud computing resource optimization method thereof for cloud big data computing architecture | |
| Imteaj et al. | Federated learning for resource-constrained iot devices: Panoramas and state of the art | |
| CN106030571B (en) | Dynamically modifying elements of a user interface based on a knowledge graph | |
| CN104137094B (en) | A kind of method and system that the content for calculating equipment is fetched in advance | |
| Raju et al. | IOT based online load forecasting using machine learning algorithms | |
| CN110020310A (en) | Method, apparatus, terminal and the storage medium of resource load | |
| CN108664331A (en) | Distributed data processing method and device, electronic equipment, storage medium | |
| Qi et al. | Using the internet of things E-government platform to optimize the administrative management mode | |
| CN110855648B (en) | Early warning control method and device for network attack | |
| CN113128686A (en) | Model training method and device | |
| CN108111399A (en) | Method, apparatus, terminal and the storage medium of Message Processing | |
| Jiang et al. | Distributed deep learning optimized system over the cloud and smart phone devices | |
| WO2024067373A1 (en) | Data processing method and related apparatus | |
| US20230106106A1 (en) | Text backup method, apparatus, and device, and computer-readable storage medium | |
| CN109564569A (en) | The memory for calculating for a long time is reduced to use | |
| CN114036051A (en) | Test method, device, equipment and storage medium | |
| Grob et al. | A recurrent neural network survival model: Predicting web user return time | |
| CN116862580A (en) | Short message reaching time prediction method and device, computer equipment and storage medium | |
| Kodavali et al. | Adaptation of Blockchain using Ethereum and IPFS for Fog based E-Healthcare activity recognition system | |
| Nimishan et al. | An approach to improve the performance of web proxy cache replacement using machine learning techniques | |
| CN114329099B (en) | Overlapping community identification method, device, equipment, storage medium and program product | |
| WO2022048432A1 (en) | Method and apparatus for constructing recommendation model, method and apparatus for constructing neural network model, and electronic device and storage medium | |
| Khetarpal et al. | Power quality disturbance signal segmentation and classification based on modified BI‐LSTM with double attention mechanism |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190716 |