CN109063106A - Network address modification method, device, computer equipment and storage medium - Google Patents
Network address modification method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109063106A CN109063106A CN201810846838.0A CN201810846838A CN109063106A CN 109063106 A CN109063106 A CN 109063106A CN 201810846838 A CN201810846838 A CN 201810846838A CN 109063106 A CN109063106 A CN 109063106A
- Authority
- CN
- China
- Prior art keywords
- network address
- correction model
- amendment
- initial
- initial network
- 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.)
- Granted
Links
Landscapes
- Small-Scale Networks (AREA)
- Information Transfer Between Computers (AREA)
Abstract
This application involves a kind of network address modification method, device, computer equipment, storage medium, which includes: to obtain the initial network address of user's input first when determination need to carry out network address amendment;Later when the initial network address meets preset condition, correction model corresponding with the preset condition is selected;The initial network address is modified using the correction model.The network address modification method, device, computer equipment, storage medium are not necessarily to the manual Introduced Malaria network address of user, can be modified to initial network address.Quickly and easily user can be helped to correct the network address of input after user misses defeated network address, improve user experience.
Description
Technical field
This application involves information technology fields, more particularly to a kind of network address modification method, device, computer equipment and deposit
Storage media.
Background technique
When user inputs network address access webpage in the browser's address bar, often wrong defeated network address causes to jump to mistake
Website or the website that is not present, at this moment user needs to correct network address in address field manually to jump to the page for being intended to browsing
Face.
Current each browser fails to be supplied to a kind of mode for correcting network address of user, and user is allow to jump to mistake
Webpage after can quickly correct and jump to correct target network address, reduce the speed of user's access target website, influence to use
The usage experience at family.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of network address modification method, device, computer equipment and
Storage medium.
In a first aspect, the embodiment of the present application provides a kind of network address modification method, which comprises
Obtain the initial network address of user's input;
If the initial network address meets preset condition, correction model corresponding with the preset condition is selected;
The initial network address is modified using the correction model.
The preset condition includes: the initial network address and particular web site there are relevance in one of the embodiments,
Or there are relevances for the web page contents of the initial network address and particular web site;
Corresponding with the preset condition correction model of the selection includes:
The correction model is selected according to the relevance.
It is described to use the correction model to institute in one of the embodiments, when the relevance is that content is associated with
Initial network address is stated to be modified, comprising:
The Web address field of the initial network address is parsed, field keyword is obtained;
The field keyword is inputted into the correction model, it is corresponding that the correction model is based on the field keyword
History corrects at least one amendment network address of probability output;Alternatively,
The Web address field of the initial network address is parsed, field attribute value is obtained;
The field attribute value is inputted into the correction model, the correction model be based on the field attribute value with it is specific
The similarity of network address exports at least one amendment network address.
It is described to use the correction model to institute in one of the embodiments, when the relevance is semantic association
Initial network address is stated to be modified, comprising:
The Web address field for parsing the initial network address obtains the corresponding semanteme of the Web address field;
By the semantic input correction model, the correction model is based on the corresponding mapping relations output of the semanteme
At least one amendment network address.
In one of the embodiments, before selecting correction model corresponding with the preset condition further include:
Using the initial network address of mark, and amendment network address corresponding with initial network address, training sample is constructed;
Using each network layer of the correction model of training sample training building, the correction model is obtained.
The initial network address is modified using the correction model in one of the embodiments, comprising:
If multiple correction models selected to use, according to the amendment network address of the multiple correction model output to described first
Beginning network address is modified.
In one of the embodiments, according to the multiple correction model output amendment network address to the initial network address into
Row amendment, comprising:
Obtain the weight of each correction model in the multiple correction model;
Using the weight, the amendment network address of each correction model output of weighted calculation, and according to the weighted calculation
As a result at least one amendment network address is exported.
It is described in one of the embodiments, that the initial network address is modified using the correction model, comprising:
In the predeterminable area of user input interface, revised network address is exported, and is received according in the predeterminable area
The selection instruction to revised network address, jump to the revised network address.
It is described in one of the embodiments, that the initial network address is modified using the correction model, comprising:
When obtained revised network address is one, the revised network address is jumped to;Alternatively,
When obtained revised network address is multiple, the revised network address most by selection number is jumped to.
Second aspect, the embodiment of the present application provide a kind of network address correcting device, and described device includes:
Module is obtained, for obtaining the initial network address of user's input;
Model fitting module selects corresponding with the preset condition if meeting preset condition for the initial network address
Correction model;
Correction module, for being modified using the correction model to the initial network address.
The third aspect, the embodiment of the present application provide a kind of computer equipment, including memory and processor, the memory
On be stored with the computer program that can be run on a processor, the processor realizes the application when executing the computer program
The image processing method network address amendment that any embodiment provides.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer program,
The computer program is executed by processor the image processing method network address amendment of the application any embodiment offer.
A kind of network address modification method provided by the present application, device, computer equipment, storage medium, the network address modification method
It include: to obtain the initial network address of user's input first when determination need to carry out network address amendment;Meet later in the initial network address
When preset condition, correction model corresponding with the preset condition is selected;Using the correction model to the initial network address into
Row amendment.The network address modification method, device, computer equipment, storage medium are not necessarily to the manual Introduced Malaria network address of user
Initial network address is modified.It can quickly and easily help user to correct the network address of input after user misses defeated network address, improve
User experience.
Detailed description of the invention
Fig. 1 is the applied environment figure of network address modification method in the application one embodiment;
Fig. 2 is the step flow diagram of network address modification method in the application one embodiment;
Fig. 3 is the step flow diagram being modified in another embodiment of the application to initial network address;
Fig. 4 is the supplement steps flow chart schematic diagram of network address modification method in another embodiment of the application;
Fig. 5 is the step flow diagram being modified in another embodiment of the application to initial network address;
Fig. 6 is the supplement steps flow chart schematic diagram of network address modification method in the application one embodiment;
Fig. 7 is the step flow diagram being modified in the application one embodiment to initial network address;
Fig. 8 is the supplement steps flow chart schematic diagram of network address modification method in the application one embodiment;
Fig. 9 is the step flow diagram being modified in the application one embodiment to initial network address;
Figure 10 is the structural block diagram of network address correcting device in the application one embodiment;
Figure 11 is the structural schematic diagram of computer equipment in the application one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Network address modification method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, terminal 110
Processor 120 and web page server 130 communicate to connect respectively.The terminal 110 be displayed for web page server 130 according to
The webpage that the network address of family input returns.The original network address and corresponding amendment network address letter of user's input are stored in terminal 110
Breath.The original network address and corresponding amendment website information of the user's input stored in the available terminal 110 of processor 120.
Optionally, terminal 110 can be, but not limited to be various smart phones, tablet computer, personal computer, notebook electricity
Brain.Optionally, which can be cloud server, which can be either more with independent server
The server cluster of a server composition is realized.
Optionally, the processor 120 or the processor being arranged in terminal 110.Optionally, it is arranged in terminal
Processor in 110 can be CPU (Central Processing Unit, central processing unit), GPU (Graphics
Processing Unit, graphics processor), IPU (Intelligence Processing Unit, neural network processor)
Etc..Optionally, which is multi-core processor, such as multicore GPU.
Optionally, which can run the algorithm of neural network model, to the data of input neural network model
It is handled.Optionally, the data for inputting neural network model can be initial data, such as text, picture, audio, video
Etc.;It can also be with structuring treated data.
In one embodiment, as shown in Fig. 2, a kind of network address modification method is provided, now with application environment shown in FIG. 1
For be illustrated, include the following steps:
Step S210: the initial network address of user's input is obtained.
Specifically, processor 120 obtains the initial network address of user's input.
Optionally, processor 120 obtains user after the trigger signal for receiving the current network address of amendment that terminal 110 is sent
The initial network address of input.Optionally, the mode of the trigger signal for the current network address of amendment that terminal 110 is sent can be to click currently
Address field.Optionally, the mode of the trigger signal for the current network address of amendment that terminal 110 is sent can be double-click current web page.It can
Choosing, if present terminal has the function of 3D Touch (three-dimensional touch), the trigger signal for the current network address of amendment that terminal 110 is sent
Mode can also be weight current device screen.
Optionally, processor 120 can also voluntarily judge whether the initial network address of user's input is target network address, and sentence
When the initial network address of disconnected user's input is non-targeted network address, the initial network address of user's input is voluntarily obtained.Optionally, processor can
Whether to be abnormal webpage voluntarily judges whether the initial network address of user's input is target network according to the webpage of initial website links
Location, alternatively, processor can also be according to the access frequency (whether less than a given threshold) of the webpage of initial website links voluntarily
Whether the initial network address for judging user's input is target network address.It should be understood that since whether initial network address is target network address
With very strong user's subjectivity, therefore when the threshold value of access frequency is arranged, which can not be excessive.
Step S220: if the initial network address meets preset condition, correction model corresponding with the preset condition is selected.
If selecting repair corresponding with the preset condition specifically, the initial network address of processor 120 meets preset condition
Positive model.Optionally, processor 120 is first analyzed and processed the initial network address, judges that this is first after obtaining initial network address
The preset condition that beginning network address meets.Optionally, the corresponding relationship of preset condition and correction model need to be preset.Optionally, may be used
A correction model can be corresponded to so that each preset condition is arranged, the corresponding amendment mould of multiple preset conditions also can be set
Type.Optionally, the preset condition can for the initial network address and particular web site there are relevance or the initial network address with
There are relevances for the web page contents of particular web site.
Step S230: the initial network address is modified using the correction model.
Specifically, processor 120 is modified the initial network address using the correction model.Optionally, processor
The related algorithm of 120 operation correction models, handles initial network address, exports at least one amendment network address, uses amendment net
Location is modified initial network address.Optionally, the network address that processor 120 can export correction model is defeated by the user of terminal
Enter interface to be shown, to carry out human-computer interaction.
When carrying out the amendment of initial network address by human-computer interaction, user can be by user input interface selection interface
Amendment network address initial network address is modified.User can correspond to triggering after user input interface selects amendment network address to select
It selects signal and is sent to processor 120, processor 120 receives the selection signal, and the amendment network address selected using user is to initial
Network address is modified.Specifically, processor 120, replaces initial network address using the amendment network address that user selects.Optionally, if repairing
The number of the amendment network address of positive model output is one, and processor 120 also can be used candidate's network address and directly replace current net
Location is modified current network address.
The network address modification method that above-described embodiment proposes, when determination need to carry out network address amendment, acquisition user input first
Initial network address;Later when the initial network address meets preset condition, correction model corresponding with the preset condition is selected;
The initial network address is modified using the correction model.The network address modification method is not necessarily to the manual Introduced Malaria net of user
Location can be modified initial network address.User can be quickly and easily helped to correct the net of input after user misses defeated network address
Location improves user experience.
As an alternative embodiment, corresponding with the preset condition correction model of the selection includes: basis
The relevance selects the correction model.
Specifically, processor 120 is according to initial network address and particular web site, there are relevances to select the correction model, or
Person, there are relevances according to the web page contents of initial network address and particular web site for processor 120.Optionally, initial network address with it is specific
Relevance existing for network address can be content relevance or semantic relevance.
The present embodiment selects amendment network address according to the relevance of initial network address and particular web site, and more conducively correction model is based on
The potential association of initial network address and particular web site quickly exports amendment network address.
As an alternative embodiment, as shown in figure 3, when the relevance be content be associated with when, it is described use institute
Correction model is stated to be modified the initial network address, comprising:
Step S231a: the Web address field of the parsing initial network address obtains field keyword.
Specifically, processor 120 parses the Web address field of the initial network address, field keyword is obtained.Optionally, field
Keyword can be the domain name main body of original net location, such as: initial network address is " http://www.abx.com ", processor 120
After parsing the initial network address, the field keyword of acquisition is " abx ".
Step S232a: the field keyword is inputted into the correction model, the correction model is closed based on the field
At least one amendment network address of the corresponding history amendment probability output of keyword.
Specifically, processor 120 runs the related neural network algorithm of correction model, the field of Introduced Malaria model is closed
Keyword carries out data processing, final correction model be based on the field keyword corresponding history amendment probability output at least one
Correct network address.Optionally, processor 120 first determines whether that the preset condition that initial network address meets is that content is associated with, selection later and
Content is associated with corresponding correction model.The corresponding history of field keyword can be based on by being somebody's turn to do correction model corresponding with content association
Correct at least one amendment network address of probability output.
As an alternative embodiment, as shown in figure 4, being somebody's turn to do correction model corresponding with content association to institute using
It states before initial network address is modified, further includes:
Step S233a: it to network address amendment historical record analysis processing is obtained, obtains using in the network address amendment historical record
The initial network address and the corresponding amendment network address of the initial network address of family input.
Optionally, the initial network address in the network address amendment historical record of the available multiple users of processor 120, Yi Jiyu
The corresponding amendment network address of the initial network address.Optionally, processor 120 can also only obtain the network address amendment history note of a certain user
Initial network address in record, and amendment network address corresponding with the initial network address.
Optionally, when the network address that the amendment historical record that processor 120 obtains is multi-user corrects historical record, processing
Device 120 can obtain the web page access historical record of a certain (or certain is several) browser first, go through again to web page access later
Records of the Historian record is screened, and the network address amendment historical record of multiple users is obtained.Optionally, it is gone through in the amendment that processor 120 obtains
When history is recorded as the network address amendment historical record of a certain user, processor 120 can be first from local cache or active user
Browser account, obtain the web page access historical record of active user, web page access historical record screened again later,
Obtain the network address amendment historical record of active user.
Step S234a: the initial network address for calculating user's input in the network address amendment historical record is modified to corresponding repair
The history of positive network address corrects probability.
Optionally, when calculating history amendment probability, processor 120 can use statistical method, calculate the history and repair
Positive record.Such as: processor, which obtains in network address amendment record, includes: 200 are modified to initial network address X1 the record of Y1, and 1
Initial network address X1 is modified to the record of Y3.Calculate the probability that initial network address X1 is modified to Y1: 200/201=0.995;It calculates just
Beginning, network address X1 was modified to the probability of Y1: 1/201=0.005.
Step S235a: probability is corrected according to the history and is arranged between the field keyword of initial network address and amendment network address
Corresponding relationship.
Specifically, processor 120 corrects the field keyword and amendment net that initial network address is arranged in probability according to the history
Corresponding relationship between location.Optionally, processor 120 is correcting the amendment network address that probability setting correction model exports according to history
When, data cleansing (for example, the domain name main part for only using initial network address) is carried out to the initial network address of reference first, is obtained just
Field keyword is arranged later and corrects the corresponding relationship between network address for the field keyword of beginning network address.This can screen out use
The data of the types such as defeated general domain suffix or network address agreement are missed at family, and the result made is more in line with expection.
Step S236a: according to the corresponding relationship between the field keyword of initial network address and amendment network address, building and content
It is associated with corresponding correction model.
Specifically, processor 120 is according to the corresponding relationship between the field keyword and amendment network address of initial network address, building
Correction model corresponding with content association, even if correction model after input field keyword, according to field keyword and is corrected
Corresponding relationship between network address, output amendment network address.
The method that the building that the present embodiment proposes is associated with corresponding correction model with content is corrected according to multi-user's network address
Historical record, obtained correction model is applied widely, versatile.Historical record is corrected according to a certain user's network address, is obtained
The correction model arrived, it is with strong points, it is suitable for user and personalized website amendment service is provided.In practical application, can basis
Correction model is arranged using which kind of network address amendment historical record in actual demand selection, and the application is it is not limited here.
As an alternative embodiment, as shown in figure 5, when the relevance be content be associated with when, it is described use institute
Correction model is stated to be modified the initial network address, comprising:
Step S231b: the Web address field of the parsing initial network address obtains field attribute value.
Specifically, processor 120 parses the Web address field of the initial network address, field attribute value is obtained.Optionally, field
Attribute value can be number of characters or character content etc..
Step S232b: the field attribute value is inputted into the correction model, the correction model is based on the field category
Property value and particular web site similarity export at least one amendment network address.
Specifically, processor 120 runs the related neural network algorithm of correction model, to the field category of Introduced Malaria model
Property value carry out data processing, final correction model exports at least one based on the similarity of the field attribute value and particular web site
Correct network address.Optionally, processor 120 is using at least one highest particular web site of similarity as amendment network address output.It is optional
, processor 120 first determines whether that the preset condition that initial network address meets for content association, selects corresponding with content association later
Correction model.This be associated with content corresponding correction model can the similarity based on the field attribute value and particular web site it is defeated
At least one amendment network address out.
As an alternative embodiment, as shown in fig. 6, being somebody's turn to do correction model corresponding with content association to institute using
It states before initial network address is modified, further includes:
Step S233b: particular web site set is obtained.
Specifically, processor 120 obtains particular web site set.Processor can be counted based on whole network data, be screened specific
Network address.Such as: it can be set and preset threshold T1 is reached to total access times of the corresponding webpage of network address, which can be added
To particular web site set.Optionally, whether preset threshold T2 can also be reached to the daily visit of the corresponding webpage of network address, determined
Whether the network address can be added to particular web site set.Optionally, it due to differences such as regional culture or Temporal changes, is selecting
When selecting particular web site, it may be considered that increase region, time factor selects particular web site from whole network data.
Step S234b: the field attribute value of initial network address and the similarity calculation rule of particular web site are preset.
Optionally, the similarity of the field attribute value of initial network address and the field attribute value of particular web site can be calculated.It can
Choosing, calculate the text distance of the field keyword of initial network address and particular web site, calculate the field attribute value of initial network address with
The similarity of particular web site.Both optionally, it can be primarily based on the field attribute value of initial network address and particular web site, mark
Similarity constructs model training sample;Using each network layer of the model training sample training similarity calculation, obtain
Similarity calculation;The field attribute value of initial network address and the similarity of particular web site are obtained using similarity calculation.
Step S235b: the amendment network address that correction model is exported based on the field attribute value is arranged according to the similarity.
Specifically, processor 120: correction model is arranged according to the similarity and is repaired based on what the field attribute value exported
Positive network address.
The method for the amendment network address based on field attribute value output that the present embodiment proposes, since particular web site is general
Network address is often used for user, in the case of user wants to access common network address but defeated mistake, can helping user's quick obtaining, this is common
Network address.
As an alternative embodiment, as shown in fig. 7, when the relevance be semantic association when, it is described use institute
Correction model is stated to be modified the initial network address, comprising:
Step S231c: the Web address field of the parsing initial network address obtains the corresponding semanteme of the Web address field.
Specifically, processor 120 parses the Web address field of the initial network address, the corresponding language of the Web address field is obtained
Justice.Optionally, processor 120 carries out data mining to the semanteme of multiple websites and the practical network address of the website, obtains website
Semanteme and website semanteme and the mapping relations of the practical network address of website.Optionally, the semantic of website can be website
The Chinese phonetic alphabet or the English synonym of website etc. information relevant to website meaning.Such as: the Chinese name of certain website is
" certain ", the practical network address of the website are " abx.com ".The initial network address that user obtains according to the Chinese phonetic alphabet of the website
" mou.com " and practical network address " abx.com " is mismatched, the mapping relations obtained at this time are as follows: " dbx.com " is set as original net
The amendment network address of location " mou.com ".
Step S232c: by it is described it is semantic input the correction model, the correction model is based on that the semanteme is corresponding to be reflected
The relationship of penetrating exports at least one amendment network address.
Specifically, processor 120 runs the related neural network algorithm of correction model, to Introduced Malaria model it is semantic into
Row data processing obtains at least one practical network address based on the corresponding mapping relations of the semanteme, as amendment network address output.It can
Choosing, processor 120 first determines whether that the preset condition that initial network address meets is semantic association, selects later corresponding with semantic association
Correction model.Being somebody's turn to do correction model corresponding with semantic association can be based on the corresponding mapping relations output at least one of the semanteme
A amendment network address.
The method for exporting at least one amendment network address based on the corresponding mapping relations of the semanteme that the present embodiment proposes, can
So that user quickly obtains the semantic and unmatched target network address of practical network address, pass through website particularly suitable for user's conjecture formula
Name character pronunciation inputs the situation that initial network address is unable to access target website.
As an alternative embodiment, as shown in figure 8, select corresponding with preset condition correction model it
Before further include:
Step S240: using the initial network address of mark, and amendment network address corresponding with initial network address, training sample is constructed
This.
Step S250: using each network layer of the correction model of training sample training building, the amendment mould is obtained
Type.
Optionally, which can be RNN-encoder-decoder (Recognition with Recurrent Neural Network coding/decoding model) mind
Through network model or other deep learning neural network models, which be may be implemented end to end
As a result it exports, i.e., directly exports amendment network address according to initial network address.Optionally, the process of training RNN-encoder-decoder
Include:
Obtained multiple model training samples are input to RNN-encoder-decoder neural network model by step a
Neural network, the neural network include multiple network layers.Using stochastic gradient descent algorithm, each layer of loss function is calculated
Gradient value, and use the weight of obtained each layer of gradient value update respective layer.
Step b calculates each layer of neural network of error-sensitivity using back-propagation algorithm, and uses each layer
The weight of error-sensitivity update respective layer.
Step c, iteration execute the step a and step b, until the gradient value using each layer updates the weight of respective layer
It is equal with each layer of the error-sensitivity update weight of respective layer is used, obtain RNN-encoder-decoder neural network.
It is to be exported to correct according to preset goal task above by deep neural network model as correction model
Network address, therefore obtained candidate network address can be with meeting the expectation of people.
As an alternative embodiment, being modified using the correction model to the initial network address, comprising: if
Multiple correction models selected to use then carry out the initial network address according to the amendment network address of the multiple correction model output
Amendment.Specifically, processor 120: if multiple correction models selected to use, according to repairing for the multiple correction model output
Positive network address is modified the initial network address.Optionally, processor 120 is selected amendment mould each in multiple correction model
All amendment network address of type output are exported.Such as: processor 120 has selected and the associated correction model M1 of content and and language
The associated correction model M2 of justice, carries out network address amendment, and amendment network address X1, correction model the M2 output of correction model M1 output is repaired
Positive network address X2;Processor 120 will correct network address X1 and amendment network address X2 all as amendment network address output.
As an alternative embodiment, as shown in figure 9, the amendment network address pair exported according to the multiple correction model
The initial network address is modified, comprising:
Step S231d: the weight of each correction model in the multiple correction model is obtained.
Specifically, processor 120 obtains the weight of each correction model in the multiple correction model.Such as: based on multi-purpose
The correction model that the network address amendment historical record at family obtains is M3;Network address amendment history note based on active user (sole user)
Recording obtained correction model is M4;Processor 120 when to select using correction model be M3, correction model is M4 amendment network address,
The weight that pre-set correction model is M3, correction model is M4 is obtained first.
Step S232d: using the weight, the amendment network address of each correction model output of weighted calculation, and according to institute
It states weighing computation results and exports at least one amendment network address.
Specifically, the amendment network address that processor 120 is exported using the weight, each correction model of weighted calculation, and
At least one amendment network address is exported according to the weighing computation results.For example, the amendment network address X31 of correction model M3 output,
X32, corresponding probability are P1, P2;Amendment network address X31, X41 of correction model M4 output, corresponding probability are P3, P4, wherein P1=
P2=P3=P4;The weight for the correction model M3 that processor 120 obtains is Y1, and the weight of correction model M3 is Y2, wherein Y2 >
Y1.Each amendment network address is weighted in processor 120, corrects the corresponding weighing computation results of network address X31 at this time are as follows: P1*
Y1+P3*Y3;Correcting the corresponding weighing computation results of network address X32 is P2*Y1;Correct the corresponding weighing computation results of network address X41
Are as follows: P4*Y2.Last processor 120 exports amendment network address according to above-mentioned weighing computation results.If exporting an amendment network address,
Output amendment network address X31;If exporting 3 amendment network address, output amendment network address X31, X41, X32.Preferably, correction model is
When M3 (multi-user data) and correction model are M4 (sole user) corresponding weight, weight lays particular stress on the corresponding amendment of sole user
Model.
The output result for the multiple correction models of combination that the present embodiment proposes carries out network address amendment, can integrate more polynary
Network address corrects influence factor, can export and be more in line with network address expected from user.
As an alternative embodiment, as shown in fig. 6, it is described using the correction model to the initial network address into
Row amendment, comprising: in the predeterminable area of user input interface, export revised network address, and connect according in the predeterminable area
The selection instruction to revised network address received jumps to the revised network address.
Optionally, in the address field of user input interface in the form of drop-down menu, output amendment network address.Optionally, when
When preceding terminal is portable terminal (such as mobile phone, ipad etc.), processor can detect user's finger in the use of terminal first
The current location of family input interface exports modified address in the current location in the form of suspended frame later.Optionally, terminal
After exporting the amendment network address, user can make a choice operation for the amendment network address of output, that is, issue selection signal.Processor
120 after receiving the selection signal in predeterminable area, and it is initial that amendment network address amendment corresponding with the selection signal can be used
Network address.
The candidate network address amendment that the present embodiment proposes, provides a kind of simply and easily man-machine interaction mode, can help
User quickly corrects current network address using candidate network address.
As an alternative embodiment, described be modified the initial network address using the correction model, wrap
It includes: when obtained revised network address is one, jumping to the revised network address;Alternatively, revised when obtaining
When network address is multiple, the revised network address most by selection number is jumped to.
It is specific optional, the hop threshold of amendment network address can be preset, is jumped if amendment network address is reached by selection number
When threshold value, the amendment network address is directly jumped.
Such as: user C input is wanted to access " dbx.com ", but user C is wrong defeated for " dbc.com ", Wu Fafang by the network address
Target network address " dbx.com " is asked, presetting hop threshold is 20 times.Processor 120 can recorde user at input " dbc.com "
Afterwards, selection is revised as the number of " dbx.com ", and judges whether the selection number reaches 20 times.If reaching, one under user
After secondary input " dbc.com ", " dbx.com " replacement " dbc.com " directly is used, jumps the corresponding webpage of dbx.com.
The network address modification method of the present embodiment is directly replaced using candidate network address based on the wrong defeated habit of individual subscriber network address
Current network address reduces data operation, improves system response efficiency.
It should be understood that although each step in the flow chart of Fig. 2-Fig. 9 is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, in Fig. 2-Fig. 9 extremely
Few a part of step may include that perhaps these sub-steps of multiple stages or stage are not necessarily same to multiple sub-steps
Moment executes completion, but can execute at different times, and the execution sequence in these sub-steps or stage is also not necessarily
It successively carries out, but in turn or can be handed over at least part of the sub-step or stage of other steps or other steps
Alternately execute.
In one embodiment, as shown in Figure 10, a kind of network address correcting device is provided, described device includes:
Module 100 is obtained, for obtaining the initial network address of user's input.
Model fitting module 200 selects corresponding with the preset condition if meeting preset condition for the initial network address
Correction model.
Network address correction module 300, for being modified using the correction model to the initial network address.
As an alternative embodiment, model fitting module 200, is also used to be deposited according to initial network address with particular web site
Relevance select the correction model;Alternatively, being closed according to existing for the web page contents of the initial network address and particular web site
The connection property selection correction model.
As an alternative embodiment, network address correction module 300, is also used to when the relevance be content association
When, the Web address field of the initial network address is parsed, field keyword is obtained;The field keyword is inputted into the amendment mould
Type, the correction model are based at least one amendment network address of the corresponding history amendment probability output of the field keyword.
As an alternative embodiment, network address correction module 300, is also used to when the relevance be content association
When, the Web address field of the initial network address is parsed, field attribute value is obtained;The field attribute value is inputted into the amendment mould
Type, the correction model export at least one amendment network address based on the similarity of the field attribute value and particular web site.
As an alternative embodiment, network address correction module 300, is also used to when the relevance be semantic association
When, the Web address field of the initial network address is parsed, the corresponding semanteme of the Web address field is obtained;It will be repaired described in the semantic input
Positive model, the correction model are based on the corresponding mapping relations of the semanteme and export at least one amendment network address.
As an alternative embodiment, network address correction module 300, is also used for the training sample training building
Correction model each network layer, obtain the correction model;Wherein, the training will this by the initial network address that marks in advance,
And amendment network address building corresponding with initial network address.
As an alternative embodiment, network address correction module 300, if can be also used for multiple amendments selected to use
Model is then modified the initial network address according to the amendment network address that the multiple correction model exports.
As an alternative embodiment, network address correction module 300, is specifically used for obtaining in the multiple correction model
The weight of each correction model;Using the weight, the amendment network address of each correction model output of weighted calculation, and according to described
Weighing computation results export at least one amendment network address.
Specific about network address correcting device limits the restriction that may refer to above for network address modification method, herein not
It repeats again.Modules in above-mentioned network address correcting device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, and structure is shown
Intention can be as shown in figure 11.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store the related data of the web page access historical record of user.The network interface of the computer equipment
For being communicated with external terminal by network connection.To realize a kind of network address amendment when the computer program is executed by processor
Method.
It will be understood by those skilled in the art that structure shown in Figure 11, only part relevant to application scheme
The block diagram of structure, does not constitute the restriction for the computer equipment being applied thereon to application scheme, and specific computer is set
Standby may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is deposited on the memory
The computer program that can be run on a processor is contained, processor performs the steps of acquisition when executing the computer program
The initial network address of user's input;If the initial network address meets preset condition, amendment mould corresponding with the preset condition is selected
Type;The initial network address is modified using the correction model.
In one embodiment, it is also performed the steps of when processor executes computer program according to initial network address and spy
Determine relevance existing for network address and selects the correction model;Alternatively, according to the web page contents of the initial network address and particular web site
Existing relevance selects the correction model.
In one embodiment, it also performs the steps of when processor executes computer program when the relevance is interior
When holding association, the Web address field of the initial network address is parsed, obtains field keyword;It will be repaired described in field keyword input
Positive model, the correction model are based at least one amendment network address of the corresponding history amendment probability output of the field keyword.
In one embodiment, it also performs the steps of when processor executes computer program when the relevance is interior
When holding association, the Web address field of the initial network address is parsed, obtains field attribute value;It will be repaired described in field attribute value input
Positive model, the correction model export at least one amendment network address based on the similarity of the field attribute value and particular web site.
In one embodiment, it is also performed the steps of when processor executes computer program when the relevance is language
When justice association, the Web address field of the initial network address is parsed, the corresponding semanteme of the Web address field is obtained;By the semantic input
The correction model, the correction model are based on the corresponding mapping relations of the semanteme and export at least one amendment network address.
In one embodiment, it is also performed the steps of when processor executes computer program and uses the training sample
Each network layer of the correction model of training building, obtains the correction model;Wherein, the training is originally first by what is marked in advance
Beginning network address, and amendment network address corresponding with initial network address building.
In one embodiment, if processor execute computer program when also perform the steps of it is selected to use multiple
Correction model is then modified the initial network address according to the amendment network address that the multiple correction model exports.
In one embodiment, processor, which is also used to execute computer program and performs the steps of to obtain, the multiple repairs
The weight of each correction model in positive model;Using the weight, the amendment network address of each correction model output of weighted calculation, and
At least one amendment network address is exported according to the weighing computation results.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the network address modification method that the application any embodiment provides when being executed by processor.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (12)
1. a kind of network address modification method, which is characterized in that the described method includes:
Obtain the initial network address of user's input;
If the initial network address meets preset condition, correction model corresponding with the preset condition is selected;
The initial network address is modified using the correction model.
2. the method according to claim 1, wherein
The preset condition include: the initial network address and particular web site there are relevance or the initial network address with it is specific
There are relevances for the web page contents of network address;
Corresponding with the preset condition correction model of the selection includes:
The correction model is selected according to the relevance.
3. according to the method described in claim 2, it is characterized in that, when the relevance be content be associated with when, it is described use institute
Correction model is stated to be modified the initial network address, comprising:
The Web address field of the initial network address is parsed, field keyword is obtained;
The field keyword is inputted into the correction model, the correction model is based on the corresponding history of the field keyword
Correct at least one amendment network address of probability output;Alternatively,
The Web address field of the initial network address is parsed, field attribute value is obtained;
The field attribute value is inputted into the correction model, the correction model is based on the field attribute value and particular web site
Similarity export at least one amendment network address.
4. according to the method described in claim 2, it is characterized in that, when the relevance be semantic association when, it is described use institute
Correction model is stated to be modified the initial network address, comprising:
The Web address field for parsing the initial network address obtains the corresponding semanteme of the Web address field;
By the semantic input correction model, the correction model is based on the corresponding mapping relations output of the semanteme at least
One amendment network address.
5. the method according to claim 1, wherein select corresponding with preset condition correction model it
Before further include:
Using the initial network address of mark, and amendment network address corresponding with initial network address, training sample is constructed;
Using each network layer of the correction model of training sample training building, the correction model is obtained.
6. the method according to claim 1, wherein being repaired using the correction model to the initial network address
Just, comprising:
If multiple correction models selected to use, according to the amendment network address of the multiple correction model output to the original net
Location is modified.
7. according to the method described in claim 6, it is characterized in that, the amendment network address pair exported according to the multiple correction model
The initial network address is modified, comprising:
Obtain the weight of each correction model in the multiple correction model;
Using the weight, the amendment network address of each correction model output of weighted calculation, and according to the weighing computation results
Export at least one amendment network address.
8. method according to claim 1-7, which is characterized in that described to use the correction model to described first
Beginning network address is modified, comprising:
In the predeterminable area of user input interface, revised network address is exported, and according to pair received in the predeterminable area
The selection instruction of revised network address jumps to the revised network address.
9. method according to claim 1-7, which is characterized in that described to use the correction model to described first
Beginning network address is modified, comprising:
When obtained revised network address is one, the revised network address is jumped to;Alternatively,
When obtained revised network address is multiple, the revised network address most by selection number is jumped to.
10. a kind of network address correcting device, which is characterized in that described device includes:
Module is obtained, for obtaining the initial network address of user's input;
Model fitting module selects amendment corresponding with the preset condition if meeting preset condition for the initial network address
Model;
Correction module, for being modified using the correction model to the initial network address.
11. a kind of computer equipment, including memory and processor, be stored on the memory to run on a processor
Computer program, which is characterized in that the processor realizes any one of claims 1 to 9 when executing the computer program
The step of the method.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 9 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810846838.0A CN109063106B (en) | 2018-07-27 | 2018-07-27 | Website correction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810846838.0A CN109063106B (en) | 2018-07-27 | 2018-07-27 | Website correction method and device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109063106A true CN109063106A (en) | 2018-12-21 |
CN109063106B CN109063106B (en) | 2022-03-04 |
Family
ID=64835825
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810846838.0A Active CN109063106B (en) | 2018-07-27 | 2018-07-27 | Website correction method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109063106B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110069364A (en) * | 2019-04-17 | 2019-07-30 | 中广核核电运营有限公司 | Spare part data error-correcting method, device, computer equipment and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6157146A (en) * | 1998-06-29 | 2000-12-05 | Rieter Ingolstadt Spinnereimaschinenbau Ag | Procedure and apparatus for speed related error correction of measurement signals from fiber band speed in a textile machine |
CN102566768A (en) * | 2010-12-13 | 2012-07-11 | 腾讯科技(深圳)有限公司 | Method and system for automatic character judgment and correction |
CN102663000A (en) * | 2012-03-15 | 2012-09-12 | 北京百度网讯科技有限公司 | Establishment method for malicious website database, method and device for identifying malicious website |
CN102685145A (en) * | 2012-05-28 | 2012-09-19 | 西安交通大学 | Domain name server (DNS) data packet-based bot-net domain name discovery method |
US8307073B1 (en) * | 2010-06-24 | 2012-11-06 | Amazon Technologies, Inc. | URL rescue by correction of encoding errors |
CN102981746A (en) * | 2011-05-03 | 2013-03-20 | 宏达国际电子股份有限公司 | Handheld electronic device and method for calibrating input of webpage address |
CN103812906A (en) * | 2012-11-14 | 2014-05-21 | 腾讯科技(深圳)有限公司 | Website recommendation method and device and communication system |
CN104965831A (en) * | 2014-06-11 | 2015-10-07 | 腾讯科技(深圳)有限公司 | Method, server, terminal and system for correcting website addresses |
CN105243073A (en) * | 2014-07-11 | 2016-01-13 | 北京金山安全软件有限公司 | Bookmark access method and device and terminal |
CN105528398A (en) * | 2015-10-22 | 2016-04-27 | 黄建东 | Method and apparatus for switching website links in browser |
CN106959959A (en) * | 2016-01-11 | 2017-07-18 | 阿里巴巴集团控股有限公司 | Webpage access method, data interactive method and server |
CN107992615A (en) * | 2017-12-20 | 2018-05-04 | 维沃移动通信有限公司 | A kind of network address recommends method, server and terminal |
-
2018
- 2018-07-27 CN CN201810846838.0A patent/CN109063106B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6157146A (en) * | 1998-06-29 | 2000-12-05 | Rieter Ingolstadt Spinnereimaschinenbau Ag | Procedure and apparatus for speed related error correction of measurement signals from fiber band speed in a textile machine |
US8307073B1 (en) * | 2010-06-24 | 2012-11-06 | Amazon Technologies, Inc. | URL rescue by correction of encoding errors |
CN102566768A (en) * | 2010-12-13 | 2012-07-11 | 腾讯科技(深圳)有限公司 | Method and system for automatic character judgment and correction |
CN102981746A (en) * | 2011-05-03 | 2013-03-20 | 宏达国际电子股份有限公司 | Handheld electronic device and method for calibrating input of webpage address |
CN102663000A (en) * | 2012-03-15 | 2012-09-12 | 北京百度网讯科技有限公司 | Establishment method for malicious website database, method and device for identifying malicious website |
CN102685145A (en) * | 2012-05-28 | 2012-09-19 | 西安交通大学 | Domain name server (DNS) data packet-based bot-net domain name discovery method |
CN103812906A (en) * | 2012-11-14 | 2014-05-21 | 腾讯科技(深圳)有限公司 | Website recommendation method and device and communication system |
CN104965831A (en) * | 2014-06-11 | 2015-10-07 | 腾讯科技(深圳)有限公司 | Method, server, terminal and system for correcting website addresses |
CN105243073A (en) * | 2014-07-11 | 2016-01-13 | 北京金山安全软件有限公司 | Bookmark access method and device and terminal |
CN105528398A (en) * | 2015-10-22 | 2016-04-27 | 黄建东 | Method and apparatus for switching website links in browser |
CN106959959A (en) * | 2016-01-11 | 2017-07-18 | 阿里巴巴集团控股有限公司 | Webpage access method, data interactive method and server |
CN107992615A (en) * | 2017-12-20 | 2018-05-04 | 维沃移动通信有限公司 | A kind of network address recommends method, server and terminal |
Non-Patent Citations (3)
Title |
---|
HODAT: "关于用javascript修正网址的问题", 《HTTPS://BBS.CSDN.NET/TOPICS/120112294》 * |
TAMBOURATZIS TATIANA: "An Artificial Neural Network Based Approach for Online String Matching/Filtering of Large Databases", 《INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS》 * |
张晓雷: "面向Web挖掘的主题网络爬虫的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110069364A (en) * | 2019-04-17 | 2019-07-30 | 中广核核电运营有限公司 | Spare part data error-correcting method, device, computer equipment and storage medium |
CN110069364B (en) * | 2019-04-17 | 2021-08-06 | 中广核核电运营有限公司 | Spare part data error correction method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109063106B (en) | 2022-03-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9934515B1 (en) | Content recommendation system using a neural network language model | |
US20240070392A1 (en) | Computing numeric representations of words in a high-dimensional space | |
CN106202059B (en) | Machine translation method and machine translation device | |
US20210342549A1 (en) | Method for training semantic analysis model, electronic device and storage medium | |
CN109190049B (en) | Keyword recommendation method, system, electronic device and computer readable medium | |
CN111666401B (en) | Document recommendation method, device, computer equipment and medium based on graph structure | |
US11636341B2 (en) | Processing sequential interaction data | |
CN109800307B (en) | Product evaluation analysis method and device, computer equipment and storage medium | |
US20190171727A1 (en) | Personalized contextual predictive type-ahead query suggestions | |
CN110162681B (en) | Text recognition method, text processing method, text recognition device, text processing device, computer equipment and storage medium | |
CN111079056A (en) | Method, device, computer equipment and storage medium for extracting user portrait | |
CN110674279A (en) | Question-answer processing method, device, equipment and storage medium based on artificial intelligence | |
KR20140119763A (en) | User Data Input Prediction | |
CN110597965B (en) | Emotion polarity analysis method and device for article, electronic equipment and storage medium | |
US20170243116A1 (en) | Apparatus and method to determine keywords enabling reliable search for an answer to question information | |
CN110334242B (en) | Method and device for generating voice instruction suggestion information and electronic equipment | |
CN110135888A (en) | Product information method for pushing, device, computer equipment and storage medium | |
CN111880668A (en) | Input display method and device and electronic equipment | |
CN113420203B (en) | Object recommendation method and device, electronic equipment and storage medium | |
CN114330704A (en) | Statement generation model updating method and device, computer equipment and storage medium | |
CN109063106A (en) | Network address modification method, device, computer equipment and storage medium | |
US9176948B2 (en) | Client/server-based statistical phrase distribution display and associated text entry technique | |
CN112711542A (en) | Method for switching test environments of mobile phone client | |
CN105302336A (en) | Input error correction method and apparatus | |
CN114428838A (en) | Content recall method and device, computer 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |