CN109063106B - Website correction method and device, computer equipment and storage medium - Google Patents
Website correction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109063106B CN109063106B CN201810846838.0A CN201810846838A CN109063106B CN 109063106 B CN109063106 B CN 109063106B CN 201810846838 A CN201810846838 A CN 201810846838A CN 109063106 B CN109063106 B CN 109063106B
- Authority
- CN
- China
- Prior art keywords
- website
- correction
- initial
- model
- field
- 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.)
- Active
Links
Images
Abstract
The application relates to a website correction method, a device, computer equipment and a storage medium, wherein the website correction method comprises the following steps: when the website correction is determined to be needed, firstly, an initial website input by a user is obtained; then when the initial website meets a preset condition, selecting a correction model corresponding to the preset condition; and correcting the initial website by using the correction model. The website correcting method, device, computer equipment and storage medium can correct the initial website without manually inputting a correction website by a user. After the user mistakenly inputs the website, the user can be quickly and conveniently helped to correct the input website, and the user experience is improved.
Description
Technical Field
The present application relates to the field of information technology, and in particular, to a method and an apparatus for correcting a website, a computer device, and a storage medium.
Background
When a user inputs a website in an address bar of a browser to access a webpage, the website is frequently mistakenly input, so that the user jumps to a wrong website or a non-existent website, and at the moment, the user needs to manually correct the website in the address bar to jump to a page which is intended to be browsed.
At present, each browser does not provide a website correcting mode for a user, so that the user can quickly correct and jump to a correct target website after jumping to an incorrect webpage, the speed of accessing the target website by the user is reduced, and the use experience of the user is influenced.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a website address correction method, apparatus, computer device and storage medium.
In a first aspect, an embodiment of the present application provides a website address correction method, where the method includes:
acquiring an initial website input by a user;
if the initial website meets a preset condition, selecting a correction model corresponding to the preset condition;
and correcting the initial website by using the correction model.
In one embodiment, the preset conditions include: the initial website and a specific website have relevance, or the initial website and the webpage content of the specific website have relevance;
the selecting a correction model corresponding to the preset condition includes:
and selecting the correction model according to the relevance.
In one embodiment, when the association is a content association, the modifying the initial website by using the modification model includes:
analyzing the website field of the initial website to obtain a field keyword;
inputting the field keywords into the correction model, and outputting at least one correction website by the correction model based on the historical correction probability corresponding to the field keywords; alternatively, the first and second electrodes may be,
analyzing the website field of the initial website to obtain a field attribute value;
and inputting the field attribute value into the correction model, and outputting at least one corrected website by the correction model based on the similarity of the field attribute value and a specific website.
In one embodiment, when the association is a semantic association, the modifying the initial website by using the modification model includes:
analyzing the website field of the initial website to obtain the corresponding semantics of the website field;
and inputting the semantics into the correction model, and outputting at least one correction website by the correction model based on the mapping relation corresponding to the semantics.
In one embodiment, before selecting the modified model corresponding to the preset condition, the method further includes:
constructing a training sample by using the marked initial website and the corrected website corresponding to the initial website;
and training each network layer of the constructed correction model by using the training samples to obtain the correction model.
In one embodiment, the revising the initial website using the revising model includes:
and if the plurality of used correction models are selected, correcting the initial website according to the correction websites output by the plurality of correction models.
In one embodiment, the modifying the initial website according to the modified websites output by the plurality of modification models includes:
obtaining the weight of each correction model in the plurality of correction models;
and using the weight to calculate the correction websites output by each correction model in a weighted manner, and outputting at least one correction website according to the weighted calculation result.
In one embodiment, the modifying the initial website using the modification model includes:
and outputting the corrected website in a preset area of a user input interface, and jumping to the corrected website according to a selection instruction of the corrected website received in the preset area.
In one embodiment, the modifying the initial website using the modification model includes:
when the obtained corrected website is one, jumping to the corrected website; alternatively, the first and second electrodes may be,
and when a plurality of corrected websites are obtained, jumping to the corrected website with the most selected times.
In a second aspect, an embodiment of the present application provides a website address modification apparatus, where the apparatus includes:
the acquisition module is used for acquiring an initial website input by a user;
the model matching module is used for selecting a correction model corresponding to a preset condition if the initial website meets the preset condition;
and the correction module is used for correcting the initial website by using the correction model.
In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, where the memory stores a computer program that is executable on the processor, and the processor implements, when executing the computer program, the web address correction of the image processing method provided in any embodiment of the present application.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the web address correction of the image processing method provided in any embodiment of the present application.
The application provides a website correction method, a device, a computer device and a storage medium, wherein the website correction method comprises the following steps: when the website correction is determined to be needed, firstly, an initial website input by a user is obtained; then when the initial website meets a preset condition, selecting a correction model corresponding to the preset condition; and correcting the initial website by using the correction model. The website correcting method, device, computer equipment and storage medium can correct the initial website without manually inputting a correction website by a user. After the user mistakenly inputs the website, the user can be quickly and conveniently helped to correct the input website, and the user experience is improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary application environment of a web site modification method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a website address modification method according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating the steps of modifying an initial web address according to another embodiment of the present application;
FIG. 4 is a flowchart illustrating additional steps of a website address correction method according to another embodiment of the present application;
FIG. 5 is a flowchart illustrating the steps of modifying an initial web address according to another embodiment of the present application;
FIG. 6 is a flowchart illustrating additional steps of a website address correction method according to an embodiment of the present application;
FIG. 7 is a flowchart illustrating the steps of modifying an initial web address according to an embodiment of the present application;
FIG. 8 is a flowchart illustrating additional steps of a website address correction method according to an embodiment of the present application;
FIG. 9 is a flowchart illustrating the steps of modifying an initial web address according to an embodiment of the present application;
FIG. 10 is a block diagram illustrating a website address modification apparatus according to an embodiment of the present application;
FIG. 11 is a block diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The website address correction method provided by the application can be applied to the application environment shown in fig. 1. Wherein, the terminal 110 is respectively connected with the processor 120 and the web server 130 in a communication way. The terminal 110 may be used to display a web page returned by the web server 130 according to a web address input by the user. The terminal 110 stores the original website input by the user and the corresponding revised website information. Processor 120 may obtain the original web address entered by the user stored on terminal 110, and the corresponding revised web address information.
Optionally, the terminal 110 may be, but is not limited to, various smart phones, tablet computers, personal computers, and notebook computers. Optionally, the processor 120 may be a cloud server, and the cloud server may be implemented by an independent server or a server cluster composed of a plurality of servers.
Alternatively, the processor 120 may be a processor disposed in the terminal 110. Optionally, the processor disposed in the terminal 110 may be a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an IPU (intelligent Processing Unit, neural network processor), or the like. Optionally, the processor 120 is a multi-core processor, such as a multi-core GPU.
Alternatively, the processor 120 may run an algorithm of the neural network model to process data input into the neural network model. Optionally, the data input into the neural network model may be raw data, such as text, picture, audio, video, etc.; the processed data may also be structured.
In an embodiment, as shown in fig. 2, a web site modification method is provided, which is now described by taking the application environment shown in fig. 1 as an example, and includes the following steps:
step S210: and acquiring an initial website input by a user.
Specifically, the processor 120 obtains an initial website address input by the user.
Optionally, the processor 120 obtains the initial website input by the user after receiving the trigger signal sent by the terminal 110 to modify the current website. Optionally, the trigger signal for modifying the current website sent by the terminal 110 may be a current address bar clicked. Alternatively, the trigger signal for modifying the current website sent by the terminal 110 may be a double click on the current webpage. Optionally, if the current terminal has a 3D Touch (stereo Touch) function, the manner of the trigger signal sent by the terminal 110 for correcting the current website may be to press the screen of the current device again.
Optionally, the processor 120 may also determine whether the initial website input by the user is a target website, and obtain the initial website input by the user when determining that the initial website input by the user is a non-target website. Optionally, the processor may automatically determine whether the initial website input by the user is the target website according to whether the webpage linked by the initial website is an abnormal webpage, or the processor may automatically determine whether the initial website input by the user is the target website according to the access frequency (whether the access frequency is less than a set threshold value) of the webpage linked by the initial website. It should be clear that this value cannot be too large when setting the threshold for the access frequency, since whether the initial web address is the target web address or not has strong user subjectivity.
Step S220: and if the initial website meets a preset condition, selecting a correction model corresponding to the preset condition.
Specifically, if the initial website address meets a preset condition, the processor 120 selects a modification model corresponding to the preset condition. Optionally, after acquiring the initial website, the processor 120 first performs analysis processing on the initial website, and determines that the initial website meets a preset condition. Optionally, the corresponding relationship between the preset condition and the correction model needs to be preset. Optionally, each preset condition may be set to correspond to one correction model, or multiple preset conditions may be set to correspond to one correction model. Optionally, the preset condition may be that the initial website has an association with a specific website, or that the initial website has an association with web page content of the specific website.
Step S230: and correcting the initial website by using the correction model.
Specifically, the processor 120 modifies the initial website address using the modification model. Optionally, the processor 120 runs a correlation algorithm of the correction model, processes the initial website, outputs at least one corrected website, and corrects the initial website using the corrected website. Optionally, the processor 120 may display the website output by the modified model through a user input interface of the terminal, so as to perform human-computer interaction.
When the initial website is corrected through man-machine interaction, a user can correct the initial website through a corrected website in a user input interface selection interface. After the user selects the revised website on the user input interface, the user correspondingly triggers to send a selection signal to the processor 120, and the processor 120 receives the selection signal and revises the initial website by using the revised website selected by the user. Specifically, the processor 120 replaces the initial web address with the revised web address selected by the user. Optionally, if the number of the revised websites output by the revision model is one, the processor 120 may also use the candidate website to directly replace the current website to revise the current website.
In the website correction method provided in the above embodiment, when it is determined that the website correction is required, an initial website input by a user is first obtained; then when the initial website meets a preset condition, selecting a correction model corresponding to the preset condition; and correcting the initial website by using the correction model. According to the website correction method, the initial website can be corrected without manually inputting a correction website by a user. After the user mistakenly inputs the website, the user can be quickly and conveniently helped to correct the input website, and the user experience is improved.
As an optional implementation manner, the selecting the modification model corresponding to the preset condition includes: and selecting the correction model according to the relevance.
Specifically, the processor 120 selects the modified model according to the association between the initial website and the specific website, or the processor 120 selects the modified model according to the association between the initial website and the web content of the specific website. Optionally, the existing association between the initial website and the specific website may be content association or semantic association.
According to the method and the device for correcting the website, the corrected website is selected according to the relevance between the initial website and the specific website, and the corrected website is more favorably and rapidly output by a correction model based on the potential relevance between the initial website and the specific website.
As an alternative embodiment, as shown in fig. 3, when the association is a content association, the modifying the initial website by using the modification model includes:
step S231 a: and analyzing the website field of the initial website to obtain a field keyword.
Specifically, the processor 120 parses the website field of the initial website to obtain a field keyword. Optionally, the field keyword may be a domain name body of the initial website, for example: the initial website address is "http:// www.abx.com", and the processor 120 obtains a field keyword of "abx" after parsing the initial website address.
Step S232 a: and inputting the field keywords into the correction model, and outputting at least one corrected website by the correction model based on the historical correction probability corresponding to the field keywords.
Specifically, the processor 120 runs a neural network algorithm related to the modification model, performs data processing on the field keyword input to the modification model, and finally outputs at least one modified web address based on the historical modification probability corresponding to the field keyword. Optionally, the processor 120 first determines that the preset condition satisfied by the initial website is content association, and then selects a modification model corresponding to the content association. The revision model corresponding to the content association may output at least one revised website based on the historical revision probability corresponding to the field keyword.
As an alternative implementation, as shown in fig. 4, before the modifying the initial website by using the modification model corresponding to the content association, the method further includes:
step S233 a: analyzing and processing the acquired website correction history record to obtain an initial website input by a user in the website correction history record and a corrected website corresponding to the initial website.
Alternatively, the processor 120 may obtain an initial website address in the website address revision history records of a plurality of users and a revision website address corresponding to the initial website address. Alternatively, the processor 120 may only obtain an initial website address in the website address modification history of a certain user and a modification website address corresponding to the initial website address.
Optionally, when the correction history acquired by the processor 120 is a website correction history of multiple users, the processor 120 may first acquire a webpage access history of a certain (or certain) browser, and then filter the webpage access history to obtain website correction histories of multiple users. Optionally, when the correction history acquired by the processor 120 is the website correction history of a certain user, the processor 120 may first acquire the webpage access history of the current user from a local cache or a browser account of the current user, and then filter the webpage access history to obtain the website correction history of the current user.
Step S234 a: and calculating the historical correction probability that the initial website correction input by the user in the website correction historical record is the corresponding corrected website.
Alternatively, the processor 120 may calculate the historical correction record by using a statistical method when calculating the historical correction probability. For example: the processor acquiring the website address correction record comprises: 200 records with the initial website X1 revised as Y1, and 1 record with the initial website X1 revised as Y3. Calculating the probability that the initial website X1 is corrected to Y1: 200/201 ═ 0.995; calculating the probability that the initial website X1 is corrected to Y1: 1/201 is 0.005.
Step S235 a: and setting the corresponding relation between the field keywords of the initial website and the corrected website according to the historical correction probability.
Specifically, the processor 120 sets a corresponding relationship between the field keyword of the initial website and the revised website according to the historical revision probability. Optionally, when the revised website output by the revision model is set according to the historical revision probability, the processor 120 first performs data cleaning on the referenced initial website (for example, only uses the domain name main part of the initial website), obtains the field keyword of the initial website, and then sets the corresponding relationship between the field keyword and the revised website. The method can screen the data of the types such as the universal domain name suffix input by the user by mistake or the website protocol, and the like, so that the obtained result is more in line with the expectation.
Step S236 a: and constructing a correction model corresponding to the content association according to the corresponding relation between the field keywords of the initial website and the corrected website.
Specifically, the processor 120 constructs a correction model corresponding to the content association according to the correspondence between the field keyword of the initial website and the correction website, and outputs the correction website according to the correspondence between the field keyword and the correction website even after the correction model inputs the field keyword.
The method for constructing the correction model corresponding to the content association provided by the embodiment is wide in application range and strong in universality when the correction model is obtained according to the multi-user website correction history. The correction model obtained according to the website correction history of a certain user has strong pertinence and is suitable for providing personalized website correction service for the user. In practical application, which website correction history record is used to set the correction model can be selected according to practical requirements, and the application is not limited herein.
As an alternative implementation, as shown in fig. 5, when the association is a content association, the modifying the initial website by using the modification model includes:
step S231 b: and analyzing the website field of the initial website to obtain a field attribute value.
Specifically, the processor 120 parses the website field of the initial website to obtain the field attribute value. Alternatively, the field attribute value may be the number of characters, or the character content, etc.
Step S232 b: and inputting the field attribute value into the correction model, and outputting at least one corrected website by the correction model based on the similarity of the field attribute value and a specific website.
Specifically, the processor 120 runs a neural network algorithm related to the modification model, performs data processing on the field attribute value input to the modification model, and finally outputs at least one modified website based on the similarity between the field attribute value and the specific website. Optionally, the processor 120 outputs at least one specific website with the highest similarity as the revised website. Optionally, the processor 120 first determines that the preset condition satisfied by the initial website is content association, and then selects a modification model corresponding to the content association. The revised model corresponding to the content association may output at least one revised web address based on a similarity of the field attribute value to the particular web address.
As an alternative implementation, as shown in fig. 6, before the modifying the initial website by using the modification model corresponding to the content association, the method further includes:
step S233 b: and acquiring a specific website set.
Specifically, the processor 120 obtains a specific set of web addresses. And the processor can screen a specific website based on the data statistics of the whole network. For example: the total number of accesses to the web page corresponding to the website may be set to reach a preset threshold T1, and the website may be added to a specific website set. Optionally, whether the daily access volume of the web page corresponding to the website reaches a preset threshold T2 may also be determined, and whether the website may be added to a specific website set. Optionally, due to differences of regional culture or time difference, when a specific website is selected, factors of increasing regions and time can be considered to select the specific website from the whole network data.
Step S234 b: and presetting a similarity calculation rule of the field attribute value of the initial website and the specific website.
Alternatively, the similarity between the field attribute value of the initial website and the field attribute value of the specific website may be calculated. Optionally, the text distance between the field keywords of the initial website and the specific website is calculated, and the similarity between the field attribute value of the initial website and the specific website is calculated. Optionally, firstly, based on field attribute values of the initial website and the specific website, marking similarity of the initial website and the specific website, and constructing a model training sample; training each network layer of a similarity calculation model by using the model training sample to obtain a similarity calculation model; and using a similarity calculation model to obtain the similarity between the field attribute value of the initial website and the specific website.
Step S235 b: and setting a correction model according to the similarity, and outputting a correction website based on the field attribute value.
Specifically, the processor 120: and setting a correction model according to the similarity, and outputting a correction website based on the field attribute value.
In the method for correcting a website output based on the field attribute value provided by this embodiment, since the specific website is generally a commonly used website of the user, the user can be helped to quickly acquire the commonly used website under the condition that the user wants to access the commonly used website but fails.
As an alternative embodiment, as shown in fig. 7, when the association is a semantic association, the modifying the initial website by using the modification model includes:
step S231 c: and analyzing the website field of the initial website to obtain the corresponding semantics of the website field.
Specifically, the processor 120 parses the website field of the initial website to obtain the semantic meaning corresponding to the website field. Optionally, the processor 120 performs data mining on the semantics of multiple websites and the actual websites of the websites to obtain the semantics of the websites and the mapping relationship between the semantics of the websites and the actual websites of the websites. Optionally, the semantic meaning of the website may be pinyin of the website, or english synonyms of the website, or other information related to the meaning of the website. For example: the Chinese name of a certain site is ' a ', and the actual website of the site is ' abx. The initial website "mou.com" obtained by the user according to the pinyin of the website is not matched with the actual website "abx.com", and the obtained mapping relation is as follows: com "is set as the revised web address of the initial web address" mou.com ".
Step S232 c: and inputting the semantics into the correction model, and outputting at least one correction website by the correction model based on the mapping relation corresponding to the semantics.
Specifically, the processor 120 runs a neural network algorithm related to the correction model, performs data processing on the semantics input into the correction model, and obtains at least one actual website based on a mapping relationship corresponding to the semantics, and outputs the actual website as a corrected website. Optionally, the processor 120 first determines that the preset condition satisfied by the initial website is semantic association, and then selects a modification model corresponding to the semantic association. The revision model corresponding to the semantic association may output at least one revised web address based on the mapping corresponding to the semantic association.
The method for outputting at least one modified website based on the mapping relationship corresponding to the semantics, which is provided by this embodiment, can enable a user to quickly acquire a target website whose semantics are not matched with an actual website, and is particularly suitable for a situation that the user guesses that the target website cannot be accessed by inputting an initial website through a website name pronunciation.
As an alternative embodiment, as shown in fig. 8, before selecting the correction model corresponding to the preset condition, the method further includes:
step S240: and constructing a training sample by using the marked initial website and the corrected website corresponding to the initial website.
Step S250: and training each network layer of the constructed correction model by using the training samples to obtain the correction model.
Optionally, the modification model may be an RNN-encoder-decoder (recurrent neural network codec) neural network model or another deep learning neural network model, and the deep learning neural network model may implement end-to-end result output, that is, directly output the modified website according to the initial website. Optionally, the process of training the RNN-encoder-decoder includes:
step a, inputting a plurality of obtained model training samples into a neural network of an RNN-encoder-decoder neural network model, wherein the neural network comprises a plurality of network layers. And calculating the gradient value of the loss function of each layer by using a random gradient descent algorithm, and updating the weight value of the corresponding layer by using the obtained gradient value of each layer.
And b, calculating the error sensitivity of each layer of the neural network by using a back propagation algorithm, and updating the weight of the corresponding layer by using the error sensitivity of each layer.
And c, iteratively executing the step a and the step b until the weight value of the corresponding layer updated by the gradient value of each layer is equal to the weight value of the corresponding layer updated by the error sensitivity of each layer, thereby obtaining the RNN-encoder-decoder neural network.
The deep neural network model is used as a correction model, and correction websites are output according to a preset target task, so that the obtained candidate websites can meet the expectations of people.
As an optional implementation, the modifying the initial website using the modification model includes: and if the plurality of used correction models are selected, correcting the initial website according to the correction websites output by the plurality of correction models. Specifically, the processor 120: and if the plurality of used correction models are selected, correcting the initial website according to the correction websites output by the plurality of correction models. Optionally, the processor 120 selects all the modification addresses output by each of the plurality of modification models to output. For example: the processor 120 selects a modification model M1 associated with the content and a modification model M2 associated with the semantics, and performs website address modification, a modification website address X1 output by the modification model M1 and a modification website address X2 output by the modification model M2; the processor 120 outputs both the revised website X1 and the revised website X2 as revised websites.
As an alternative embodiment, as shown in fig. 9, the modifying the initial website according to the modified websites output by the plurality of modification models includes:
step S231 d: and acquiring the weight of each of the plurality of correction models.
Specifically, the processor 120 obtains a weight value of each of the plurality of modified models. For example: a correction model obtained based on the website correction history of multiple users is M3; a correction model obtained based on the website correction history of the current user (single user) is M4; when the processor 120 selects the website address corrected by using the corrected model M3 and the corrected model M4, it first obtains the preset weights of the corrected model M3 and the corrected model M4.
Step S232 d: and using the weight to calculate the correction websites output by each correction model in a weighted manner, and outputting at least one correction website according to the weighted calculation result.
Specifically, the processor 120 uses the weight to calculate the modified website output by each of the modification models in a weighted manner, and outputs at least one modified website according to the weighted calculation result. For example, the correction websites X31 and X32 output by the correction model M3 have corresponding probabilities of P1 and P2; the correction websites X31 and X41 output by the correction model M4 have corresponding probabilities of P3 and P4, wherein P1 is P2 is P3 is P4; the weight of the modified model M3 obtained by the processor 120 is Y1, and the weight of the modified model M3 is Y2, where Y2 > Y1. The processor 120 performs a weighted calculation on each modified web address, where the weighted calculation result corresponding to the modified web address X31 is: P1Y 1+ P3Y 3; the weighting calculation result corresponding to the revised website address X32 is P2X 1; the weighting calculation result corresponding to the revised website X41 is: p4 × Y2. Finally, the processor 120 outputs the revised website address according to the weighted calculation result. If a correction website is output, outputting a correction website X31; if 3 correction addresses are output, correction addresses X31, X41 and X32 are output. Preferably, when the modified model is M3 (multi-user data) and the modified model is a weight corresponding to M4 (single user), the weight is biased to the modified model corresponding to the single user.
The website correction is performed by combining the output results of the plurality of correction models, so that more diversified website correction influence factors can be integrated, and a website more conforming to the expectation of the user can be output.
As an alternative embodiment, as shown in fig. 6, the modifying the initial website by using the modification model includes: and outputting the corrected website in a preset area of a user input interface, and jumping to the corrected website according to a selection instruction of the corrected website received in the preset area.
Optionally, the revised website is output in a pull-down menu form in an address bar of the user input interface. Alternatively, when the current terminal is a portable terminal (e.g., a mobile phone, an ipad, etc.), the processor may first detect a current position of a finger of the user at a user input interface of the terminal, and then output a corrected address at the current position in the form of a floating frame. Optionally, after the terminal outputs the revised website, the user may perform a selection operation with respect to the output revised website, that is, send a selection signal. After receiving the selection signal in the predetermined area, the processor 120 may modify the initial website address using the modified website address corresponding to the selection signal.
The candidate website correction provided by the embodiment provides a simple and convenient human-computer interaction mode, and can help a user to quickly correct the current website by using the candidate website.
As an optional implementation, the modifying the initial website by using the modification model includes: when the obtained corrected website is one, jumping to the corrected website; or when a plurality of corrected websites are obtained, jumping to the corrected website with the most times of selection.
Specifically, optionally, a jump threshold of the modified website may be preset, and if the number of times of selection of the modified website reaches the jump threshold, the modified website is directly jumped.
For example: the user C inputs that the user C wants to access 'dbx.com', but the user C mistaks the website as 'dbc.com', cannot access the target website 'dbx.com', and the preset jump threshold value is 20 times. The processor 120 may record the number of times the user selects modification to "dbx.com" after inputting "dbc.com" and judge whether the number of times of selection reaches 20 times. And if so, directly replacing 'dbc.com' by 'dbx.com' after the user inputs 'dbc.com' next time, and jumping to the webpage corresponding to the dbx.com.
The website correction method of the embodiment directly uses the candidate website to replace the current website based on the personal website miss-input habit of the user, reduces data operation, and improves the system response efficiency.
It should be understood that although the various steps in the flowcharts of fig. 2-9 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-9 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 10, there is provided a web site address correcting apparatus, including:
the acquiring module 100 is configured to acquire an initial website input by a user.
And the model matching module 200 is configured to select a correction model corresponding to a preset condition if the initial website meets the preset condition.
A website address modification module 300, configured to modify the initial website address by using the modification model.
As an optional implementation manner, the model matching module 200 is further configured to select the modified model according to the existing association between the initial website and the specific website; or selecting the correction model according to the relevance of the initial website and the webpage content of the specific website.
As an optional implementation manner, the website address modification module 300 is further configured to, when the association is content association, parse a website address field of the initial website address to obtain a field keyword; and inputting the field keywords into the correction model, and outputting at least one corrected website by the correction model based on the historical correction probability corresponding to the field keywords.
As an optional implementation manner, the website address modifying module 300 is further configured to, when the association is content association, parse the website address field of the initial website address to obtain a field attribute value; and inputting the field attribute value into the correction model, and outputting at least one corrected website by the correction model based on the similarity of the field attribute value and a specific website.
As an optional implementation manner, the website address modification module 300 is further configured to, when the association is semantic association, analyze the website address field of the initial website address, and obtain a semantic corresponding to the website address field; and inputting the semantics into the correction model, and outputting at least one correction website by the correction model based on the mapping relation corresponding to the semantics.
As an optional implementation manner, the website address modification module 300 is further configured to train, using the training samples, each network layer of the constructed modification model to obtain the modification model; the training protocol is constructed by a pre-marked initial website and a correction website corresponding to the initial website.
As an optional implementation manner, the website address modification module 300 may be further configured to modify the initial website address according to a modification website address output by the plurality of modification models if the plurality of modification models are selected for use.
As an optional implementation manner, the website address modification module 300 is specifically configured to obtain a weight of each of the plurality of modification models; and using the weight to calculate the correction websites output by each correction model in a weighted manner, and outputting at least one correction website according to the weighted calculation result.
For the specific limitation of the website address correction device, reference may be made to the above limitation on the website address correction method, and details are not described herein again. Each module in the above website correction apparatus may be wholly or partially implemented by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, and the computer device may be a server, and the schematic structural diagram of the computer device may be as shown in fig. 11. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing relevant data of the webpage access history of the user. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a web site modification method.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory and a processor, the memory having stored thereon a computer program operable on the processor, the processor implementing the following steps when executing the computer program: acquiring an initial website input by a user; if the initial website meets a preset condition, selecting a correction model corresponding to the preset condition; and correcting the initial website by using the correction model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: selecting the correction model according to the relevance of the initial website and the specific website; or selecting the correction model according to the relevance of the initial website and the webpage content of the specific website.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when the relevance is content relevance, analyzing the website field of the initial website to obtain a field keyword; and inputting the field keywords into the correction model, and outputting at least one corrected website by the correction model based on the historical correction probability corresponding to the field keywords.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when the relevance is content relevance, analyzing the website field of the initial website to obtain a field attribute value; and inputting the field attribute value into the correction model, and outputting at least one corrected website by the correction model based on the similarity of the field attribute value and a specific website.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when the correlation is semantic correlation, analyzing the website field of the initial website to acquire the semantic corresponding to the website field; and inputting the semantics into the correction model, and outputting at least one correction website by the correction model based on the mapping relation corresponding to the semantics.
In one embodiment, the processor, when executing the computer program, further performs the steps of: training each network layer of a constructed correction model by using the training samples to obtain the correction model; the training protocol is constructed by a pre-marked initial website and a correction website corresponding to the initial website.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and if the plurality of used correction models are selected, correcting the initial website according to the correction websites output by the plurality of correction models.
In one embodiment, the processor is further configured to execute the computer program to perform the steps of: obtaining the weight of each correction model in the plurality of correction models; and using the weight to calculate the correction websites output by each correction model in a weighted manner, and outputting at least one correction website according to the weighted calculation result.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement the website address correction method provided in any embodiment of the present application.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (11)
1. A web address correction method, comprising:
if a trigger signal for correcting the current website is received, acquiring an initial website input by a user;
if the initial website and the specific website have relevance, or the initial website and the webpage content of the specific website have relevance, selecting a corresponding correction model according to the relevance;
using the correction model to correct the letters of the initial website, including:
analyzing the website field of the initial website, inputting the analysis result into the correction model, and outputting at least one correction website by the correction model.
2. The method of claim 1, wherein when the association is a content association, the modifying the initial web address letter using the modification model comprises:
analyzing the website field of the initial website to obtain a field keyword;
inputting the field keywords into the correction model, and outputting at least one correction website by the correction model based on the historical correction probability corresponding to the field keywords; alternatively, the first and second electrodes may be,
analyzing the website field of the initial website to obtain a field attribute value;
and inputting the field attribute value into the correction model, and outputting at least one corrected website by the correction model based on the similarity of the field attribute value and a specific website.
3. The method of claim 1, wherein when the association is a semantic association, the modifying the initial web address letter using the modification model comprises:
analyzing the website field of the initial website to obtain the corresponding semantics of the website field;
and inputting the semantics into the correction model, and outputting at least one correction website by the correction model based on the mapping relation corresponding to the semantics.
4. The method of claim 1, further comprising, prior to selecting the corresponding modified model:
constructing a training sample by using the marked initial website and the corrected website corresponding to the initial website;
and training each network layer of the constructed correction model by using the training samples to obtain the correction model.
5. The method of claim 1, wherein modifying the initial web address using the modification model comprises:
and if the plurality of used correction models are selected, correcting the initial website according to the correction websites output by the plurality of correction models.
6. The method of claim 5, wherein modifying the initial website according to the modified websites output by the plurality of modification models comprises:
obtaining the weight of each correction model in the plurality of correction models;
and using the weight to calculate the correction websites output by each correction model in a weighted manner, and outputting at least one correction website according to the weighted calculation result.
7. The method according to any one of claims 1-6, wherein said modifying the letter of the initial web address using the modification model comprises:
and outputting the corrected website in a preset area of a user input interface, and jumping to the corrected website according to a selection instruction of the corrected website received in the preset area.
8. The method according to any one of claims 1-6, wherein said modifying the letter of the initial web address using the modification model comprises:
when the obtained corrected website is one, jumping to the corrected website; alternatively, the first and second electrodes may be,
and when a plurality of corrected websites are obtained, jumping to the corrected website with the most selected times.
9. A website address correction apparatus, comprising:
the acquisition module is used for acquiring an initial website input by a user if a trigger signal for correcting the current website is received;
the model matching module is used for selecting a corresponding correction model according to the relevance when the relevance exists between the initial website and the specific website or the relevance exists between the initial website and the webpage content of the specific website;
a correction module, configured to correct the letter of the initial website by using the correction model, including:
analyzing the website field of the initial website, inputting the analysis result into the correction model, and outputting at least one correction website by the correction model.
10. A computer device comprising a memory and a processor, the memory having stored thereon a computer program operable on the processor, wherein the processor, when executing the computer program, performs the steps of the method of any of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.
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 CN109063106A (en) | 2018-12-21 |
| CN109063106B true 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) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Citations (8)
| 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 |
| 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 |
| 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 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8307073B1 (en) * | 2010-06-24 | 2012-11-06 | Amazon Technologies, Inc. | URL rescue by correction of encoding errors |
| 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 |
| CN105528398B (en) * | 2015-10-22 | 2019-02-26 | 金寨希姆网络科技有限公司 | Switch the method and device of website links in a kind of browser |
| CN112115336A (en) * | 2016-01-11 | 2020-12-22 | 阿里巴巴集团控股有限公司 | Webpage access method, client and preset server |
-
2018
- 2018-07-27 CN CN201810846838.0A patent/CN109063106B/en active Active
Patent Citations (8)
| 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 |
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109063106A (en) | 2018-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110457431B (en) | Knowledge graph-based question and answer method and device, computer equipment and storage medium | |
| JP7073576B2 (en) | Association recommendation method, equipment, computer equipment and storage media | |
| CN109190049B (en) | Keyword recommendation method, system, electronic device and computer readable medium | |
| US20150169710A1 (en) | Method and apparatus for providing search results | |
| US9619283B2 (en) | Function-based action sequence derivation for personal assistant system | |
| CN110674279A (en) | Question-answer processing method, device, equipment and storage medium based on artificial intelligence | |
| US20200074999A1 (en) | Semi-supervised question answering machine | |
| RU2664481C1 (en) | Method and system of selecting potentially erroneously ranked documents with use of machine training algorithm | |
| CN105531701A (en) | Personalized trending image search suggestion | |
| CN109814779B (en) | Menu display method and device, computer equipment and storage medium | |
| JP6693582B2 (en) | Document abstract generation method, device, electronic device, and computer-readable storage medium | |
| CN110781396A (en) | Information recommendation method, device, equipment and storage medium | |
| US20240104154A1 (en) | Ranking of recall data | |
| US10878189B2 (en) | Method for correcting a mistyped word resulting from at least one of an inaccurate keyboard input and a wrong keyboard layout and system implementing thereof | |
| US20210383491A1 (en) | Patent text generating device, patent text generating method, and non-transitory computer-readable medium | |
| CN109063106B (en) | Website correction method and device, computer equipment and storage medium | |
| CN114297361A (en) | Human-computer interaction method based on scene conversation understanding and related components | |
| US11468125B2 (en) | Resource search method and related product | |
| CN108197288B (en) | House source pushing method, device, equipment and medium according to user characteristic preference | |
| KR20150029719A (en) | A web browser operation method and system | |
| US9176948B2 (en) | Client/server-based statistical phrase distribution display and associated text entry technique | |
| EP4053713A1 (en) | Question and answer method and apparatus based on knowledge graph | |
| CN114238715A (en) | Question-answering system based on social aid, construction method, computer equipment and medium | |
| CN110895924B (en) | Method and device for reading document content aloud, electronic equipment and readable storage medium | |
| CN109885787B (en) | APP page display method and system, mobile terminal and computer readable 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 |