CN103995852B - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN103995852B CN103995852B CN201410198312.8A CN201410198312A CN103995852B CN 103995852 B CN103995852 B CN 103995852B CN 201410198312 A CN201410198312 A CN 201410198312A CN 103995852 B CN103995852 B CN 103995852B
- Authority
- CN
- China
- Prior art keywords
- content
- information
- user
- shows
- browsed
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
- G06F16/9577—Optimising the visualization of content, e.g. distillation of HTML documents
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention proposes a kind of data processing method and device, and the data processing method shows including mobile terminal to search result；The information for showing content on mobile terminal screen is obtained, the content that shows includes：Initial screen shows content, and, the screen after each screen sliding of user shows content；The information for showing content is sent to server, so as to show the information of content described in the server record, the information for showing content is used to obtain the content not browsed to by user in the search result, and the information of the content not browsed to by user is removed in click logs are showed.This method can reduce input data amount, and improve model pre-estimating accuracy rate.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of data processing method and device.
Background technology
With the fast development of internet, user can obtain more information by the page that internet shows.For
Internet advertising is launched for business, and click behavior of the analysis user to interconnection online advertisement, the advertisement putting to itself has weight
Want meaning.The click behavior of user on the internet, which can be recorded in, to be showed in click logs, and it is indispensable to show click logs
Few training data, it is widely used in clicking rate (Click Through Rate, CTR) prediction model of advertisement.
In correlation technique, show click logs as the defeated of ad click rate prediction model in direct application searches engine
Enter data, the advertisement loaded on default page has all been presented to user, and it is positive example that user, which clicks on, is otherwise negative example.
But relative to PC (Personal Computer, PC), the screen of mobile terminal is smaller, and what is showed is interior
Have limit, the advertisement for causing to load on the page can not all be presented to user.Therefore, direct use shows click logs and not only led
Cause the input data amount of CTR mod type larger, and can not truly reflect that user's browses click behavior, exist a large amount of non-genuine
Data, influence the accuracy rate that CTR mod type is estimated.
The content of the invention
It is contemplated that at least solves one of technical problem in correlation technique to a certain extent.
Therefore, it is an object of the present invention to propose a kind of data processing method, this method can reduce CTR mod type
Input data amount, and improve model and estimate accuracy rate.
It is another object of the present invention to propose a kind of data processing equipment.
To reach above-mentioned purpose, data processing method that first aspect present invention embodiment proposes, including：To search result
Showed, the search result is that the search term inputted according to user obtains；Obtain and show content on mobile terminal screen
Information, the content that shows includes：Initial screen shows content, and, the screen after each screen sliding of user shows content；Will
The information for showing content is sent to server, so as to show the information of content described in the server record, it is described to show
The information of content is used to obtain the content not browsed to by user in the search result, and is removed in click logs are showed
The information of the content not browsed to by user.
The data processing method that first aspect present invention embodiment proposes, by the way that content will be showed on mobile terminal screen
Information is sent to server, then determine not browsed to by user according to the information for showing content on mobile terminal screen in
Hold, and the information for the content not browsed to by user is removed in click logs are showed, on the one hand due to eliminating part letter
Breath can reduce the input data amount of CTR mod type, on the other hand due to eliminating the information of the content not browsed to by user,
The information using inaccuracy can be avoided, and as the input data of model, that improves model estimates accuracy rate.
To reach above-mentioned purpose, data processing method that second aspect of the present invention embodiment proposes, including：Obtain server
Show the information of content on the mobile terminal screen of middle record, the information for showing content is that the mobile terminal is tied to search
Fruit obtains after being showed and is sent to the server, and the search result is that the search term inputted according to user obtains
, the content that shows includes：Initial screen shows content, and, the screen after each screen sliding of user shows content；According to institute
State the content for showing and not browsed in search result described in the acquisition of information of content by user；Removed in click logs are showed
The information of the content not browsed to by user.
The data processing method that second aspect of the present invention embodiment proposes, by according to showing content on mobile terminal screen
Information determine the content that is not browsed to by user, and the content not browsed to by user is removed in click logs are showed
Information, on the one hand the input data amount of CTR mod type can be reduced due to eliminating partial information, on the other hand due to eliminating
The information for the content not browsed to by user, the input data using the information of inaccuracy as model can be avoided, improves mould
Type estimates accuracy rate.
To reach above-mentioned purpose, data processing equipment that third aspect present invention embodiment proposes, including：Display module,
For showing to search result, the search result is that the search term inputted according to user obtains；Acquisition module, it is used for
The information for showing content on mobile terminal screen is obtained, the content that shows includes：Initial screen shows content, and, user
Screen after each screen sliding shows content；Sending module, for the information for showing content to be sent into server, so that institute
State the information for showing content described in server record, the information for showing content be used to obtain in the search result not by
The content that user browses to, and remove in click logs are showed the information of the content not browsed to by user.
The data processing equipment that third aspect present invention embodiment proposes, by showing on the mobile terminal screen
The information of appearance is sent to server, then shows according to not clear by user in search result described in the acquisition of information of content
The content look at, and remove in click logs are showed the information of the content not browsed to by user, on the one hand due to
The input data amount of CTR mod type can be reduced by eliminating partial information, on the other hand not browsed to due to eliminating by user
Content information, can avoid using inaccuracy information as the input data of model, that improves model estimates accuracy rate.
To reach above-mentioned purpose, data processing equipment that fourth aspect present invention embodiment proposes, including：Acquisition module,
Show the information of content on the mobile terminal screen recorded in server for obtaining, the information for showing content is the shifting
Dynamic terminal-pair search result is obtained after being showed and is sent to the server, and the search result is inputted according to user
Search term obtain, the content that shows includes：Initial screen shows content, and, the screen exhibition after each screen sliding of user
Existing content；Determining module, do not have for making the server show according in search result described in the acquisition of information of content
The content browsed to by user；Remove module, for removed in click logs are showed it is described do not browsed to by user in
The information of appearance.
The data processing equipment that fourth aspect present invention embodiment proposes, by according to showing content on mobile terminal screen
Information determine the content that is not browsed to by user, removed in click logs are showed it is described do not browsed to by user in
The information of appearance, the input data amount of CTR mod type on the one hand can be reduced due to eliminating partial information, on the other hand due to removing
The information for the content not browsed to by user, it can avoid the information of inaccuracy being used as the input data of model, raising
Model estimates accuracy rate.
To reach above-mentioned purpose, mobile terminal that fifth aspect present invention embodiment proposes, including：Housing, processor, deposit
Reservoir, circuit board and power circuit, wherein, the circuit board is placed in the interior volume that the housing surrounds, the processor
It is arranged on the memory on the circuit board；The power circuit, for each circuit or device for the mobile terminal
Part is powered；The memory is used to store executable program code；What the processor was stored by reading in the memory
Executable program code runs program corresponding with the executable program code, for：Search result is showed,
The search result is that the search term inputted according to user obtains；Obtain the information for showing content on mobile terminal screen, institute
State and show content and include：Initial screen shows content, and, the screen after each screen sliding of user shows content；Show described
The information of content is sent to server, so as to show the information of content described in the server record, the letter for showing content
Cease for obtaining the content not browsed in the search result by user, and remove in click logs are showed and described not have
The information of the content browsed to by user.The mobile terminal that fifth aspect present invention embodiment proposes, by by mobile terminal screen
The information for showing content on curtain is sent to server, then according to show on mobile terminal screen content information determine not by
The content that user browses to, and the information for the content not browsed to by user is removed in click logs are showed, on the one hand by
The input data amount of CTR mod type can be reduced in eliminating partial information, is not on the other hand browsed due to eliminating by user
The information of the content arrived, can avoiding the information using inaccuracy, that improves model estimates accuracy rate as the input data of model.
To reach above-mentioned purpose, data processing equipment that sixth aspect present invention embodiment proposes, including：Housing, processing
Device, memory, circuit board and power circuit, wherein, the circuit board is placed in the interior volume that the housing surrounds, the place
Reason device and the memory are arranged on the circuit board；The power circuit, for each circuit or device for described device
Part is powered；The memory is used to store executable program code；What the processor was stored by reading in the memory
Executable program code runs program corresponding with the executable program code, for：Obtain what is recorded in server
Show the information of content on mobile terminal screen, the information for showing content is that the mobile terminal is opened up to search result
Now obtain afterwards and be sent to the server, the search result is that the search term inputted according to user obtains, the exhibition
Existing content includes：Initial screen shows content, and, the screen after each screen sliding of user shows content；According in described show
The content not browsed in search result described in the acquisition of information of appearance by user；Being removed in click logs are showed described does not have
The information of the content browsed to by user.The data processing equipment that sixth aspect present invention embodiment proposes, by according to movement
The information for showing content on terminal screen determines the content that is not browsed to by user, and removes and do not have in click logs are showed
The information of the content browsed to by user, the input data amount of CTR mod type on the one hand can be reduced due to eliminating partial information,
Information of the another aspect due to eliminating the content not browsed to by user, can avoid the information using inaccuracy as model
Input data, that improves model estimates accuracy rate.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein：
Fig. 1 is the schematic flow sheet for the data processing method that one embodiment of the invention proposes；
Fig. 2 is the schematic flow sheet for the data processing method that another embodiment of the present invention proposes；
Fig. 3 is the schematic flow sheet for the data processing method that another embodiment of the present invention proposes；
Fig. 4 is the structural representation for the data processing equipment that another embodiment of the present invention proposes；
Fig. 5 is the structural representation for the data processing equipment that another embodiment of the present invention proposes.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, is only used for explaining the present invention, and is not considered as limiting the invention.On the contrary, this
All changes that the embodiment of invention includes falling into the range of the spirit and intension of attached claims, modification and equivalent
Thing.
Fig. 1 is the schematic flow sheet for the data processing method that one embodiment of the invention proposes, this method includes：
S11：Mobile terminal shows to search result, and the search result is that the search term inputted according to user obtains
's.
In similar correlation technique, after user inputs search term in a browser by mobile terminal, it can obtain searching with this
Search result corresponding to rope word.
Search result can include the content of one or at least two, when the content that search result includes is more, due to
The limitation of mobile terminal screen size, once all user generally can not be presented to, it is necessary to which the continuous screen sliding of user obtains more
Information, continue to show the content that last time do not show on the basis of in last time can showing after each screen sliding.
In addition, the screen sliding in the embodiment of the present invention, which is not limited by, touches the screen sliding that screen is realized, also adopted including traditional
With key mode so that showing the continually changing mode of content.
S12：Show the information of content on acquisition for mobile terminal mobile terminal screen, the content that shows includes：Initial screen
Curtain shows content, and, the screen after each screen sliding of user shows content.
In the present embodiment, JS (JavaScript) code can be implanted into webpage in mobile terminal to search, monitoring is used
The screen sliding operation at family, to obtain the information for showing content after initially showing and the letter for showing content after each screen sliding
Breath.
S13：The information for showing content is sent to server by mobile terminal, so that exhibition described in the server record
The information of existing content, the information for showing content are used to obtain the content not browsed to by user in the search result,
And the information of the content not browsed to by user is removed in click logs are showed.
Wherein it is possible to the information for showing content on mobile terminal screen is sent to by server according to above-mentioned JS codes,
Such as after each screen sliding of user, the information for showing content after corresponding screen sliding is sent to server.Server receives this
It can be recorded, such as be recorded in screen sliding daily record after showing the information of content.In follow-up process, such as carry out CTR modelings
When the information for showing content can be obtained from server, and in the search result according to this shows the acquisition of information of content
The content not browsed to by user, and remove in click logs are showed the letter of the content not browsed to by user
Breath.
Further, the information for showing content can be specially the letter that the last item shows content on mobile terminal screen
Breath, for example, presenting three on mobile terminal screen from top to bottom shows content, Article 3 can only be showed to the information of content
It is sent to server.
Further, the last item shows the information of content and can specifically included：The last item shows the numbering of content,
And the last item shows showing highly for content.Because search result is provided by server, therefore, server can be remembered
Record the information of every content in search result.Wherein, server can enter every content according to the order that shows from top to bottom
Line number, for example, after server obtains a plurality of search result, according to pre-defined algorithm can determine each bar search result on to
Under put in order, server can carry out volume from small to large to each bar search result in accordance with the order from top to bottom afterwards
Number.So, when server, which receives the last item on screen, shows numbering (such as 3) of content, it is possible to compiled before determining
The content that shows of number (such as 1,2) is browsed by user.In addition, the entirety of every search result can be also recorded in server
Highly, and the last item search result is probably all to show in the terminal, such as only shows whole height
A part, server can show according to this in height and whole height determine whether the last item belongs to and browsed to by user
Hold.
Showing the information of content on the screen that mobile terminal is sent can record in the server, to be adopted in follow-up process
With, for example, the content that can not browsed to when CTR is modeled according to information determination by user, and then click on day showing
The information of the content not browsed to by user is removed in will, avoids inputting the data of inaccuracy in CTR mod type.
The present embodiment by the information for showing content on mobile terminal screen by being sent to server so that remembers in server
Record has the information that this shows content, and then can be determined in follow-up process according to the information for showing content on mobile terminal screen
The content not browsed to by user, and the information for the content not browsed to by user is removed in click logs are showed, one
Aspect can reduce the input data amount of CTR mod type due to eliminating partial information, on the other hand due to eliminate not by with
The information for the content that family browses to, the information using inaccuracy can be avoided to improve estimating for model as the input data of model
Accuracy rate.
Fig. 2 is the schematic flow sheet for the data processing method that another embodiment of the present invention proposes, this method includes：
S21：Obtain the information for showing content on the mobile terminal screen recorded in server, the information for showing content
It is that the server is obtained and be sent to after the mobile terminal shows to search result, the search result is basis
What the search term of user's input obtained, the content that shows includes：Initial screen shows content, and, after each screen sliding of user
Screen show content.
The information for showing content can be the information that the last item shows content on mobile terminal screen.
Further, described the last item shows the information of content, including：The last item shows the numbering of content, and
The last item shows showing highly for content.
S22：According to it is described show the acquisition of information of content described in the content that is not browsed to by user in search result.
For example, the content that shows before described the last item shows the numbering of content is defined as being browsed by user
The content arrived；And
According to described the last item show content show height determine described the last item show content whether be by with
The content that family browses to.
Further, the height that shows that content can be showed in described the last item shows content with described the last item
When ratio between whole height is more than default threshold value, it is in being browsed to by user to determine that described the last item shows content
Hold.
Further, the default threshold value can be specially 1/4.
S23：The information of the content not browsed to by user is removed in click logs are showed.
Wherein, in correlation technique, the information that every search result can be recorded in click logs is showed, no matter this searches for knot
Whether fruit is browsed to by user.For example, after user inputs a search term, server loads all search corresponding with the search term
As a result, it is assumed that the number of all search results is 8, then showing in correlation technique in click logs can search comprising this 8
The information of hitch fruit, it is exactly positive example when user clicks on certain search result therein, is otherwise negative example.But this 8 search
As a result there may be the result not appeared at all on screen in, accordingly, user can not possibly browse to, and cause data not
Accurately.
And in the present embodiment, the content that is not browsed to for user, the user is removed in click logs are showed not to be had
The information of the content browsed to, avoid being predicted using inaccurate data.
Wherein, the executive agent of the present embodiment can be data processing equipment, after can be processed by the device
Show click logs, the click logs that show after the processing can be used in occasions such as CTR modelings.
The present embodiment passes through in being determined not browsed to by user according to the information for showing content on mobile terminal screen
Hold, and the information for the content not browsed to by user is removed in click logs are showed, on the one hand due to eliminating part letter
Breath can reduce the input data amount of CTR mod type, on the other hand due to eliminating the information of the content not browsed to by user,
The information using inaccuracy can be avoided, and as the input data of model, that improves model estimates accuracy rate.
Fig. 3 is the schematic flow sheet for the data processing method that another embodiment of the present invention proposes, in the present embodiment, with movement
Terminal is mobile phone, exemplified by search result is advertisement.Referring to Fig. 3, the present embodiment includes：
S301：Mobile phone receives the search term of user's input.
S302：Search term is sent to server by mobile phone.
S303：Server is scanned for using preset algorithm to search term, obtains a plurality of advertisement.And server to from
The advertisement up to showed down is numbered successively, and records the whole height of every advertisement.
S304：A plurality of advertisement is sent to mobile phone by server.
S305：Mobile phone is initially showed to a plurality of advertisement.
S306：Mobile phone by the numbering for initially showing rear screen the last item advertisement and show height be sent to server.
S307：The information of reception is numbered and shows altitude record in screen sliding daily record by server.
S308：Mobile phone obtains the numbering of the last item advertisement after each screen sliding and shows height after each screen sliding of user.
S309：After each screen sliding, by the numbering of the last item advertisement after each screen sliding and show height be sent to service
Device.
S310：Server the numbering of the last item advertisement and shows height by the information of reception, i.e., after each screen sliding, record
In screen sliding daily record.
Wherein, the information of content is showed (e.g., finally after being recorded in screen sliding daily record per next state (after initial and each screen sliding)
The numbering of one advertisement and show height).
S311：Data processing equipment obtains screen sliding daily record from server.
Wherein, data processing equipment can be the device of offline post-processing librarian use, and the device is used for showing
Click logs are handled.The device can be located in server or outside server.
S312：Data processing equipment according to recorded in screen sliding daily record it is stateful when information, determine that user owns
The advertisement all not browsed to after screen sliding by user.
For example, all search results that server obtains share 10 advertisements, user's screen sliding twice, records when initial
The information of the last item advertisement is：(num3, h1), the information of the last item advertisement recorded after first time screen sliding be (num5,
H2), the information of the last item advertisement recorded after second of screen sliding is (num9, h3), due to the last exhibition of last time screen sliding
9 during the numbering of existing advertisement, then can determine that numbering 1-8 advertisement is browsed to, the advertisement of numbering 10 be not by
What user browsed to, the advertisement for numbering 9, it can be determined according to height and whole height is showed, for example, it is assumed that numbering 9
The whole height of advertisement is H, and when h3/H ratio is more than predetermined threshold value, the advertisement that may indicate that numbering 9 is browsed by user
Arrive, otherwise do not browsed to by user.
S313：Data processing equipment removes the information for the advertisement not browsed to by user in click logs are showed.
Illustrated with above-mentioned example, in correlation technique, show the letter of the advertisement of meeting record number 1~10 in click logs
Breath, and in the present embodiment, it is assumed that the advertisement of numbering 9 is also not browsed to by user, then day is clicked in showing for the application
The information of the advertisement of meeting record number 1~8 in will, no longer include the information of two advertisements below.
So for CTR mod type, its for the advertisement that is presented in above the page, such as numbering 1-8 advertisement, use
Exactly original shows click logs, for the advertisement of the advertisement being presented in below the page, such as numbering 9-10, using filtering
Afterwards show click logs.Separated processing of the CTR mod type to input module, the data using mistake are may indicate that, ensure prediction
Accuracy.
The present embodiment knows the information for showing content by mobile phone, and this shows the information of content to server record, at data
Reason device removes the content not browsed to by user according to the information in click logs are showed, on the one hand due to eliminating portion
Point information can reduce the input data amount of CTR mod type, on the other hand due to eliminating the content not browsed to by user
Information, can avoiding the information using inaccuracy, that improves model estimates accuracy rate as the input data of model.
Fig. 4 is the structural representation for the data processing equipment that another embodiment of the present invention proposes, the device 40 includes showing
Module 41, acquisition module 42 and sending module 43.
Display module 41 is used to show search result, and the search result is that the search term inputted according to user obtains
Arrive；
In similar correlation technique, after user inputs search term in a browser by mobile terminal, it can obtain searching with this
Search result corresponding to rope word.
Search result can include the content of one or at least two, when the content that search result includes is more, due to
The limitation of mobile terminal screen size, once all user generally can not be presented to, it is necessary to which the continuous screen sliding of user obtains more
Information, continue to show the content that last time do not show on the basis of in last time can showing after each screen sliding.
In addition, the screen sliding in the embodiment of the present invention, which is not limited by, touches the screen sliding that screen is realized, also adopted including traditional
With key mode so that showing the continually changing mode of content.
Acquisition module 42 is used to obtain the information for showing content on mobile terminal screen, and the content that shows includes：Initially
Screen shows content, and, the screen after each screen sliding of user shows content；
In the present embodiment, JS (JavaScript) code can be implanted into webpage in mobile terminal to search, monitoring is used
The screen sliding operation at family, to obtain the information for showing content after initially showing and the letter for showing content after each screen sliding
Breath.
Sending module 43 is used to the information for showing content being sent to server, so that described in the server record
Show the information of content, the information for showing content is used to obtain in the search result do not browsed to by user in
Hold, and the information of the content not browsed to by user is removed in click logs are showed.
Wherein it is possible to the information for showing content on mobile terminal screen is sent to by server according to above-mentioned JS codes,
Such as after each screen sliding of user, the information for showing content after corresponding screen sliding is sent to server.Server receives this
It can be recorded, such as be recorded in screen sliding daily record after showing the information of content.In follow-up process, such as carry out CTR modelings
When the information for showing content can be obtained from server, and in the search result according to this shows the acquisition of information of content
The content not browsed to by user, and remove in click logs are showed the letter of the content not browsed to by user
Breath.
Further, the information for showing content can be specially the letter that the last item shows content on mobile terminal screen
Breath, for example, presenting three on mobile terminal screen from top to bottom shows content, Article 3 can only be showed to the information of content
It is sent to server.
Further, the last item shows the information of content and can specifically included：The last item shows the numbering of content,
And the last item shows showing highly for content.
Because search result is provided by server, therefore, server can record the letter of every content in search result
Breath.Wherein, server can by every content according to from top to bottom show order be numbered, for example, server obtain it is more
After bar search result, the putting in order from top to bottom of each bar search result can be determined according to pre-defined algorithm, afterwards server
Numbering from small to large can be carried out to each bar search result in accordance with the order from top to bottom.So, when server receives screen
When the last item shows numbering (such as 3) of content on curtain, it is possible to which the content that shows of numbering (such as 1,2) is before determining
Browsed by user.In addition, can also record the whole height of every search result in server, and in the terminal last
Bar search result is probably all to show, such as only shows a part for whole height, and server can be according to the exhibition
Now height determines whether the last item belongs to the content browsed to by user with whole height.
Showing the information of content on the screen that mobile terminal is sent can record in the server, to be adopted in follow-up process
With, for example, the content that can not browsed to when CTR is modeled according to information determination by user, and then click on day showing
The information of the content not browsed to by user is removed in will, avoids inputting the data of inaccuracy in CTR mod type.
The present embodiment by the information for showing content on mobile terminal screen by being sent to server so that remembers in server
Record has the information that this shows content, and then can be determined in follow-up process according to the information for showing content on mobile terminal screen
The content not browsed to by user, and the information for the content not browsed to by user is removed in click logs are showed, one
Aspect can reduce the input data amount of CTR mod type due to eliminating partial information, on the other hand due to eliminate not by with
The information for the content that family browses to, the information using inaccuracy can be avoided to improve estimating for model as the input data of model
Accuracy rate.
Fig. 5 is a kind of structural representation for data processing equipment that another embodiment of the present invention provides, and the device 50 wraps
Include acquisition module 51, determining module 52 and remove module 53.
Acquisition module 51 is used to obtain the information for showing content on the mobile terminal screen recorded in server, described to show
The information of content is that the server, the search are obtained and be sent to after the mobile terminal shows to search result
Result is that the search term inputted according to user obtains, and the content that shows includes：Initial screen shows content, and, user
Screen after each screen sliding shows content；
The information for showing content can be the information that the last item shows content on mobile terminal screen.
Further, described the last item shows the information of content, including：The last item shows the numbering of content, and
The last item shows showing highly for content.
Determining module 52 is used to show in search result described in the acquisition of information of content according to not to be browsed by user
The content arrived；
For example, the content that shows before described the last item shows the numbering of content is defined as being browsed to by user
Content；And
According to described the last item show content show height determine described the last item show content whether be by with
The content that family browses to.
Further, the height that shows that content can be showed in described the last item shows content with described the last item
When ratio between whole height is more than default threshold value, it is in being browsed to by user to determine that described the last item shows content
Hold.
Further, the default threshold value can be specially 1/4.
Remove the information that module 53 is used to remove the content not browsed to by user in click logs are showed.
Wherein, in correlation technique, the information that every search result can be recorded in click logs is showed, no matter this searches for knot
Whether fruit is browsed to by user.For example, after user inputs a search term, server loads all search corresponding with the search term
As a result, it is assumed that the number of all search results is 8, then showing in correlation technique in click logs can search comprising this 8
The information of hitch fruit, it is exactly positive example when user clicks on certain search result therein, is otherwise negative example.But this 8 search
As a result there may be the result not appeared at all on screen in, accordingly, user can not possibly browse to, and cause data to be forbidden
Really.
And in the present embodiment, the content that is not browsed to for user, the user is removed in click logs are showed not to be had
The information of the content browsed to, avoid being predicted using inaccurate data.
Show the information of content, the exhibition on the mobile terminal screen that the present embodiment is sent by receiving mobile terminal
The information of existing content is obtained after the mobile terminal shows to search result, and the search result is defeated according to user
What the search term entered obtained；According to it is described show the acquisition of information of content described in do not browsed to by user in search result in
Hold；The information of the content not browsed to by user is removed in click logs are showed, on the one hand due to eliminating part
Information can reduce the input data amount of CTR mod type, on the other hand due to eliminating the letter of the content not browsed to by user
Breath, can avoiding the information using inaccuracy, that improves model estimates accuracy rate as the input data of model.
The embodiment of the present invention additionally provides a kind of mobile terminal, and the mobile terminal includes housing, processor, memory, electricity
Road plate and power circuit, wherein, circuit board is placed in the interior volume that housing surrounds, and processor and memory are arranged on circuit board
On；Power circuit, for each circuit or the device power supply for mobile terminal；Memory is used to store executable program code；
The executable program code that processor is stored by reading in memory runs program corresponding with executable program code, with
For performing following steps：S11’：Mobile terminal shows to search result, and the search result is inputted according to user
What search term obtained.
In similar correlation technique, after user inputs search term in a browser by mobile terminal, it can obtain searching with this
Search result corresponding to rope word.
Search result can include the content of one or at least two, when the content that search result includes is more, due to
The limitation of mobile terminal screen size, once all user generally can not be presented to, it is necessary to which the continuous screen sliding of user obtains more
Information, continue to show the content that last time do not show on the basis of in last time can showing after each screen sliding.
In addition, the screen sliding in the embodiment of the present invention, which is not limited by, touches the screen sliding that screen is realized, also adopted including traditional
With key mode so that showing the continually changing mode of content.
S12’：Show the information of content on acquisition for mobile terminal mobile terminal screen, the content that shows includes：Initial screen
Curtain shows content, and, the screen after each screen sliding of user shows content.
In the present embodiment, JS (JavaScript) code can be implanted into webpage in mobile terminal to search, monitoring is used
The screen sliding operation at family, to obtain the information for showing content after initially showing and the letter for showing content after each screen sliding
Breath.
S13’：The information for showing content is sent to server by mobile terminal, so that described in the server record
Show the information of content, the information for showing content is used to obtain in the search result do not browsed to by user in
Hold, and the information of the content not browsed to by user is removed in click logs are showed.
Wherein it is possible to the information for showing content on mobile terminal screen is sent to by server according to above-mentioned JS codes,
Such as after each screen sliding of user, the information for showing content after corresponding screen sliding is sent to server.Server receives this
It can be recorded, such as be recorded in screen sliding daily record after showing the information of content.In follow-up process, such as carry out CTR modelings
When the information for showing content can be obtained from server, and in the search result according to this shows the acquisition of information of content
The content not browsed to by user, and remove in click logs are showed the letter of the content not browsed to by user
Breath.
Further, the information for showing content can be specially the letter that the last item shows content on mobile terminal screen
Breath, for example, presenting three on mobile terminal screen from top to bottom shows content, Article 3 can only be showed to the information of content
It is sent to server.
Further, the last item shows the information of content and can specifically included：The last item shows the numbering of content,
And the last item shows showing highly for content.Because search result is provided by server, therefore, server can be remembered
Record the information of every content in search result.Wherein, server can enter every content according to the order that shows from top to bottom
Line number, for example, after server obtains a plurality of search result, according to pre-defined algorithm can determine each bar search result on to
Under put in order, server can carry out volume from small to large to each bar search result in accordance with the order from top to bottom afterwards
Number.So, when server, which receives the last item on screen, shows numbering (such as 3) of content, it is possible to compiled before determining
The content that shows of number (such as 1,2) is browsed by user.In addition, the entirety of every search result can be also recorded in server
Highly, and the last item search result is probably all to show in the terminal, such as only shows whole height
A part, server can show according to this in height and whole height determine whether the last item belongs to and browsed to by user
Hold.
Showing the information of content on the screen that mobile terminal is sent can record in the server, to be adopted in follow-up process
With, for example, the content that can not browsed to when CTR is modeled according to information determination by user, and then click on day showing
The information of the content not browsed to by user is removed in will, avoids inputting the data of inaccuracy in CTR mod type.
The present embodiment by the information for showing content on mobile terminal screen by being sent to server so that remembers in server
Record has the information that this shows content, and then can be determined in follow-up process according to the information for showing content on mobile terminal screen
The content not browsed to by user, and the information for the content not browsed to by user is removed in click logs are showed, one
Aspect can reduce the input data amount of CTR mod type due to eliminating partial information, on the other hand due to eliminate not by with
The information for the content that family browses to, the information using inaccuracy can be avoided to improve estimating for model as the input data of model
Accuracy rate.
The embodiment of the present invention additionally provides a kind of data processing equipment, and the device includes housing, processor, memory, electricity
Road plate and power circuit, wherein, circuit board is placed in the interior volume that housing surrounds, and processor and memory are arranged on circuit board
On；Power circuit, for each circuit or the device power supply for device；Memory is used to store executable program code；Processing
The executable program code that device is stored by reading in memory runs program corresponding with executable program code, for
Perform following steps：
S21’：Obtain the information for showing content on the mobile terminal screen recorded in server, the letter for showing content
Breath is that the server is obtained and be sent to after the mobile terminal shows to search result, and the search result is root
What the search term inputted according to user obtained, the content that shows includes：Initial screen shows content, and, each screen sliding of user
Screen afterwards shows content.
The information for showing content can be the information that the last item shows content on mobile terminal screen.
Further, described the last item shows the information of content, including：The last item shows the numbering of content, and
The last item shows showing highly for content.
S22’：According to it is described show the acquisition of information of content described in the content that is not browsed to by user in search result.
For example, the content that shows before described the last item shows the numbering of content is defined as being browsed by user
The content arrived；And
According to described the last item show content show height determine described the last item show content whether be by with
The content that family browses to.
Further, the height that shows that content can be showed in described the last item shows content with described the last item
When ratio between whole height is more than default threshold value, it is in being browsed to by user to determine that described the last item shows content
Hold.
Further, the default threshold value can be specially 1/4.
S23’：The information of the content not browsed to by user is removed in click logs are showed.
Wherein, in correlation technique, the information that every search result can be recorded in click logs is showed, no matter this searches for knot
Whether fruit is browsed to by user.For example, after user inputs a search term, server loads all search corresponding with the search term
As a result, it is assumed that the number of all search results is 8, then showing in correlation technique in click logs can search comprising this 8
The information of hitch fruit, it is exactly positive example when user clicks on certain search result therein, is otherwise negative example.But this 8 search
As a result there may be the result not appeared at all on screen in, accordingly, user can not possibly browse to, and cause data not
Accurately.
And in the present embodiment, the content that is not browsed to for user, the user is removed in click logs are showed not to be had
The information of the content browsed to, avoid being predicted using inaccurate data.
Wherein, the executive agent of the present embodiment can be data processing equipment, after can be processed by the device
Show click logs, the click logs that show after the processing can be used in occasions such as CTR modelings.
The present embodiment passes through in being determined not browsed to by user according to the information for showing content on mobile terminal screen
Hold, and the information for the content not browsed to by user is removed in click logs are showed, on the one hand due to eliminating part letter
Breath can reduce the input data amount of CTR mod type, on the other hand due to eliminating the information of the content not browsed to by user,
The information using inaccuracy can be avoided, and as the input data of model, that improves model estimates accuracy rate.
It should be noted that in the description of the invention, term " first ", " second " etc. are only used for describing purpose, without
It is understood that to indicate or implying relative importance.In addition, in the description of the invention, unless otherwise indicated, the implication of " multiple "
It is two or more.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Necessarily refer to identical embodiment or example.Moreover, specific features, structure, material or the feature of description can be any
One or more embodiments or example in combine in an appropriate manner.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changed, replacing and modification.
Claims (16)
- A kind of 1. data processing method, it is characterised in that including：Search result is showed, the search result is that the search term inputted according to user obtains；The information for showing content on mobile terminal screen is obtained, the content that shows includes：Initial screen shows content, and, Screen after each screen sliding of user shows content；The information for showing content is sent to server, so as to show the information of content described in the server record, institute The information for showing content is stated for obtaining the content not browsed in the search result by user, and is showing click logs The middle information for removing the content not browsed to by user；Wherein, the server is searched according to determining pre-defined algorithm The numbering of hitch fruit, in being obtained in the search result according to the numbering for showing content and not browsed to by user Hold.
- 2. according to the method for claim 1, it is characterised in that the information for showing content be mobile terminal screen on most Latter bar shows the information of content.
- 3. according to the method for claim 2, it is characterised in that described the last item shows the information of content, including：The last item shows the numbering of content, to number in showing before described the last item shows the numbering of content Hold the content for being defined as having been browsed to by user；AndThe last item show content show height, so as to according to described the last item show content show height determine described in The last item shows whether content is the content browsed to by user.
- A kind of 4. data processing method, it is characterised in that including：The information for showing content on the mobile terminal screen recorded in server is obtained, the information for showing content is the shifting Dynamic terminal-pair search result is obtained after being showed and is sent to the server, and the search result is inputted according to user Search term obtain, the content that shows includes：Initial screen shows content, and, the screen exhibition after each screen sliding of user Existing content；According to it is described show the acquisition of information of content described in the content that is not browsed to by user in search result；Wherein, it is described Server determines the numbering of the search result according to pre-defined algorithm, so as to be searched according to the numbering acquisition for showing content The content not browsed in hitch fruit by user；The information of the content not browsed to by user is removed in click logs are showed.
- 5. according to the method for claim 4, it is characterised in that the information for showing content be mobile terminal screen on most Latter bar shows the information of content.
- 6. according to the method for claim 5, it is characterised in that described the last item shows the information of content, including：Finally One numbering for showing content, and the last item show the height that shows of content, and the information of content is showed described in the basis The content not browsed in the search result by user is obtained, including：By the content for showing content and being defined as having been browsed to by user before described the last item shows the numbering of content； AndThe height that shows for showing content according to described the last item determines that described the last item shows whether content is clear by user The content look at.
- 7. according to the method for claim 6, it is characterised in that described to show height according to what described the last item showed content Degree determines that described the last item shows whether content is the content browsed to by user, including：When described the last item show content show height and described the last item shows ratio between the whole height of content When value is more than default threshold value, it is the content browsed to by user to determine that described the last item shows content.
- 8. according to the method for claim 7, it is characterised in thatThe default threshold value is 1/4.
- A kind of 9. data processing equipment, it is characterised in that including：Display module, for showing to search result, the search result is that the search term inputted according to user obtains；Acquisition module, the information of content is showed for obtaining on mobile terminal screen, the content that shows includes：Initial screen exhibition Existing content, and, the screen after each screen sliding of user shows content；Sending module, for the information for showing content to be sent into server, so as to show described in the server record The information of content, the information for showing content are used to obtain the content not browsed to by user in the search result, and The information of the content not browsed to by user is removed in click logs are showed；Wherein, the server is according to predetermined Algorithm determines the numbering of the search result, so as to the numbering for showing content according to described obtain in the search result not by The content that user browses to.
- 10. device according to claim 9, it is characterised in that the letter for showing content that the acquisition module obtains Cease the information for showing content for the last item on mobile terminal screen.
- 11. device according to claim 10, it is characterised in that described the last item shows the information of content, including：The last item shows the numbering of content, to number in showing before described the last item shows the numbering of content Hold the content for being defined as having been browsed to by user；AndThe last item show content show height, so as to according to described the last item show content show height determine described in The last item shows whether content is the content browsed to by user.
- 12. a kind of data processing equipment, it is characterised in that also include：Acquisition module, show the information of content on the mobile terminal screen recorded in server for obtaining, it is described to show content Information be that the server, the search result are obtained and be sent to after the mobile terminal shows to search result It is that the search term inputted according to user obtains, the content that shows includes：Initial screen shows content, and, user is each Screen after screen sliding shows content；Determining module, in showing according in search result described in the acquisition of information of content and not browsed to by user Hold；Wherein, the server determines the numbering of the search result according to pre-defined algorithm, so as to according to the volume for showing content Number obtain the content not browsed in the search result by user；Module is removed, for removing the information of the content not browsed to by user in click logs are showed.
- 13. device according to claim 12, it is characterised in that the information for showing content is on mobile terminal screen The last item shows the information of content.
- 14. device according to claim 13, it is characterised in that described the last item shows the information of content, including：Most Latter bar shows the numbering of content, and the last item shows showing highly for content, and the determining module is specifically used for：By the content for showing content and being defined as having been browsed to by user before described the last item shows the numbering of content； AndThe height that shows for showing content according to described the last item determines that described the last item shows whether content is clear by user The content look at.
- 15. device according to claim 14, it is characterised in that the determining module is specifically used for：When described the last item show content show height and described the last item shows ratio between the whole height of content When value is more than default threshold value, it is the content browsed to by user to determine that described the last item shows content.
- 16. device according to claim 15, it is characterised in thatThe default threshold value is 1/4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410198312.8A CN103995852B (en) | 2014-05-12 | 2014-05-12 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410198312.8A CN103995852B (en) | 2014-05-12 | 2014-05-12 | Data processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103995852A CN103995852A (en) | 2014-08-20 |
| CN103995852B true CN103995852B (en) | 2018-01-09 |
Family
ID=51310017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410198312.8A Active CN103995852B (en) | 2014-05-12 | 2014-05-12 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103995852B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462278B (en) * | 2014-11-26 | 2017-12-08 | 百度在线网络技术（北京）有限公司 | The control method and system that content of pages shows |
| CN105528408B (en) * | 2015-12-03 | 2019-03-12 | 百度在线网络技术（北京）有限公司 | Page display method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101369276A (en) * | 2008-09-28 | 2009-02-18 | 杭州电子科技大学 | Evidence obtaining method for Web browser caching data |
| CN101923545A (en) * | 2009-06-15 | 2010-12-22 | 北京百分通联传媒技术有限公司 | Method for recommending personalized information |
| CN103530292A (en) * | 2012-07-02 | 2014-01-22 | 阿里巴巴集团控股有限公司 | Webpage displaying method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7693856B2 (en) * | 2004-06-25 | 2010-04-06 | Apple Inc. | Methods and systems for managing data |
-
2014
- 2014-05-12 CN CN201410198312.8A patent/CN103995852B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101369276A (en) * | 2008-09-28 | 2009-02-18 | 杭州电子科技大学 | Evidence obtaining method for Web browser caching data |
| CN101923545A (en) * | 2009-06-15 | 2010-12-22 | 北京百分通联传媒技术有限公司 | Method for recommending personalized information |
| CN103530292A (en) * | 2012-07-02 | 2014-01-22 | 阿里巴巴集团控股有限公司 | Webpage displaying method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103995852A (en) | 2014-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220094B (en) | Page loading method and device and electronic equipment | |
| CN109819284B (en) | Short video recommendation method and device, computer equipment and storage medium | |
| CN104809154B (en) | The method and device recommended for information | |
| CN109299994B (en) | Recommendation method, device, equipment and readable storage medium | |
| CA2891213C (en) | Providing content recommendation to users on a site | |
| JP6646931B2 (en) | Method and apparatus for providing recommendation information | |
| CN104216965A (en) | Information recommendation method and device | |
| CN104462593A (en) | Method and device for providing user personalized resource message pushing | |
| CN107918622A (en) | Commending contents, methods of exhibiting, client, server and system | |
| CN104407937B (en) | The method and browser of data are loaded in browser | |
| US20190379618A1 (en) | Presenting visual media | |
| CN104766224B (en) | A kind of shopping evaluation display method and system | |
| CN106062743A (en) | Systems and methods for keyword suggestion | |
| CN105224548A (en) | A kind of page display method, device and server | |
| CN107274242A (en) | A kind of Method of Commodity Recommendation based on association analysis algorithm | |
| CN108228720B (en) | Identify method, system, device, terminal and the storage medium of target text content and original image correlation | |
| CN106776860A (en) | One kind search abstraction generating method and device | |
| US20140136527A1 (en) | Apparatus, system, and method for searching for power user in social media | |
| CN103514282A (en) | Method and device for displaying search results of videos | |
| CN104077707B (en) | A kind of optimization method and device for promoting presentation mode | |
| CN112394861A (en) | Page jump method and device, storage medium and electronic device | |
| CN106557556A (en) | A kind of methods of exhibiting of Webpage, device, server and system | |
| CN109961351A (en) | Information recommendation method, device, storage medium and computer equipment | |
| CN108108450B (en) | Image processing method and related equipment | |
| CN109819002B (en) | Data pushing method and device, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |