CN108255886A - The appraisal procedure and device of commending system - Google Patents
The appraisal procedure and device of commending system Download PDFInfo
- Publication number
- CN108255886A CN108255886A CN201611254995.XA CN201611254995A CN108255886A CN 108255886 A CN108255886 A CN 108255886A CN 201611254995 A CN201611254995 A CN 201611254995A CN 108255886 A CN108255886 A CN 108255886A
- Authority
- CN
- China
- Prior art keywords
- user
- access information
- link
- page
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the appraisal procedures and device of a kind of commending system, are related to technical field of data processing, and main purpose is the recommendation effect for solving the problems, such as only to assess commending system by click volume.The present invention main technical schemes be：It obtains User Page access information and user recommends access information；Judge that the User Page access information recommends whether access information matches with the user；If matching, the assessed value based on caused direct after recommendation described in default access order, the User Page access information and the user recommendation access information statistic of user accessing and indirect flow value as the commending system.It is mainly used for the assessment of commending system.
Description
Technical field
The present invention relates to technical field of data processing more particularly to the appraisal procedures and device of a kind of commending system.
Background technology
Gradually abundant with web page contents, major website can all establish commending system in webpage so that user according to
Commending system rapidly and accurately finds the content oneself liked.It is imitated to preferably analyze commending system to the recommendation that user brings
Fruit, developer can carry out recruitment evaluation to commending system.
At present, the click volume that is often generated in commending system by user assesses recommendation effect, for example, when recommending to launch
Measure when being 100, click the click volume that commending system produces 70, then assess launch commending system recommendation effect it is preferable, still,
Commending system, which is assessed, only by click volume obviously can not take into account pushing away for other resources for being generated by commending system
Effect is recommended, this can undoubtedly reduce the accuracy of Evaluated effect.
Invention content
In view of the above problems, it is proposed that the present invention is in order to provide the appraisal procedure and device of a kind of commending system, main mesh
Be that the accuracy of Evaluated effect for solving the problem of to assess commending system by click volume is poor.
By above-mentioned technical proposal, a kind of appraisal procedure of commending system provided by the invention, including：
It obtains User Page access information and user recommends access information, wherein the User Page access information includes using
Generated access data when family accesses Website page, the user recommend access information to include user's access Website page
Generated access data during the recommendation that middle commending system provides；
Judge that the User Page access information recommends whether access information matches with the user；
If matching, access information is recommended based on default access order, the User Page access information and the user
Assessment of the caused direct and indirect flow value as the commending system after recommendation described in statistic of user accessing
Value.
By above-mentioned technical proposal, a kind of apparatus for evaluating of commending system provided by the invention, including：
Acquiring unit recommends access information, wherein the User Page for obtaining User Page access information and user
Access information includes generated access data when user accesses Website page, and the user recommends access information to be visited including user
Generated access data when asking the recommendation that commending system provides in the Website page；
Judging unit, for judging that the User Page access information recommends whether access information matches with the user；
Statistic unit, if access information is recommended to match with the user for the User Page access information, based on pre-
If access order, the User Page access information and the user recommend described in access information statistic of user accessing in recommendation
Assessed value of the caused direct and indirect flow value as the commending system after appearance.
By above-mentioned technical proposal, technical solution provided in an embodiment of the present invention at least has following advantages：
The appraisal procedure and device of a kind of commending system provided in an embodiment of the present invention obtain User Page and access letter first
Breath and user recommend access information, wherein the User Page access information includes generated visit when user accesses Website page
Data are asked, when the user recommends the recommendation that access information is provided including commending system in user's access Website page
Then generated access data judge that the User Page access information recommends whether access information matches with the user,
If matching, access information counting user is recommended based on default access order, the User Page access information and the user
Access assessed value of caused direct after the recommendation and indirect flow value as the commending system.Not only examine
Consider user and access direct flow caused by recommendation, it is also contemplated that the indirect flow as caused by recommendation, from stream
Magnitude angle has carried out accurate assessment to the recommendation effect of commending system, recommends system with existing only assessed by click volume
The scheme of the recommendation effect of system is compared, and undoubtedly greatly improves the accuracy of assessment commending system recommendation effect.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, below the special specific embodiment for lifting the present invention.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this field
Technical staff will become clear.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings：
Fig. 1 shows a kind of flow chart of the appraisal procedure for commending system that inventive embodiments provide；
Fig. 2 shows the flow charts of the appraisal procedure of another commending system that inventive embodiments provide
Fig. 3 shows a kind of block diagram of the apparatus for evaluating for commending system that inventive embodiments provide；
Fig. 4 shows the block diagram of the apparatus for evaluating for another commending system that inventive embodiments provide.
Specific embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
An embodiment of the present invention provides a kind of appraisal procedure of commending system, as shown in Figure 1, the method includes：
101st, it obtains User Page access information and user recommends access information.
Wherein, the User Page access information includes generated access data when user accesses Website page, described
User recommends access information to include generated visit when user accesses the recommendation that commending system provides in the Website page
Ask data, the User Page access information can be ID, temporal information, link URL, the page caused by user to access pages
Title etc., the user recommend access information can be ID caused by recommendation in user to access pages, temporal information,
Link URL, page title etc., the embodiment of the present invention is not specifically limited.
It should be noted that obtain information mode can by way of burying code using JS codes in each website into
Row information acquires, user recommend access information by user by the recommendation of the commending system in accession page generating or
Person user accesses the commending system in commending system after commending system and generates once more by accessing, end user's page access
Information can be multiple User Page access informations caused by multiple pages that user accesses, and user recommends access information can be with
It is identical with User Page access information, can not also be identical, usually, it is in the page accessible by user that user, which recommends access information,
Commending system generation.
For example, User Page access information caused by access Website page can include identity to the user obtained for the first time
Identify ID1,9 points of temporal information 20 minutes, page title film, user caused by user's back-call Website page of acquisition
Page access information can include identity ID1,9 points of temporal information 23 minutes, page title American film, and the user of acquisition the
Access three times User Page access information caused by Website page can include identity ID1,9 points of temporal information 26 minutes,
Page title A Fanda；The user of acquisition accesses user caused by the recommendation of commending system offer in the Website page and pushes away
Identity ID1,9 points of temporal information 26 minutes, page title A Fanda can be included by recommending access information.
102nd, judge that the User Page access information recommends whether access information matches with the user.
Wherein, the matching can be User Page access information and the information whole phase in user's recommendation access information
Together, or part is identical, and the embodiment of the present invention is not specifically limited.
If the 103, matching, recommend to access based on default access order, the User Page access information and the user
Information Statistics user accesses caused direct after the recommendation and indirect flow value as the commending system
Assessed value.
Wherein, the default access order can be time sequencing, can also be page jump sequence, the embodiment of the present invention
It is not specifically limited, the direct flow value directly accesses the flow value of recommendation generation, the indirect flow value for user
After accessing recommendation for user, and continue to access generated flow value after other recommendations or webpage.
For example, if User Page access information includes ID1,26 minutes 9 points of time, page title A Fanda and ID2, time
9 points 30 minutes, page title James Ka Meilong, and user recommends access information to include ID1,26 minutes 9 points of time, page title
The flow value then generated during the statistic of user accessing A Fanda pages during A Fanda and access James Ka Meilong pages when institute
The flow value of generation, and user is accessed into direct flow value caused by the A Fanda pages and accesses James Ka Meilong
Indirect assessed value of the flow value as commending system caused by the page.
The appraisal procedure of a kind of commending system provided in an embodiment of the present invention, by comparing User Page access information with using
Whether family recommends access information identical, if identical, recommends to visit based on default access order, User Page access information and user
Ask that Information Statistics user accesses caused direct and indirect flow value commenting as the commending system after recommendation
Valuation not only allows for user and accesses direct flow caused by recommendation, it is also contemplated that between as caused by the recommendation
Flow is connect, accurate assessment has been carried out to the recommendation effect of commending system from flow value angle, has only passed through click with existing
The scheme of the recommendation effect of amount assessment commending system is compared, and undoubtedly greatly improves the accurate of assessment commending system recommendation effect
Property.
The embodiment of the present invention additionally provides the appraisal procedure of another commending system, as shown in Fig. 2, the method includes：
201st, it obtains User Page access information and user recommends access information.
Wherein, the access data include at least one of：User accesses the Website page or user accesses institute
Time when stating the recommendation that commending system in Website page provides, the link clicked.
This step is identical with the method described in step 101 described in Fig. 1, and which is not described herein again.
202nd, the User Page access information corresponding time, link and the user are recommended into access information pair
Time for answering, link are orderly stored according to default access order.
Wherein, the default access order can be preset time sequence, or it is default to redirect sequentially, it is described orderly
Storage can be to be stored sequentially in time, or be stored according to sequence is redirected, the embodiment of the present invention is not done
It is specific to limit.
It should be noted that storage location can store in the buffer, it can also be stored in local memory, the present invention is real
It applies example to be not specifically limited, when storage can be grouped storage according to certain type, in order to carry out judging that user visits
When asking that page info and user recommend the access information whether to match, orderly page access letter is directly extracted from storage location
Breath improves the efficiency of judgment step, simplifies judgment step, so as to improve the assessment efficiency of commending system.
203a, when judging that the User Page access information corresponding time and the user recommend access information corresponding
Between whether match.
Wherein, the User Page access information corresponding time time phase corresponding with user recommendation access information
With as matching.
It should be noted that when the corresponding time number of User Page access information is multiple, user recommends access information
When the number of corresponding time is 1, need user's recommendation information corresponding time and all User Page access informations
The corresponding time is compared.By judging that the User Page access information corresponding time recommends access information corresponding with user
Whether the time matches, and to extract the matched time, realizes and carries out statistics flow value according to time attribute.
For the embodiment of the present invention, with step 203a step 203b arranged side by side, judge the User Page access information pair
The link answered recommends whether corresponding link of access information matches with the user.
Wherein, access information is corresponding links phase with user recommendation for the corresponding link of the User Page access information
With as matching.
It should be noted that when the corresponding link number of User Page access information is multiple, user recommends access information
When the number of corresponding link is 1, need the corresponding link of user's recommendation information and all User Page access informations
Corresponding link is compared.By judging that the corresponding link of User Page access information recommends access information corresponding with user
Whether link matches, and to extract matched link, realizes that basis redirects sequential attribute and carries out statistics flow value.
For the embodiment of the present invention, the step 204a after step 203a, if the User Page access information is corresponding
In the presence of the time that the time corresponding with user recommendation access information matches in time, then the User Page is accessed and believed
The time that access information corresponding time is recommended to match with the user is ceased in the corresponding time as reference time, and is extracted
The User Page access information corresponding at least one continuous time after the reference time and the reference time.
Wherein, when the default access order accesses the Website page for user or user accesses the Website page
The time sequencing for the recommendation that middle commending system provides, at least one continuous time after the reference time be according to
In the User Page access information corresponding time that time sequencing is stored, the time after reference time.Certainly, click pushes away
The click path recommended after content is deeper, and the effect come by recommendation is smaller, can limit the depth of statistics so as to reduce
The effect that data are exaggerated, and then more truly react the recommendation effect of commending system.Such as a session has 20 pv, it can be with
Limit the flow value for thinking that only 10 pv are just contributed at last before the time of recommendation.
For example, User Page access information is ordered as ID1-13:24、ID1-13:26、ID1-13:38、ID1-13:40,
It is ID1-13 that the user matched, which recommends access information,:26, then by ID1-13:26 are used as reference time, then after extracting reference time
Time ID1-13:26 and ID1-13:38、ID1-13:40 corresponding User Page access informations.By by the matched time
As reference time, and the time corresponding User Page access information after reference time is extracted, accurately to determine user
It accesses recommendation and visits again User Page access information caused by other pages later, could obtain user based on this accesses
Caused directly or indirectly flow value after recommendation.
For the embodiment of the present invention, the step 205a after step 204a determines the reference time and the reference
The corresponding page of User Page access information corresponding at least one continuous time after time, and statistic of user accessing
The flow value generated during all pages.
For example, corresponding at least one continuous time after determining the reference time and the reference time
The corresponding page of User Page access information is respectively ID1-13:26 and ID1-13:38、ID1-13:40, browsing pages are produced
Raw flow is respectively 40,30,60, then the flow value counted be 40+30+60, as 130.Pass through statistic of user accessing reference
The corresponding page of User Page access information corresponding at least one continuous time after time and reference time
Flow value is realized based on reference time, user of the statistics with contributed value access after recommendation it is caused directly with
And indirect flow value is as assessed value.
For the embodiment of the present invention, step 206a after step 205a, by the flow value be configured to it is described recommend be
The assessed value of system.
By the way that flow value to be used as to the assessed value of commending system, avoid carrying out recommendation effect evaluation only according to click volume, carry
The high accuracy of assessment.
For the embodiment of the present invention, if the step 204b, the User Page access information after step 203b are corresponding
Exist in link and recommend access information is corresponding link linking of matching with the user, then the User Page is accessed into letter
It ceases in corresponding link and to recommend access information is corresponding link linking of matching and linked, and extract as reference with the user
The User Page access information with reference to corresponding to link and at least one continuous link with reference to after link.
Wherein, when the default access order accesses the Website page for user or user accesses the Website page
Sequence is redirected after the recommendation that middle commending system provides, it is described continuously to be linked as leading to reference at least one after link
It crosses after clicking the link that current recommendation generates, the link generated successively further through the recommendation in the page, and so on,
It is what adopting consecutive click chemical reaction recommendation generated.
It should be noted that with reference to be linked as to present in the corresponding link of User Page access information with the user
Recommend access information is corresponding to link what the link to match was identified, with reference at least one continuous after link
Link is also the link by after to the commending system in user to access pages, being generated successively further through the recommendation in the page
Be identified, so as to by it is all by access commending system recommendations generate link be used as historical data into
Row storage, when extracting these links, it is only necessary to find corresponding mark, directly extraction identifies corresponding link.
For example, a is linked as the recommendation generation by clicking commending system, in the corresponding pages of current link a
The recommendation that face again taps on commending system in the page corresponds to the link b generated, and page is clicked in the corresponding pages of current link b
The recommendation of commending system corresponds to the link c of generation and non-in the corresponding pages of current link c click the page in face
The content of commending system corresponds to the link d of generation, then is linked a as reference, with reference at least one continuous after link
Link is only link b and link c.By being used as matched link with reference to link, and extract with reference at least one after link
A continuous link, to extract in User Page access information potential user by accessing what is generated after recommendation
Flow value caused by page info.
For the embodiment of the present invention, step 205b after step 204b, determine it is described with reference to link and the reference
The corresponding page of User Page access information corresponding at least one continuous link after link, and statistic of user accessing
The flow value generated during all pages.
For example, referring to ss is linked as, continuous by referring to link generation is linked as ff, ww, hh, determines these links pair
The page s, f, w, the h answered, statistics access flow value caused by s, f, w, h page.By statistic of user accessing with reference to link with
And it is produced during the corresponding page of User Page access information corresponding at least one continuous link with reference to after link
Raw flow value realizes that, by referring to link, the corresponding flow value of user to access pages of the statistics with contributed value, which is used as, to be commented
Valuation.
For the embodiment of the present invention, step 206b after step 205b, by the flow value be configured to it is described recommend be
The assessed value of system.
By the way that flow value to be used as to the assessed value of commending system, avoid carrying out evaluation recommendation effect only according to click volume, carry
The accuracy of height assessment commending system.
For the embodiment of the present invention, specific application scenarios can be as follows, but not limited to this, including：It is adopted by js
The User Page access information that code is got is A-15:16、B-15:20、C-15:36、D-15:40、E-15:45、F-16:00、
G-16:03、H-16:10、I-16:20, these times are stored according to preset time sequence, when user's recommendation information is
C1-15:When 36, judge that User Page access information recommends access information to match with user, and extract reference time 15:After 36
At least one continuous time corresponding to User Page access information namely statistic of user accessing C-15:36 and D-15:
40、E-15:45、F-16:00、G-16:03、H-16:10、I-16:Flow value caused by 20 pages and 90, as commenting
The assessed value of valency system.The appraisal procedure of commending system provided in an embodiment of the present invention, by comparing user to access pages information
Recommend access information whether identical with user, if identical, according to preset time sequence and redirect order statistics user access page
User as another assessed value of commending system other than click volume, is accessed recommendation by flow value caused by face
Caused direct flow is combined consideration with the indirect flow as caused by recommendation, recommends flow value as evaluation
One angle of effect, so as to improve the accuracy of the recommendation effect assessment to commending system.
Further, the specific implementation as method shown in Fig. 1, an embodiment of the present invention provides a kind of commenting for commending system
Device is estimated, as shown in figure 3, described device can include：Acquiring unit 31, judging unit 32, statistic unit 33.
Acquiring unit 31 recommends access information, wherein the user page for obtaining User Page access information and user
Interview asks that information includes generated access data when user accesses Website page, and the user recommends access information to include user
Generated access data when accessing the recommendation that commending system provides in the Website page；The acquiring unit 31 is pushes away
The apparatus for evaluating for recommending system performs the function module for obtaining User Page access information and user's recommendation access information.
Judging unit 32, for judge the User Page access information and the user recommend access information whether
Match；Judging unit 32 is judge the User Page access information and the user recommendation for the apparatus for evaluating execution of commending system
The whether matched function module of access information.
Statistic unit 33, if judging that the User Page access information recommends to access with the user for judging unit 32
Information matches recommend access information statistics to use based on default access order, the User Page access information and the user
Family accesses assessed value of caused direct after the recommendation and indirect flow value as the commending system.Statistics
Unit 33 is to perform for the apparatus for evaluating of commending system and judging that the User Page access information and the user recommend access
After information matches, access information is recommended to count based on default access order, the User Page access information and the user
User accesses caused direct after the recommendation and indirect flow value as the assessed value of the commending system
Function module.
A kind of apparatus for evaluating of commending system provided in an embodiment of the present invention, with it is existing by click volume to commending system
Recommendation effect is compared, and whether the present invention recommends access information identical by comparing user to access pages information with user, if identical,
Based on institute after default access order, User Page access information and user recommendation access information statistic of user accessing recommendation
Assessed value of the direct and indirect flow value brought as the commending system not only allows for user and accesses recommendation
Caused direct flow, it is also contemplated that the indirect flow as caused by recommendation, from flow value angle to commending system
Recommendation effect has carried out accurate assessment, the scheme phase with the existing recommendation effect that commending system is only assessed by click volume
Than undoubtedly greatly improving the accuracy for assessing commending system recommendation effect.
The device embodiment is corresponding with preceding method embodiment, and for ease of reading, present apparatus embodiment is no longer to aforementioned side
Detail content in method embodiment is repeated one by one, it should be understood that the device in the present embodiment can correspond to realize it is aforementioned
Full content in embodiment of the method.
Further, the specific implementation as method shown in Fig. 2, the embodiment of the present invention provide commenting for another commending system
Device is estimated, as shown in figure 4, described device can include：Acquiring unit 41, judging unit 42, statistic unit 43, storage unit
44。
Acquiring unit 41 recommends access information, wherein the user page for obtaining User Page access information and user
Interview asks that information includes generated access data when user accesses Website page, and the user recommends access information to include user
Generated access data when accessing the recommendation that commending system provides in the Website page；Acquiring unit 41 is to recommend
The apparatus for evaluating of system performs the function module for obtaining User Page access information and user's recommendation access information.
Judging unit 42, for judge the User Page access information and the user recommend access information whether
Match；Judging unit 42 is judge the User Page access information and the user recommendation for the apparatus for evaluating execution of commending system
The whether matched function module of access information.
Statistic unit 43, if judging that the User Page access information recommends to access with the user for judging unit 42
Information matches recommend access information statistics to use based on default access order, the User Page access information and the user
Family accesses assessed value of caused direct after the recommendation and indirect flow value as the commending system.Statistics
Unit 43 is to perform for the apparatus for evaluating of commending system and in judging unit 42 judge the User Page access information and the use
After access information matching is recommended at family, recommend to visit based on default access order, the User Page access information and the user
Ask that Information Statistics user accesses caused direct after the recommendation and indirect flow value as the commending system
Assessed value function module.
Further, described device further includes：
Storage unit 44, for the User Page access information corresponding time, link and the user to be recommended
Access information corresponding time, link are orderly stored according to default access order.Storage unit 44 is for commending system
Apparatus for evaluating is performed recommends access information pair by the User Page access information corresponding time, link and the user
The function module that time for answering, link are orderly stored according to default access order.
The judging unit 42, specifically for judging that the User Page access information corresponding time pushes away with the user
Recommend whether the access information corresponding time matches；Judging unit 42 be for commending system apparatus for evaluating execution judge the user
Page access information corresponding time time whether matched function module corresponding with user recommendation access information.
The judging unit 42 is specifically additionally operable to judge the corresponding link of the User Page access information and the user
Recommend whether the corresponding link of access information matches.At this time judging unit 42 be for commending system apparatus for evaluating execution judge institute
State User Page access information it is corresponding link with the user recommendation access information it is corresponding link whether matched function mould
Block.
Further, the statistic unit 43 includes：
Extraction module 4301, if judging exist in the User Page access information corresponding time for judging unit 42
Recommend the time that access information corresponding time matches with the user, then by the User Page access information it is corresponding when
Between in the user recommend time that access information corresponding time matches as reference time, and when extracting the reference
Between and the reference time after at least one continuous time corresponding to User Page access information；Extraction module
If 4301 be for commending system apparatus for evaluating perform judging unit 42 judge the User Page access information corresponding time
During the time that the middle presence time corresponding with user recommendation access information matches, by the User Page access information pair
Recommend with the user time that access information corresponding time matches in the time answered as reference time, and described in extraction
The work(of the User Page access information corresponding at least one continuous time after reference time and the reference time
It can module.
Determining module 4302, it is at least one continuous after the reference time and the reference time for determining
The corresponding page of User Page access information corresponding to time, and the flow generated during all pages described in statistic of user accessing
Value；Determining module 4302 is for after the determining reference time of apparatus for evaluating execution of commending system and the reference time
At least one continuous time corresponding to the corresponding page of User Page access information, and described in statistic of user accessing own
The function module of the flow value generated during the page.
Configuration module 4303, for the flow value to be configured to the assessed value of the commending system.Configuration module 4303
It is to perform the function module of the assessed value that the flow value is configured to the commending system for the apparatus for evaluating of commending system.
The extraction module 4301, if being additionally operable to judging unit 42 judges the corresponding link of the User Page access information
It is middle exist recommend access information is corresponding to link linking of matching with the user, then by the User Page access information pair
Recommend with the user access information is corresponding link linking of matching as with reference to linking, and described in extraction in the link answered
With reference to the User Page access information corresponding to link and at least one continuous link with reference to after link；Extraction
If module 4301 be for commending system apparatus for evaluating perform judging unit 42 judge that the User Page access information is corresponding
In link exist with the user recommend access information it is corresponding link match when linking, by the User Page access letter
It ceases in corresponding link and to recommend access information is corresponding link linking of matching and linked, and extract as reference with the user
The User Page access information with reference to corresponding to link and at least one continuous link with reference to after link
Function module.
The determining module 4302 is additionally operable to determine described with reference to link and described with reference at least one after link
The corresponding corresponding page of User Page access information of continuous link, and generated during all pages described in statistic of user accessing
Flow value；Determining module 4302 is the determining reference link of apparatus for evaluating execution and the reference strand for commending system
The corresponding page of User Page access information corresponding at least one continuous link after connecing, and statistic of user accessing institute
State the function module of the flow value generated during all pages.
The configuration module 4303 is additionally operable to the flow value being configured to the assessed value of the commending system.Mould is configured
Block 4303 is to perform the function of the assessed value that the flow value is configured to the commending system for the apparatus for evaluating of commending system
Module.
The apparatus for evaluating of commending system provided in an embodiment of the present invention is pushed away by comparing User Page access information with user
Whether identical access information is recommended, if identical, according to preset time sequence and produced by redirecting order statistics user to access pages
Flow value, as another assessed value of commending system other than click volume, user is accessed caused by recommendation
Direct flow is combined consideration with the indirect flow as caused by recommendation, using flow value as the one of evaluation recommendation effect
A angle, so as to improve the accuracy of the recommendation effect assessment to commending system.
The device embodiment is corresponding with preceding method embodiment, and for ease of reading, present apparatus embodiment is no longer to aforementioned side
Detail content in method embodiment is repeated one by one, it should be understood that the device in the present embodiment can correspond to realize it is aforementioned
Full content in embodiment of the method.
The apparatus for evaluating of the commending system includes processor and memory, above-mentioned acquiring unit, judging unit and statistics
Unit etc. as program unit storage in memory, by processor perform above procedure unit stored in memory Lai
Realize corresponding function.
Comprising kernel in processor, gone in memory to transfer corresponding program unit by kernel.Kernel can set one
Or more, it solves to assess commending system by click volume by adjusting kernel parameter, the standard of obtained Evaluated effect
The problem of really property is poor.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM), memory includes at least one deposit
Store up chip.
Present invention also provides a kind of computer program products, first when being performed on data processing equipment, being adapted for carrying out
The program code of beginningization there are as below methods step：It obtains User Page access information and user recommends access information, wherein described
User Page access information includes generated access data when user accesses Website page, and the user recommends access information packet
Include generated access data when user accesses the recommendation that commending system provides in the Website page；Judge the user
Page access information recommends whether access information matches with the user；If matching, based on default access order, the user page
Face access information and the user recommend after recommendation described in access information statistic of user accessing it is caused directly and
Indirect assessed value of the flow value as the commending system.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware can be used in the application
Apply the form of example.Moreover, the computer for wherein including computer usable program code in one or more can be used in the application
The computer program production that usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is with reference to the flow according to the method for the embodiment of the present application, equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that it can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
The processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that the instruction performed by computer or the processor of other programmable data processing devices is generated for real
The device of function specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction generation being stored in the computer-readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps are performed on calculation machine or other programmable devices to generate computer implemented processing, so as in computer or
The instruction offer performed on other programmable devices is used to implement in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, CD-ROM read-only memory (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, available for storing the information that can be accessed by a computing device.It defines, calculates according to herein
Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It these are only embodiments herein, be not limited to the application.To those skilled in the art,
The application can have various modifications and variations.All any modifications made within spirit herein and principle, equivalent replacement,
Improve etc., it should be included within the scope of claims hereof.
Claims (10)
1. a kind of appraisal procedure of commending system, which is characterized in that including：
It obtains User Page access information and user recommends access information, wherein the User Page access information is visited including user
Ask generated access data during Website page, the user recommends access information to include pushing away in user's access Website page
Generated access data when the recommendation of system offer is provided；
Judge that the User Page access information recommends whether access information matches with the user；
If matching, recommends access information to count based on default access order, the User Page access information and the user
User accesses assessed value of caused direct after the recommendation and indirect flow value as the commending system.
2. according to the method described in claim 1, it is characterized in that, the access data include at least one of：User visits
It asks the time when Website page or user access the recommendation that commending system provides in the Website page, click
Link.
3. according to the method described in claim 2, it is characterized in that, the acquisition User Page access information and user recommend to visit
After asking information, the method further includes：
By the User Page access information corresponding time, link and the user recommend access information corresponding time,
Link is orderly stored according to default access order；
It is described judge the User Page access information and the user recommend access information whether match including：
Judge the User Page access information corresponding time and the user recommend access information corresponding time whether
Match；Or
Judge the User Page access information it is corresponding link with the user recommendation access information it is corresponding link whether
Match.
4. according to the method described in claim 3, it is characterized in that, the default access order accesses the website pages for user
Face or user access in the Website page time sequencing for the recommendation that commending system provides and
If the matching, access information is recommended based on default access order, the User Page access information and the user
Assessment of the caused direct and indirect flow value as the commending system after recommendation described in statistic of user accessing
Value includes：
Recommend the corresponding time phase of access information with the user if existing in the User Page access information corresponding time
The matched time, then will in the User Page access information corresponding time with the user recommend access information it is corresponding when
Between time for matching as reference time, and extract at least one company after the reference time and the reference time
User Page access information corresponding to the continuous time；
Determine the User Page corresponding at least one continuous time after the reference time and the reference time
The corresponding page of access information, and the flow value generated during all pages described in statistic of user accessing；
The flow value is configured to the assessed value of the commending system.
5. according to the method described in claim 3, it is characterized in that, the default access order accesses the website pages for user
Face or user access after the recommendation that commending system provides in the Website page redirect sequence and
If the matching, access information is recommended based on default access order, the User Page access information and the user
Assessment of the caused direct and indirect flow value as the commending system after recommendation described in statistic of user accessing
Value includes：
Recommend that access information is corresponding to link phase with the user if existing in the corresponding link of the User Page access information
Matched link then will recommend the corresponding chain of access information in the corresponding link of the User Page access information with the user
It connects the link to match to be used as with reference to link, and extracts the reference link and at least one company with reference to after link
User Page access information corresponding to continuous link；
Determine the User Page with reference to corresponding to link and at least one continuous link with reference to after link
The corresponding page of access information, and the flow value generated during all pages described in statistic of user accessing；
The flow value is configured to the assessed value of the commending system.
6. a kind of apparatus for evaluating of commending system, which is characterized in that including：
Acquiring unit recommends access information, wherein the User Page accesses for obtaining User Page access information and user
Information includes generated access data when user accesses Website page, and the user recommends access information to include user's access institute
Generated access data when stating the recommendation that commending system provides in Website page；
Judging unit, for judging that the User Page access information recommends whether access information matches with the user；
Statistic unit, if access information is recommended to match with the user for the User Page access information, based on default visit
After asking that sequence, the User Page access information and the user recommend recommendation described in access information statistic of user accessing
Assessed value of the caused direct and indirect flow value as the commending system.
7. device according to claim 6, which is characterized in that the access data include at least one of：User visits
It asks the time when Website page or user access the recommendation that commending system provides in the Website page, click
Link.
8. device according to claim 7, which is characterized in that described device further includes：Storage unit, for by the use
Family page access information corresponding time, link and the user recommend access information corresponding time, link according to default
Access order is orderly stored；
The judging unit, specifically for judging that the User Page access information corresponding time recommends to access with the user
Whether the information corresponding time matches；Or
The judging unit, specifically for judging that the corresponding link of the User Page access information is recommended to access with the user
Whether the corresponding link of information matches.
9. device according to claim 8, which is characterized in that the statistic unit includes：
Extraction module, if recommending access information with the user for existing in the User Page access information corresponding time
The time that the corresponding time matches then will recommend to access in the User Page access information corresponding time with the user
The time that the information corresponding time matches as reference time, and after extracting the reference time and the reference time
At least one continuous time corresponding to User Page access information；
Determining module, for determining that at least one continuous time institute after the reference time and the reference time is right
The corresponding page of User Page access information answered, and the flow value generated during all pages described in statistic of user accessing；
Configuration module, for the flow value to be configured to the assessed value of the commending system.
10. device according to claim 8, which is characterized in that
The extraction module, if recommending to access with the user in the corresponding link of the User Page access information existing
Information is corresponding to link the link to match, then will recommend in the corresponding link of the User Page access information with the user
Access information is corresponding to be linked the link that matches and is used as with reference to linking, and extract described with reference to link and described with reference to link
The User Page access information corresponding at least one continuous link later；
The determining module, for determining at least one continuous link with reference to after link and the reference link
The corresponding corresponding page of User Page access information, and the flow value generated during all pages described in statistic of user accessing；
The configuration module, for the flow value to be configured to the assessed value of the commending system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611254995.XA CN108255886B (en) | 2016-12-29 | 2016-12-29 | Evaluation method and device of recommendation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611254995.XA CN108255886B (en) | 2016-12-29 | 2016-12-29 | Evaluation method and device of recommendation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108255886A true CN108255886A (en) | 2018-07-06 |
| CN108255886B CN108255886B (en) | 2021-08-13 |
Family
ID=62722031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611254995.XA Active CN108255886B (en) | 2016-12-29 | 2016-12-29 | Evaluation method and device of recommendation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108255886B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948056A (en) * | 2019-03-19 | 2019-06-28 | 安庆师范大学 | A kind of appraisal procedure and device of recommender system |
| CN110765308A (en) * | 2019-09-27 | 2020-02-07 | 上海麦克风文化传媒有限公司 | Evaluation method and system of audio album recommendation system |
| CN111061956A (en) * | 2019-12-24 | 2020-04-24 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN111797310A (en) * | 2020-06-19 | 2020-10-20 | 北京达佳互联信息技术有限公司 | Behavior review method and device, electronic equipment and storage medium |
| WO2020224515A1 (en) * | 2019-05-08 | 2020-11-12 | 阿里巴巴集团控股有限公司 | Data processing method, system and apparatus |
| CN112784032A (en) * | 2021-01-28 | 2021-05-11 | 上海明略人工智能(集团)有限公司 | Conversation corpus recommendation evaluation method and device, storage medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120143718A1 (en) * | 2010-12-03 | 2012-06-07 | Choicestream, Inc. | Optimization of a web-based recommendation system |
| CN104123321A (en) * | 2013-04-28 | 2014-10-29 | 百度在线网络技术（北京）有限公司 | Method and device for determining recommended pictures |
| CN104732338A (en) * | 2015-03-06 | 2015-06-24 | 安徽师范大学 | Method for evaluating services based on fuzzy theory in cloud environment |
| CN105005918A (en) * | 2015-07-24 | 2015-10-28 | 金鹃传媒科技股份有限公司 | Online advertisement push method based on user behavior data and potential user influence analysis and push evaluation method thereof |
| CN105069099A (en) * | 2015-08-06 | 2015-11-18 | 北京奇艺世纪科技有限公司 | Information recommendation method and system |
| CN106228392A (en) * | 2016-07-15 | 2016-12-14 | 北京小米移动软件有限公司 | Evaluation management method and device |
-
2016
- 2016-12-29 CN CN201611254995.XA patent/CN108255886B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120143718A1 (en) * | 2010-12-03 | 2012-06-07 | Choicestream, Inc. | Optimization of a web-based recommendation system |
| CN104123321A (en) * | 2013-04-28 | 2014-10-29 | 百度在线网络技术（北京）有限公司 | Method and device for determining recommended pictures |
| CN104732338A (en) * | 2015-03-06 | 2015-06-24 | 安徽师范大学 | Method for evaluating services based on fuzzy theory in cloud environment |
| CN105005918A (en) * | 2015-07-24 | 2015-10-28 | 金鹃传媒科技股份有限公司 | Online advertisement push method based on user behavior data and potential user influence analysis and push evaluation method thereof |
| CN105069099A (en) * | 2015-08-06 | 2015-11-18 | 北京奇艺世纪科技有限公司 | Information recommendation method and system |
| CN106228392A (en) * | 2016-07-15 | 2016-12-14 | 北京小米移动软件有限公司 | Evaluation management method and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948056A (en) * | 2019-03-19 | 2019-06-28 | 安庆师范大学 | A kind of appraisal procedure and device of recommender system |
| CN109948056B (en) * | 2019-03-19 | 2022-12-09 | 安庆师范大学 | Evaluation method and device of recommendation system |
| WO2020224515A1 (en) * | 2019-05-08 | 2020-11-12 | 阿里巴巴集团控股有限公司 | Data processing method, system and apparatus |
| CN110765308A (en) * | 2019-09-27 | 2020-02-07 | 上海麦克风文化传媒有限公司 | Evaluation method and system of audio album recommendation system |
| CN111061956A (en) * | 2019-12-24 | 2020-04-24 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| US11412070B2 (en) | 2019-12-24 | 2022-08-09 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for generating information |
| CN111797310A (en) * | 2020-06-19 | 2020-10-20 | 北京达佳互联信息技术有限公司 | Behavior review method and device, electronic equipment and storage medium |
| CN112784032A (en) * | 2021-01-28 | 2021-05-11 | 上海明略人工智能(集团)有限公司 | Conversation corpus recommendation evaluation method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108255886B (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108255886A (en) | The appraisal procedure and device of commending system | |
| CN106250987B (en) | A kind of machine learning method, device and big data platform | |
| CN106503022B (en) | Method and device for pushing recommendation information | |
| CN109286825A (en) | Method and apparatus for handling video | |
| Mans et al. | Business process mining success | |
| CN106651416A (en) | Analyzing method and analyzing device of application popularization information | |
| CN107766469A (en) | A kind of method for caching and processing and device | |
| JP2013117830A (en) | Recommendation device, recommendation system, recommendation method and program | |
| CN109753603A (en) | Products Show information displaying method, device, computer equipment and storage medium | |
| CN105868254A (en) | Information recommendation method and apparatus | |
| CN107562613A (en) | Program testing method, apparatus and system | |
| CN106570013A (en) | Method and device for processing page access data | |
| CN106843820A (en) | Code process method and apparatus | |
| CN109063502A (en) | Data encryption, data analysing method and device | |
| CN108134760A (en) | Website monitoring data acquisition methods and device | |
| CN106126629A (en) | A kind of master data management method and system based on live industry | |
| CN109472017A (en) | Obtain the method and device that judgement document the court to be generated thinks section relevant information | |
| CN108156118A (en) | User Identity method and device | |
| CN108733694A (en) | Method and apparatus are recommended in retrieval | |
| CN110309295A (en) | Generate the method and device that judgement document finds out section through trying | |
| Linden | Using group‐based trajectory modelling to enhance causal inference in interrupted time series analysis | |
| CN112910890B (en) | Anonymous network flow fingerprint identification method and device based on time convolution network | |
| RU2014126762A (en) | METHOD FOR PRESENTING SEARCH RESULTS IN ACCORDANCE WITH SEARCH REQUEST ON THE INTERNET NETWORK | |
| CN110209582A (en) | The statistical method and device of code coverage, electronic equipment, storage medium | |
| CN110399284A (en) | A kind of test case writes and executes method and device |
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 | ||
| CB02 | Change of applicant information |
Address after: 100083 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: Beijing Guoshuang Technology Co.,Ltd. Address before: 100086 Beijing city Haidian District Shuangyushu Area No. 76 Zhichun Road cuigongfandian 8 layer A Applicant before: Beijing Guoshuang Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |