CN104871193A - Generating application recommendations based on user feedback - Google Patents

Generating application recommendations based on user feedback Download PDF

Info

Publication number
CN104871193A
CN104871193A CN201280074559.8A CN201280074559A CN104871193A CN 104871193 A CN104871193 A CN 104871193A CN 201280074559 A CN201280074559 A CN 201280074559A CN 104871193 A CN104871193 A CN 104871193A
Authority
CN
China
Prior art keywords
application
suggestion
feedback score
index
association
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
Application number
CN201280074559.8A
Other languages
Chinese (zh)
Other versions
CN104871193B (en
Inventor
I·马哈尼奥克
B·梅塔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Google LLC
Original Assignee
Google LLC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Google LLC filed Critical Google LLC
Publication of CN104871193A publication Critical patent/CN104871193A/en
Application granted granted Critical
Publication of CN104871193B publication Critical patent/CN104871193B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • 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

Abstract

Methods, systems and apparatus, including computer programs encoded on a computer storage medium for receiving a search log, the search log comprising event data associated with a plurality of suggested applications available through an application marketplace; for each suggested application, determining a feedback score based on the event data to provide a plurality of feedback scores; storing the plurality of feedback scores in an index of suggested applications, a feedback score being associated with a suggested application within the index of suggested applications; receiving a request to display one or more suggested applications associated with a selected application; identifying a set of suggested applications based on the selected application and the index of suggested applications; and transmitting instructions to a client computing device to display suggested applications of the set of suggested applications in an order based on respective feedback scores.

Description

Generate application based on user feedback to recommend
Technical field
Present disclosure relates in application market based on the one or more application of selected application proposal.
Background technology
Mobile computing device (or referred to as " mobile device ") can run various software application, and these software application are expanded existing equipment ability and added new ability.Usually can obtain very eurypalynous application, such as the application of acquisition of information, for the application that communicates and the application for amusement.Each application can be created by mobile device manufacturers and/or third party's (such as application developer), and can be installed in advance by manufacturer, or can be downloaded by equipment user and be installed.
User can by browse useful application catalogue, find new application by the interface associated with application on site market.In addition, usually by information that advertisement, industry summary, " top ten " and " the best " list and being recommended by public praise can be obtained about new application.When understanding new application, user can obtain, installs and use the full release of this application, or user can access the beta release of this application, the beta release of this application allows user in purchase or attempts this application when not buying this application.Finally, user can retain this application, upgrades this application (such as from beta release to full release), and can delete the application no longer wanted.
Summary of the invention
The novelty aspect of the theme described in this instructions can realize by method, and these methods comprise following action: receive search daily record, this search daily record comprises and the event data by the obtainable multiple suggestion association of application market; For each suggestion application, based on this event data determination feedback score to provide multiple feedback score; The plurality of feedback score is stored in the index of suggestion application, the suggestion association in the index that feedback score and this suggestion are applied; Receive in order to the one or more requests of advising apply of display with selected association; Based on selected application and this suggestion application index identify suggestion application set; And to client computing device transfer instruction to show the suggestion application in the set of this suggestion application according to the order of marking based on respective feedback.
The computer program that other embodiments of these aspects comprise the system of the correspondence of the action being configured to manner of execution, device and encode on computer memory device.
These and other embodiments can comprise the one or more features in following characteristics separately alternatively.Such as, the feedback score for corresponding suggestion application is determined based on the event associated with this respective application; This event comprises the installation of click and this suggestion application of applying this suggestion; This event is just being provided in the list of suggestion application based on this corresponding suggestion application and is being generated; Feedback score for corresponding suggestion application is determined based on the click number of suggestion association corresponding to this and the installation number of suggestion association corresponding to this; This feedback score is also determined based at least one item installed in multiplier, position multiplier and payment applications multiplier; This installation multiplier is applied to described installation number and is greater than one; Determine that this corresponding suggestion is applied as payment applications, this payment applications multiplier is provided as the value being greater than, and apply this payment applications multiplier to this installation number; Determine that this corresponding suggestion application is not payment applications, this payment applications multiplier is provided as the value equaling, and applies this payment applications multiplier to this installation number; For each click clicked in number, the position that this position multiplier is applied in the list of suggestion application based on this corresponding suggestion is determined; For each installation in this installation number, the position that this position multiplier is applied in the list of suggestion application based on this corresponding suggestion is determined.
The various embodiments of present disclosure can have the one or more features in following characteristics.Such as, the subjective sensation by catching the correlativity to two methods expressed by user generates and the sequencing table applying relevant application.Additive method can consider the data that application developer provides; And analyze end user's feedback to regulate sort algorithm.Therefore, user more easily finds the application that they may like, and produces the installation sum of larger application.
In the following drawings and the one or more embodiments of the detail setting forth the theme described in this instructions in describing.According to description, accompanying drawing and claim, other possible features of theme, aspect and advantage will become clear.
Accompanying drawing explanation
Fig. 1 describes the example system that can perform the realization of present disclosure.
Fig. 2 describes the example mobile device for showing the application being identified as suggestion application in view of selected application.
Fig. 3 comprises the block diagram for the system in view of the selected exemplary components that should be used for by one or more application identities being suggestion application.
Fig. 4 is the process flow diagram of the instantiation procedure that can be performed according to the realization of present disclosure.
Fig. 5 is the process flow diagram of diagram for the instantiation procedure of list of application.
Fig. 6 is that diagram is for showing the process flow diagram of the instantiation procedure of the application being identified as suggestion application in view of selected application.
Fig. 7 is the block diagram of the system comprised for identifying the exemplary components for the application advised based on user feedback.
Fig. 8 is the process flow diagram of diagram for identifying the instantiation procedure for the application advised based on user feedback.
In various figures, similar Reference numeral represents similar element.
Embodiment
This instructions describes and is used for system and method that one or more application identities is relevant to selected application in application market.In some implementations, the user of computing equipment (such as mobile computing device) can search for and can perform application in application market, and can download and install these application on the computing device.But it is very loaded down with trivial details to find other application that can be proposed in view of selected application that user can find to search for application market usually.
Degree of correspondence between selected application and intended application is based on inquiry log data and apply metadata.If the degree of correspondence between selected application and intended application is enough, then in view of selected suggestion (such as user may the be interested) intended application that should be used for.Such as, the application that may be used for same or similar object can should be used for suggestion in view of other, even if do not have other direct correlation (such as identical developer) between these application.
In some implementations, user can by inputted search item in the inquiry field that provides in the user interface of application market be searched through application market can application.Can to the inquiry of this application market transmission gained, this search useful application is to identify the one or more application corresponding with inquiry.This application market can return the list of one or more application to computing equipment.User then can from the list that computing equipment shows selective gist.Select in response to this user, the information relevant with selected application can be presented via computing equipment to user.In addition, as discussed in further detail below, also can show the list of the one or more application be proposed in view of selected application to user in response to this user selects.This user can start the installation of selected application on the computing device.
The information relevant to search inquiry, the selection being used for the application showing details, application installation, application content, application sequence etc. can be stored in a database.This information can illustrate search inquiry, installation to the multiple users in the request of details and multiple equipment.As discussed in further detail below, application message can be processed should be used for application identities as suggestion application in view of selected.In application market, the suggestion application suggestion be shown as in view of selected application can be applied.
As discussed in detail further herein, the user interface with suggestion application can be monitored and apply in view of selected application is identified as suggestion to affect which application further.In some implementations, user interface is provided as the end user's feedback about suggestion application.In some instances, end user's feedback can be provided as suggestion application shown in the list that the suggestion in view of selected application apply click and when occurring clicking suggestion be applied in the position in list that suggestion applies.In some instances, end user's feedback can be provided as suggestion application shown in the list that the suggestion in view of selected application apply installation and when starting to install suggestion be applied in the position in list that suggestion applies.
Fig. 1 is the figure of the example system 100 of the realization that can perform present disclosure.System 100 comprises computing equipment 102A to 102F, and this computing equipment communicates with server system 104 each via network 106.Each computing equipment in computing equipment 102A to 102F comprises the user 108A to 108F of association respectively.Network 116 can comprise the large computer network of the mobile computing device connecting any number, fixing computing equipment and server system, such as LAN (Local Area Network) (LAN), wide area network (WAN), the Internet, cellular network or its combination.Server system 104 comprises one or more computing equipment 110 and one or more machine-readable storage storehouse or database 112.
In example system 100, computing equipment 102A to 102D is illustrated as mobile computing device, and computing equipment 102E is illustrated as desktop computing equipment and computing equipment 102F is illustrated as lap-top computing devices.But, be to be understood that, computing equipment 102A to 102F can comprise the computing equipment of any type separately, any two or more combination in such as desktop PC, laptop computer, handheld computer, personal digital assistant (PDA), cell phone, network home appliance, camera, smart phone, Enhanced GPRS (EGPRS) mobile phone, computation sheet equipment, media player, navigator, electronic mail equipment, game machine or these data processing equipments or other data processing equipments.
Computing equipment 102A to 102F makes corresponding user 108A to 108F can be mutual with application market.Example application market comprises the Google Play (being called Android Market in the past) that Google company provides.In some implementations, this application market can be included in the upper trustship of one or more server (such as computing equipment 102A to 102F) and use the website that computing equipment (such as computing equipment 102A to 102F) visits.In some implementations, this application market may be provided in the upper execution of computing equipment (such as computing equipment 102A to 102F) and obtains the application of application message from one or more server (such as server system 104).
Application market can carry out advertisement to the application that can be used for installing in the one or more computer equipments download in computing equipment 102A to 102F and the one or more computer equipments in computing equipment 102A to 102F.Such as, the user 108A of computing equipment 102A can with application market alternately to check and/or to find interested application.Such as, user 102A can inquire about to application market inputted search.This search inquiry can be processed (such as by one or more server system trustship, or providing data to application market) to identify the one or more application corresponding with search inquiry.Apply corresponding information can be transferred to computing equipment 102A for showing to user 108A with one or more.As another example, application market can show various application (such as nearest application, the application, best free application, best payment applications, application-specific, amusement, yield-power, business, education etc. of downloading at most).In response to selection particular types, apply corresponding information with one or more in this concrete kind and can be transferred to computing equipment 102A for showing to user 108A.
Continue above example, user 108A can select application-specific to check the extra details relevant with this application and/or to apply to download to computing equipment 102A and to install from the application of one or more display.Such as, in response to user's input, the extra details relevant with selected application can be shown.The example of extra details can comprise the description of application, user's sequence of application, user comment, application screen sectional drawing and be confirmed as other relevant with selected application to be applied.As discussed in further detail herein, the realization of present disclosure relates to determines whether two methods is correlated with.
Fig. 2 describes the example mobile device 200 for showing the application being identified as suggestion application in view of selected application.This mobile device 200 can be corresponding with the computing equipment 102A to 102D of Fig. 1.Mobile device 200 comprises display 202, tracking ball 204 and navigation button 206a to 206d.Display 202 display graphics user interface 208.This GUI 208 provides the application that the storer of user (such as user 108A to 108D) and operating system and mobile device 200 stores to carry out mutual interface.Example operating system comprises the Android Operating System that Google company provides.User can with GUI 208 alternately with store in the storer browsing mobile device 200 and the list of executable application on mobile device 200, with select the application for being performed by the processor of mobile device 200, with apply the term of execution provide input etc. to application.
The user of mobile device 200 browses GUI208 via display 202, tracking ball 204 and navigation button 206a to 206d and/or other input medias (the such as sense of hearing and/or sense of touch).In some implementations, display 202 is touch-screen display.Tracking ball 204 controls can as the cursor of the part of GUI 208 for selecting item shown on GUI 208.Navigation button 206a to 206d depends on specific operation system that mobile device 200 stores and has various realization.In some implementations, navigation button 206a provides " previously " button current state of GUI 208 being back to the original state of GUI 208; Navigation button 206b provide menu function; Navigation button 206c provides the main interface function making GUI 208 enter " main screen ", and navigation button 206d provides function of search.
Mobile device 200 stores application market application.The application of this application market may be provided in client side application, and this client side application can communicate with the application market being provided as (such as performing on one or more server system) backend application.The application of this application market provides the list of the application that can be used for downloading to mobile device 200 and installing on mobile device 200 to user.Particularly, user carrys out the application of selective gist market by browsing GUI 208.Any mode that user can be provided by the operating system that mobile device 200 stores carrys out selective gist market application (such as initiating application market application to be used for performing).When user's selective gist market is applied, the application of this application market can show inquiry field in GUI 208.User can to inputted search item in inquiry field with generated query.The application-specific of more information that this search terms can go for user (relevant with may installing of the application be included on mobile device 200) is relevant.In some implementations, search terms is relevant with application-specific, such as relevant with Google Earth Application search terms " Google Earth ".In some implementations, search terms can be relevant with the kind of the interested application of user, such as comprises the search terms of " shopping ", and wherein multiple application can be relevant to this search terms.Multiple application can comprise such as " Google Shopper " and " AmazonMobile " etc.
User to inquiring about in field after inputted search item, application market application returns to the interface after renewal to GUI 208.Particularly, in response to inquiry, GUI 208 can comprise be identified as the application corresponding with search terms list as Search Results.User can from Search Results selective gist.In response to the selection of application-specific, the interface after the application of this application market provides the renewal relevant with selected application 209 to GUI 208.Particularly, GUI 208 can comprise application interface 210, and this application interface 210 comprises selected application 209 specific information.
In some implementations, the list of application can be inputted in response to other users by GUI 208 and show, and/or can present the default list of application.Such as, when on mobile device 200, selective gist market is applied, can show welcome screen, this welcome screen comprises the default list of application.The default list of this application can comprise such as search application at most or install application at most.In addition, the list of this application can show based on kind.Such as, user can select particular types (such as news, books, amusement), and the list of the application corresponding with selected kind can be shown.Application can be selected from any list of application, otherwise presents on GUI 208.
Application interface 210 comprises application head part 212, mark part 214 and content part 216.Head part 212 comprises selected application 209 specific summary infos.The specific information of this application can comprise such as Apply Names 218, application developer 220, application icon 222, installment state 224 and sequence 226.Installment state 224 comprises whether being arranged on information relevant on mobile device 200 with selected application 209 is current.In some implementations, sequence 226 is the sequences provided by the user of this mobile device 200 when selected application 209 is current or be previously installed on mobile device 200.In some implementations, sequence 226 is the sequence mean value that the multiple users on multiple mobile device provide.
Mark part 214 comprises such as about label 228, comment label 230 and similar (or suggestion) label 232.When the user of the label mobile device 200 of mark part 214 chooses, the content relevant to selected label is displayed in content part 216.When selected, about the content relating to the description relevant with selected application 209 in label 228 displaying contents part 216.This description is provided by the developer of selected application 209.When selected, relate to the content of the comment that other users provide in comment label 230 displaying contents part 216, these other users have the previous experiences using selected application 209 on corresponding mobile device.This comment can comprise text, audio frequency, video etc.In addition, comment can comprise the sequence of selected application 209.When selected, in similar (or suggestion) label 232 displaying contents part 216, apply the relevant content of list of 236 with the suggestion in view of selected application 209.Particularly, as discussed in further detail below, similar tags 232 shows the list 234 of the suggestion application 236 being identified as suggestion in view of selected application 209.List 234 may be provided in scrollable list.The user of mobile device 200 can the scroll list 234 vertically, makes list 236 show other related application 236 while the related application 236 hiding current display.The list 234 of suggestion application 236 can comprise the specific information of application of each suggestion application 236, such as Apply Names 238, application developer 240, application icon 242, price 244 and sequence 246.
Fig. 3 is the block diagram of the system 300 comprised for the exemplary components in view of selected application being suggestion application by one or more application identities.This system 300 comprises inquiry log database 302, common weight engine 3 04, application data base 306, metadata engine 308, suggestion application engine 310 and suggestion application data base 312.
Inquiry log database 302 provides information with the form of inquiry log to common weight engine 3 04.This common weight engine 3 04 processes inquiry log to generate the index (degree of correspondence such as between application) of the common weight of application.For each application, the index of the common weight of application comprises the list of the common weight of the application be proposed in view of this application.Such as, the first application in the index of the common weight of application comprises correspondence first list of the common weight of the application be proposed in view of the first application, and the second application in the index of the common weight of application comprises correspondence second list of the application be proposed in view of the second application.Inquiry log database 302 comprises the information relevant with applying the inquiry that inputs to application market.This information can comprise such as event.As discussed in further detail below, example event can comprise click or install.In some implementations, and for given event, inquiry log can also comprise the record of the position of this event source of instruction in the list of the Search Results of concrete inquiry.The inquiry that inquiry log is processed to generate this click and install number maps 305 to first of set of applications.
Application data base 306 stores the information corresponding with the application that can be used for downloading to computing equipment (mobile device 200 of such as Fig. 2) and installing on the computing device.This application data base 306 provides the initial list of the application stored in application data base 306 and applies relevant information with these to metadata engine 308.This metadata engine 308 processes this information and applies corresponding associated metadata to provide with each.This metadata can comprise such as Apply Names, developer's title, sequence, price, kind, application and whether belong to certain content (such as mature content) etc.The metadata that metadata engine 308 provides these to apply to suggestion application engine 310.
Suggestion application engine 310 receives the initial list of the application stored application data base 306 and associated metadata from metadata engine 308 and receives the index of the common weight of application from common weight engine 3 04.In some implementations, application data base 206 provides the initial list of application to suggestion application engine 310.This suggestion application engine 310 is removed the application not being identified as suggestion based on metadata and is applied right filter list to generate from the initial list of application.As discussed in further detail below, this suggestion application engine 310 processes the index that the right filter list of application applies to generate suggestion in view of the index of common weight of application.This suggestion application engine 310 to suggestion application data base 312 offer suggestions application index.This suggestion application data base 312 stores the index of suggestion application.The index that this suggestion application data base 312 makes suggestion apply can be used for application market.
In order to generate the index of the common weight of application, common weight engine 3 04 based on the information provided from inquiry log database 302 determine apply between common weight.As discussed above, the information (such as event) in inquiry log database 302 of can processing maps 305 to provide relevant with the application (App) of each inquiry (Q) to the Search Results being identified as inquiry first.For each application of each correspondence inquiry, first maps 305 also comprises the click number (C) of application and installs number (I).Such as, the inquiry Q of the first mapping 305 1search Results that generate, that comprise App1 and App2 is (namely at user input query Q 1time, App1 and App2 be presented as with inquiry Q 1corresponding Search Results).App1 comprise from as inquiry Q 1the correspondence that obtains of the App1 of Search Results click number (C 1,1) and corresponding installation number (I 1,1).Equally, App2 comprise from as inquiry Q 1the correspondence that obtains of the App2 of Search Results click number (C 2,1) and corresponding installation number (I 2,1).As used herein, click instruction search subscriber and at least obtain the more information relevant with this application from the application of Search Results is clicked.As used herein, the application that in fact instruction search subscriber is downloaded and installed is installed.
The Hash that common weight engine 3 04 generates each inquiry in the inquiry (Q) being used for the first mapping 305 maps to second of application from inquiring about Hash to generate.For each application of each inquiry, based on clicking number and installing number, common weight engine 3 04 determines that the weighting of each application is to generate the 3rd mapping from inquiry Hash to application.This common weight engine 3 04 determines total weighting of each application inquired about on each inquiry Hash in Hash, determine the common weight that each application is right, and the common weight right to each application is normalized.If the normalization that application-specific is right is weighted in more than threshold value, then common weight engine 3 04 comprises the right normalization weighting of this application-specific at the index of the common weight of application.If the normalization weighting that application-specific is right is less than threshold value, then common weight engine 3 04 does not comprise the right normalization weighting of this application-specific in the index of the common weight of application.
The example that generation first maps below is provided.Common weight engine 3 04 generates based on the information provided from inquiry log database 302 and maps (such as first maps 305) to being provided as first of the application (App) of Search Results in response to corresponding inquiry from inquiry (Q).For the object of simplified characterization, this example comprises four inquiry (Q 1to Q 4); But example is applicable to the inquiry of any number.Particularly, for each inquiry (Q uniquely n), generate the mapping of the application (APPm) to the Search Results being provided as corresponding inquiry.In this example, inquiry be mapped to application as follows:
first maps
Q 1→App1(C 1,1,I 1,1)，App2(C 2,1,I 2,1)；
Q 2→App1(C 1,2,I 1,2)，App2(C 2,2,I 2,2)；
Q 3→ App1 (C 1,3, I 1,3); And
Q 4→App1(C 1,4,I 1,4),App3(C 3,4,I 3,4)。
Should be appreciated that above provide first to map be only example for purposes of illustration, the number of application of mapped value ad hoc inquiry can be not limited to the example numbers of provided application herein.
For each application m be provided in response to inquiry n, C m,ninstruction applies m at the upper clicked total degree of equipment (such as mobile computing device), I m,nthe total degree that instruction application m is mounted on equipment.To application click or user to application selection comprise to user display apply relevant details with " clicked ".
Common weight engine 3 04 removes inquiry and the Hash generating each inquiry in the inquiry of the first mapping maps to provide from inquiry Hash to application second.In some implementations, removing inquiry can comprise removes punctuation mark from inquiry, and the search terms of rearrangement inquiry, removes the duplicate keys etc. in search inquiry.Continue above example, the second mapping can be provided as follows:
second maps
Hash 1 → App1 (C 1,1, I 1,1), App2 (C 2,1, I 2,1)
Hash 2 → App1 (C 1,2, I 1,2), App2 (C 2,2, I 2,2)
Hash 3 → App1 (C 1,3, I 1,3)
Hash 4 → App1 (C isosorbide-5-Nitrae, I isosorbide-5-Nitrae), App3 (C 3,4, I 3,4)
For each application of each Hash, based on click number and installation number, common weight engine 3 04 determines that weighting is to provide the 3rd mapping.Particularly, common weight engine 3 04 determines the weighting (w of each application (Appm) m,n).In some implementations, this weighting can be determined according to following relational expression:
w m,n＝C m,n+αI m,n
Variable α changes the weighting of the installation number applying to application.In some implementations, the value of α can be greater than one, and the installation number applied is weighted more gravely than the click number of application.3rd mapping can be provided as follows:
3rd maps
Hash 1→App1(w 1,1)，App2(w 2,1)
Hash 2→App1(w 1,2)，App2(w 2,2)
Hash 3→App1(w 1,3)
Hash 4→App1(w 1,4)，App3(w 3,4)
Common weight engine 3 04 determines the total weighting inquiring about each application on each inquiry Hash in Hash.This common weight engine 3 04 is to square summation of each weighting that all inquiry Hash are applied.Particularly, total weighting of each application can be determined based on following relational expression:
App1→tw 1＝(w 1,1) 2+(w 1,2) 2+(w 1,3) 2+(w 1,4) 2
App2→tw 2＝(w 2,1) 2+(w 2,2) 2
App3→tw 3＝(w 3,4) 2
Common weight engine 3 04 determines the common weight that each application is right.Common weight aw x,ycan determine based on following relational expression:
aw x,y＝sum(w x,i*w y,i)
Wherein x=1 ..., m; Y=1 ..., m; And i=1 ..., n.As non-limiting example, the common weight aw between App1 and App2 1,2can be determined as follows:
aw 1,2＝w 1,1*w 2,1+w 1,2*w 2,2+w 1,3*w 2,3+w 1,4*w 2,4
But, in current non-limiting example, weighting w 2,3and w 2,4be zero (that is, there is not weighting w in current non-limiting example 2,3and w 2,4).Therefore, the common weight aw between App1 and App2 1,2for:
aw 1,2＝w 1,1*w 2,1+w 1,2*w 2,2
Continue this example, common weight engine 3 04 determines the common weight of each application as follows:
App1→App2(aw 1,2),App3(aw 1,3)
App2→App1(aw 2,1)
App3→App1(aw 3,1)
The common weight normalization that common weight engine 3 04 is right to each application.This normalization common weight is as follows:
App1→App2(nw 1,2),App3(nw 1,3)
App2→App1(nw 2,1)
App3→App1(nw 3,1)
Wherein nw x,y=(aw x,y/ (tw x+ tw y).
In some implementations, normalization weighting is the factor of the associated degree of application of mark application centering.The right normalization weighting of each application can be considered to scoring, and can with threshold value normalization weighted ratio comparatively.If the normalization that application-specific is right is weighted in more than threshold value normalization weighting, then the common weight that the application-specific in the index of the common weight of common weight engine 3 04 output application is right.If the normalization weighting that application-specific is right is less than threshold value normalization weighting, then common weight engine 3 04 does not export the common weight of the application-specific in the index of the common weight of application.In one example, if nw 1,2be greater than threshold value nw tHR, then common weight engine 3 04 comprises common weight nw at the index of the common weight of application 1,2.But, if nw 1,2be less than threshold value nw tHR, then common weight engine 3 04 does not comprise common weight nw in the index of the common weight of application 1,2.
Common weight engine 3 04 carrys out the index of the common weight of computing application based on the normalization common weight of the normalization weighting had more than threshold value normalization weighting.As discussed above, for each application, the index of the common weight of application is included in the list of the common weight of the application of more than threshold value normalization weighting.Continue above example, App1 can comprise the corresponding lists of the common weight of suggestion application, and this list comprises the normalization common weight of App2 and App3.App2 can comprise the corresponding lists of the common weight of suggestion application, and this list comprises the normalization common weight of App1; And App3 can comprise the corresponding lists of the common weight of suggestion application, and this list comprises the normalization common weight of App1.
Suggestion application engine 310 receives the index of the initial list of application and the common weight of associated metadata and application stored in application data base 306.Metadata can comprise filter metadata and/or scoring metadata.As described in detail below, this filter metadata comprises the metadata for (such as removing) filtering the application of the initial list carrying out self-application.As described in detail below, this scoring metadata comprises for determining any application of applying in the application of the application centering that right overall score is proposed in view of the selection of other application with mark in conjunction with normalization common weight.More specifically, as described in detail below, this scoring metadata may be used for the scoring of generator data.Some metadata can be provided as filter metadata and scoring metadata (namely can be used to both filtration and score calculation).
In some implementations, advise that the filter metadata of the application in the initial list of application compares to generate the right filter list of application by application engine 310.If the filter metadata of the application of application-specific centering is corresponding, then related application engine 3 10 comprises this application-specific pair in the right filter list of application.If the filter metadata of the application of application-specific centering is not corresponding, then related application engine 3 10 does not comprise this application-specific pair in the filter list that application is right.In addition, as described in detail below, in some implementations, if the filter metadata of any application of application-specific centering is not more than threshold value, then from the right filter list of application, remove this application right.
Filter metadata can comprise such as kind metadata, content metadata, title metadata, descriptive metadata, installation metadata, sequence metadata, place metadata and developer and to mark metadata.In some implementations, the kind metadata of the application of the application-specific centering in the initial list of application can be compared.If determine that application is corresponding with identical type (such as play, amusement, education), then application-specific can be applied in right filter list being included in.But, if determine that application is not corresponding with identical type, then application-specific is not applied in right filter list being included in.
Content metadata can indicate the particular content of application.In some implementations, application content can comprise such as mature content.The content metadata of the application of the application-specific centering in the initial list of the application stored in application data base 306 can be compared.If determine that application is corresponding with identical content (such as mature content), then can by application-specific to being included in the right filter list of application.But, if determine that application is not corresponding with identical content, then application-specific is not applied in right filter list being included in.Such as, the content metadata of the first application of application-specific centering can indicate the first application to comprise mature content, and the content metadata of second of this application centering the application can indicate related content not comprise mature content.As annotation, although application market can get rid of the application comprising Pornograph, but still can obtain from application market the application (such as comprising the application of the content relevant with sexy underwear and/or the content relevant with bonkbuster) comprising and can be regarded as vulgar content.Continue above example, to application content metadata comparison disclose application content difference (namely first application comprise mature content and second apply do not comprise mature content).Therefore, application is not applied in right filter list being included in.
The title metadata of application can be processed.This title metadata comprises can to the title of application of user's display, such as Apply Names 218 or 238 all shown in figure 2.If determine that at least one application in the application of application-specific centering comprises sky title (such as title is for blank), then this application-specific is not applied in right filter list being included in.
The descriptive metadata of application can be processed.This descriptive metadata comprises the information relevant with the description of the application that can show to user.This descriptive metadata can be provided by the developer applied.If determine that at least one application in the application of application-specific centering comprises empty description (being such as described as blank), then this application-specific is not applied in right filter list being included in.
The installation metadata of application can be processed.In some implementations, this installation metadata comprises the installation total number of the upper application of multiple computing equipment (such as computing equipment 102).If determine that the installation number of at least one application in the application of application-specific centering is below minimum installation number, be not then included in this application in the filter list of application.In some implementations, this installation metadata comprises the unloading rate of application.Unloading rate is the application unloading number (such as after the installation of application, user unloads this application) that number is installed in each application.If at least one determining in the application of application-specific centering is applied in more than maximum unloading rate, then not by this application to being included in the filter list of application.
The sequence metadata of application can be processed.In some implementations, this sequence metadata comprises the sequence number of application.Such as, this sequence number each total number sorted of association for providing with the user (such as user 108) of application.If determine that the sequence number of at least one application in the application of application-specific centering is below minimum sequence number, then do not apply this application-specific in right filter list being included in.In some implementations, the metadata that sorts comprises the average sequence of application.The average sequence of application can be in any subset of the user (or all users) of application.If determine that the average sequence of at least one application in the application of application-specific centering is below minimum average B configuration sequence, then do not apply this application in right filter list being included in.
The place metadata of application can be compared.Metadata instruction of this place with apply herein by the relevant data in the geographic area supported.In some implementations, place can indicate the country applied herein by supporting, such as China or the U.S..In some implementations, place can indicate the language that application has been translated into.Such as, given application can provide with German in English.If the Locale information instruction of the application of application-specific centering is overlapping, then this application is applied in right filter list being included in.Such as, if determine that application comprises language overlapping (such as two kinds of application provide all in English) and/or country's overlapping (such as two kinds of application all can obtain in the U.S.), then application is regarded as corresponding with identical place and corresponding application is applied in right filter list being included in.But, if determine that application is not corresponding with identical place, then the application of correspondence is not applied in right filter list being included in.
The developer that can compare application marks metadata.This developer scoring can relate to the sequence associated with the developer of application.Such as, developer sorts the average sequence of application that the history sequence of the application that can provide based on developer or developer provide.If determine that developer's scoring of at least one application in the application of application-specific centering is below minimum scoring, then do not apply this application in right filter list being included in.
In some implementations, advise that application engine 310 processes the scoring metadata of the application of application centering with generator data scoring (ms).Particularly, advise that the scoring metadata of the application of application centering compares by application engine 310 to mark with generator data.As discussed in further detail below, advise that the metadata of the application of application centering is marked with normalization weighted array to provide overall score by application engine 310.This scoring metadata can comprise such as title metadata, descriptive metadata and license metadata.
The title metadata of the application of application-specific centering can be processed, and corresponding similarity score can be generated.Particularly, compare to generate title similarity score to the similarity of the text of the title metadata of application.
The descriptive metadata of the application of application-specific centering can be processed, and similarity score discussed in further detail below can be created on.Particularly, the similarity of the text of the descriptive metadata of application is compared generate description similarity scoring.Title metadata and the descriptive metadata of the application of application-specific centering can be processed, and can similarity score be generated.Such as, the descriptive metadata of the title metadata and Another Application that can process an application is marked to generate title-description similarity.The license metadata of the application of application-specific centering can be processed, and corresponding similarity score can be generated.This license metadata can comprise and the API (application programming interface) of application permits access computing equipment (such as mobile device 200), data that such as API of GPS (GPS) API or flashlamp is relevant.
As non-limiting example, following relational expression can be used to mark (ms) to provide each application to the metadata of (Appu, Appv):
ms u,v＝[(k 1×ConceptSimilarity u,v)×(k 2×TitleSimilarity u,v)×(k 3×Title uDescription vSimilarity)×(k 4×Title vDescription uSimilarity)×(k 5×DescriptionSimilarity u,v)]×[(k 6×PermissionSimilarity u,v)×(k 7×TitleSimilarity u,v)]
But, should be appreciated that and other relational expressions can be used to determine that metadata is marked.
ConceptSimilarity u,vfor marking based on the concept similarity of the text with each association in application.Such as, can extract with the important word in extensive documentation (description of such as applying) to determine the most similar word based on search pattern.For small-sized document, can directly expand.Concept similarity scoring for document is defined as the weighted sum of these concepts, and wherein the list of each concept word represents.
TitleSimilarity u,vfor the title similarity score of the similarity of the text based on the title metadata between application u and v.Title udescription vsimilarity marks with title-description similarity of the similarity of the text of the descriptive metadata of application v based on the text of the title metadata of application u.Title vdescription usimilarity marks with title-description similarity of the similarity of the text of the descriptive metadata of application u based on the text of the title metadata of application v.DescriptionSimilarity u,vfor the description similarity scoring of the similarity of the text based on the descriptive metadata between application u and v.PermissionSimilarity u,vfor the license similarity score of the similarity based on the license metadata between application u and v.Variable k 1to k 7change and to mark the weighting applied to the respective meta-data with this variable association.
In this example, final related application engine 3 10 makes metadata mark square being multiplied by mutually to generate and applying right overall score (os) of (ms) and normalization weighting (nw).This overall score can be provided as follows:
os u,v＝(nw u,v) 2x ms u,v
Wherein u=1 ..., m, v=1 ..., m.But, should be appreciated that and other relational expressions can be used to determine overall score.Metadata scoring (ms) can be the calculated value of any combination of metadata scoring (such as title, description, license).
Suggestion application engine 310 then can be right by the application in the right filter list of application overall score compared with overall score threshold value.Then suggestion application engine 310 can assign to determine that whether the application of applying centering is fully similar based on general comment, and the selection made it possible in view of the Another Application of the application centering in the index of suggestion application will apply the application identities of centering for suggestion.If overall score is more than overall score threshold value, then advising that application engine 310 is determined can be suggestion by the application identities of application centering in view of the selection of the Another Application of application centering.If overall score is less than overall score threshold value, then advise that application engine 310 determines that the application identities of application centering cannot be suggestion by the selection in view of the Another Application of application centering.In some implementations, advise that the application of application engine 310 based on the overall score had more than overall score threshold value is to the index generating suggestion application.
In some implementations, overall score may be used for sorting for display to suggestion application.As non-limiting example, suggestion application engine 310 is based on os 1,2and os 1,3determine that App2 and App3 is identified as suggestion application in view of App1 respectively.Ask to show the application that is proposed in view of App1 in response to user, App2 and App3 can show according to the clooating sequence based on the right overall score of each application.Such as, if overall score os 1,2be greater than overall score os 1,3, then App2 shows according to the clooating sequence higher than App3.
Suggestion application engine 310 to suggestion application data base 312 offer suggestions application index.Suggestion application data base 312 stores the index of suggestion application, is shown as mapping 316.The index that suggestion application data base 312 makes suggestion apply can be used for application market.
Fig. 4 is the process flow diagram of the instantiation procedure 400 that can perform of realization according to present disclosure.This instantiation procedure 400 can use one or more computing equipment to perform.Such as, one or more server system (server system 104 of such as Fig. 1) can be used to perform instantiation procedure 400.
Receive inquiry log (402).Total weighting tw is determined for each application m on all Hash m(404).Such as, this total weighting tw mthe quadratic sum of each weighting of all Hash being applied m can be confirmed as.
For each application to determining common weight aw x,y(406).For each application to determining common weight aw x,ynormalization weighting nw x,y(408).Based on the common weight aw that each application is right x,ygenerate the index of the common weight that (410) apply.Such as, the index of the common weight of application is right based on the application of the normalization weighting had more than threshold value normalization weighting.
Fig. 5 is the process flow diagram of diagram for the instantiation procedure 500 of filtration application list.This instantiation procedure 500 can use one or more computing equipment to perform.Such as, one or more server system (server system 104 of such as Fig. 1) can be used to perform instantiation procedure 500.
Receive the list (502) of application.Such as, the initial list of the application stored in application data base 306 can be received.Receive apply metadata (504).This apply metadata can comprise filter metadata and content metadata.Filter metadata can comprise such as kind metadata, title metadata, descriptive metadata, installation metadata, sequence metadata, place metadata and developer and to mark metadata.The application come in the initial list of filtration application based on filter metadata applies right filter list (506) to generate.For each application pair in the filter list that application is right, come Computing Meta data scoring (ms) (508) based on scoring metadata.For each application pair in the filter list that application is right, calculate overall score (os) (510) based on normalization weighting (nw) and metadata scoring (ms).
Generate the index (512) of suggestion application.Such as, for each application pair in the filter list that application is right, overall score is compared with threshold value overall score.If apply right overall score to be greater than threshold value overall score, then the application of application centering is included in the index of suggestion application.If apply right overall score to be not more than threshold value overall score, then the application of application centering is not included in the index of suggestion application.
Fig. 6 is that diagram is for showing the process flow diagram of the instantiation procedure of the application being identified as suggestion application in view of selected application.This instantiation procedure 600 can use one or more computing equipment to perform.Such as, one or more server system (server system 104 of such as Fig. 1) can be used to perform instantiation procedure 600.
Receive search inquiry (602).This search inquiry can comprise the search terms relevant with the kind of application-specific or application.Generate Search Results (604).This Search Results can comprise the list of the application identified in response to search terms.This Search Results can be transmitted for display (606).This Search Results can in the upper display of mobile computing device (such as mobile computing device 200).User's input (608) of the selection of instruction application is received from Search Results.Obtain application data (610).Such as, the user in response to application selects to obtain application data.Obtain suggestion application data (612).This suggestion application data is corresponding with the application being identified as suggestion in view of selected application.Transmitting user data and suggestion application are used for display (614).These data can in the upper display of mobile computing device (such as mobile computing device 200).
The realization of present disclosure relates to applies in view of being used for identifying one or more suggestion selected by user feedback.In some instances, the search daily record in market provides with clicked application and mounted applies corresponding data.Corresponding each application, can determine whether click or installation are derived from this application and are shown as suggestion application in view of selected application.Such as, be derived from this application be shown as suggestion application in view of selected application if click or install, then in search daily record, stored data sets and this data set can comprise application identities symbol, type of interaction (such as click or install) and this suggestion and be applied in position in the list of the suggestion application presented to user.These data can be polymerized each application on all users of application market.
As non-limiting example, the index (mapping 316 of such as Fig. 3) of application of can offering suggestions for using together with application market.Search subscriber can access application market to search for application.This search subscriber can selective gist and the suggestion based on selected application can be asked to apply.The input (such as key word) that selected application can be used as the index of suggestion application is applied with one or more suggestion of selected association to identify.The suggestion application identified is shown to this search subscriber.In some instances, and as discussed above, according to clooating sequence display suggestion application.If this search subscriber clicks suggestion application, then to the corresponding event data of inquiry log data-base recording.Example event data can comprise and the identifier of suggestion association, the position that is applied in clooating sequence with the hit counter of suggestion association or the increment and advising when clicking or install and occurring of installing counter.If search subscriber installs suggestion application, then to the corresponding event data of inquiry log data-base recording.This event data is polymerized in all suggestion application and user, makes inquiry log database provide the list of clicked/mounted suggestion application, and for each suggestion application, each position in the list of suggestion application provides to be clicked and installs number.
In some realizations of present disclosure, the event data that can process provides in inquiry log database will show with definition the order applied with the suggestion of selected association.In some implementations, the event data that provides in search daily record can be processed with the possible index of amendment or more new suggested application.In this way, the index of suggestion application can be considered end user's feedback, the such as click of event form or install.
In some implementations, can for each application provided in suggestion application references to generation feedback score (fs).In some instances, this feedback score is used for defining and will shows the order applied with the suggestion of selected association.In some instances, this feedback score can be used for determining whether that one in view of application centering should be used for the Another Application of application centering to be maintained suggestion application.In some instances, feedback score can be used for revising the overall score (os) (being namely used in view of should be used for Another Application being designated suggestion application) previously determined, and amended overall score can be used for determining whether that one in view of application centering should be used for the Another Application of application centering to be maintained suggestion application.
In some implementations, feedback score is determined with the ratio clicking number based on clicking number, installation data, installation multiplier, payment applications multiplier, position multiplier and/or installing number.In some instances, installation multiplier is multiplied by provide than clicking the large weighting of number (such as, installing multiplier for >1) to installing number by installing number.In some instances, payment applications multiplier is multiplied by provide the weighting larger than the application of user charges to mounted application by installing number.In some instances, payment applications multiplier equals one for free application, and for payment applications, be >1.To (such as use multiplier discussed above revise after) click number and number summation can be installed, and summation can be multiplied by position multiplier and above-mentioned both ratios.In some instances, position multiplier is used for providing than being in the larger weighting of lower position application in the list of suggestion application when event is generated to suggestion application.In this way, can consider that less user is rolled to the fact of the bottom of the list of suggestion application.
In some instances, multiple click-position multiplier can be provided.Each click-position multiplier can associate with the relevant position in the list advising applying.Such as, the first click-position multiplier can associate with primary importance, and the second click-position multiplier can associate with the second place, by that analogy.Each click-position multiplier can be determined based on the click number associated with top (such as the highest sorting position) and the click number associated with relevant position.In some instances, each click-position multiplier can be confirmed as the click number that associates with tip position and the ratio of click number associated with relevant position.Such as, the click number associated with tip position is 10 and the click number associated with relevant position is 8, then the click associated with relevant position-position multiplier is 1.25 (such as 10/8).
Be similar to click-position multiplier, in some instances, multiple installation-position multiplier can be provided.Each installation-position multiplier can associate with the relevant position in the list advising applying.Such as, the first installation-position multiplier can associate with primary importance, and the second installation-position multiplier can associate with the second place, by that analogy.Each installation-position multiplier can be determined based on the installation number associated with top (such as the highest sorting position) and the installation number associated with relevant position.In some instances, each installation-position multiplier can be confirmed as the installation number that associates with tip position and the ratio of installation number associated with relevant position.Such as, the installation number associated with tip position is 10 and the installation number associated with relevant position is 5, then the installation associated with relevant position-position multiplier is 2 (such as 10/5).
In some implementations, feedback score be stored in suggestion application index in and for define will to user display suggestion application order.Such as, search subscriber can access application market to search for application.Search subscriber can selective gist and can based on selected should be used for request suggestion application.The input (such as key word) that selected application can be used as the index of suggestion application is applied with one or more suggestion of selected association to identify.According to the respective feedback scoring based on suggestion application, the order of definition shows to search subscriber in the suggestion application identified.In some instances, this order is provided as the descending of feedback score.
Fig. 7 is the block diagram of the system 700 comprising the exemplary components that the suggestion for identifying based on user feedback is applied.This exemplary components comprises inquiry log database 302, feedback score (fs) engine 710 and suggestion application data base 312.The computer executable program that these parts may be implemented as one or more computer-readable memory and can use one or more process to perform.
Program log database 302 provides search daily record 702, and this search daily record 702 comprises the event data with the one or more suggestion associations in view of selected application.Such as, as discussed in detail above, previously App2 and App3 being applied in view of App1 is designated suggestion, and provided App2 and App3 in the index (mapping 316 of Fig. 3) of suggestion application.Search daily record 702 comprises the event data of each suggestion association in applying with suggestion, and this event data generates based on user feedback.In described example, event data comprises clicks order (C), install number (I) and with click number and the position data (P) of installing number and associating.In some instances, in view of one or more suggestions application (such as App2) of selected application (such as App1) can have for clicking number, installing one or more values of number and position data.Such as, depend on the time of computing equipment 102A to 102F and the current mapping 316 of generation, App2 can have no position data, and the click number of the App2 relevant with each position data and install number and can be stored in by inquiry log database 302 and search in daily record 702.In some instances, position data instruction association suggestion when generating correlating event is applied in the position in the list of suggestion application.
Feedback score engine 710 obtains search daily record data and generates feedback score for each suggestion application in the suggestion application provided in search daily record 702.This feedback score engine 710 provides feedback score to suggestion application data base 312, each feedback score is stored and to the corresponding suggestion association of advising in the index applied, such as map 316 '.Suggestion application data base 312 makes mapping 316 ' can be used for application market.
Fig. 8 is the process flow diagram of the instantiation procedure 800 that diagram is applied for the suggestion identified based on user feedback.This instantiation procedure 800 can use one or more computing equipment to perform.Such as, one or more server system (server system 104 of such as Fig. 1) can be used to perform instantiation procedure 800.
Receive search daily record (802).Such as, the feedback score engine 710 of Fig. 7 receives search daily record from inquiry log database 302.Generate feedback score (804).Such as, the feedback score engine 710 of Fig. 7 processes the event data that provides in search daily record to generate feedback score, each feedback score with advise association.To the index stores feedback score (806) of suggestion application.
The realization of present disclosure and all functions operation that provides herein can with Fundamental Digital Circuits or with computer software, firmware or hardware, and the structure disclosed in comprising in this instructions and structural equivalents thereof or one or more combination realize.The realization of present disclosure can be implemented as one or more computer program, one or more modules of the computer program instructions of namely encoding on a computer-readable medium, these instructions are performed by data processing equipment or in order to the operation of control data treating apparatus.This computer-readable medium can be machine readable storage device, machine readable storage substrate, memory devices, the composition affecting machine readable transmitting signal or one or more combination.Term " data processing equipment " is contained for the treatment of all devices of data, equipment and machine, comprises such as programmable processor, computing machine or multiple processor or computing machine.In addition to hardware, this device can comprise for discussed computer program creates the code of execution environment, such as, form the code of processor firmware, protocol stack, data base management system (DBMS), operating system or one or more combination.
Computer program (also referred to as program, software, software application, script or code) can be write with any type of programming language (comprising compiler language or interpretative code), and computer program can be disposed by any form, comprise as stand-alone program or as module, parts, subroutine or applicable other unit used in a computing environment.The non-essential file corresponded in file system of computer program.Program can be stored in the part of the file keeping other programs or data (the one or more scripts stored in such as marking language document), be stored in the Single document being exclusively used in discussed program, or be stored in multiple coordinated files (such as storing the file of the part of one or more module, subroutine or code).Computer program can be deployed and perform on a computer, or is being positioned at a website place or is being distributed in multiple website place and by multiple computing machines of interconnection of telecommunication network perform.
Process described in present disclosure and logic flow can be performed by the one or more programmable processors performing one or more computer program and carry out n-back test to be inputted data by operation and to be generated output.This process and logic flow also can be performed by dedicated logic circuit, and device also can be implemented as this dedicated logic circuit, this dedicated logic circuit is such as FPGA (field programmable gate array) or ASIC (special IC).
Be applicable to performing any one or more processors that the processor of computer program comprises the digital machine of such as general and both special microprocessors and any kind.Usually, processor receives instruction and data from ROM (read-only memory) or random access memory or the two.The element of computing machine can comprise the processor for performing instruction and the one or more memory devices for storing instruction and data.Usually, computing machine also will comprise one or more mass memory unit to store data, or this computing machine be operationally coupled with from mass memory unit receive or to mass memory unit transmit data or the two, this mass memory unit is such as disk, magneto-optic disk or CD.But computing machine does not need to have such equipment.In addition, computing machine can be embedded in another equipment, and this another equipment is such as mobile phone, personal digital assistant (PDA), Mobile audio player, GPS (GPS) receiver etc.The computer-readable medium being applicable to storing computer program instructions and data comprises the nonvolatile memory of form of ownership, medium and memory devices, comprises such as: semiconductor memory devices, as EPROM, EEPROM and flash memory device; Disk, as built-in hard disk or removable dish; Magneto-optic disk; And CD ROM and DVD-ROM dish.This processor and storer can supplement with dedicated logic circuit or be incorporated in this dedicated logic circuit.
Mutual in order to what provide with user, the realization of present disclosure can realize on the computing machine with the display device for showing information to user (such as CRT (cathode-ray tube (CRT)) or LCD (liquid crystal display) monitor) and keyboard and pointing device (such as mouse or tracking ball can provide input to computing machine by its user).What also can use the equipment of other kinds to provide with user is mutual; Such as, the feedback provided to user can be any type of sense feedback, such as visual feedback, audio feedback or tactile feedback; And can receive in any form from the input of user, comprise the sense of hearing, voice or sense of touch input.
Although present disclosure comprises some details, but these details should be interpreted as the restriction of the scope to present disclosure or claimed content, but be appreciated that the description of the feature of the example implementation to present disclosure.Some feature described in the situation realized separately in present disclosure can also provide with single realization combination.On the contrary, each feature described in the situation of single realization also can provide respectively or provide in any suitable sub-portfolio in multiple realization.In addition; perform although more than can describe feature as with certain combination and even initially just require such protection; but the one or more features can removed from combination in some cases from claimed combination, and claimed combination can relate to the change of sub-portfolio or sub-portfolio.
Similarly, although describe operation according to particular order in the accompanying drawings, but this is not appreciated that and requires that such operation performs according to shown particular order or according to sequential order, or require that all illustrated operations are all performed, to realize the result expected.In some circumstances, multitask and parallel processing may be favourable.In addition, the separation of the various system units in realization described above is not appreciated that and all requires such separation in all realization, and should be appreciated that described program element and system usually can integrate or be packaged into multiple software product in single software product.
Therefore, the specific implementation of present disclosure has been described.Other realize in the scope of following claim.Such as, the action recorded in claim can perform according to different orders, and these actions still can realize the result of expectation.Describe a large amount of realization.But, should be appreciated that and can make various amendment when not departing from the spirit and scope of present disclosure.Such as, can use each form of the above flow process illustrated, wherein step can be reordered, adds or remove.Therefore, other realize in the scope of following claim.

Claims (20)

1. a system, comprising:
One or more computing machine; And
Be coupled to the computer-readable medium of described one or more computing machine, have instruction stored thereon, described instruction makes described one or more computing machine executable operations when being performed by described one or more computing machine, and described operation comprises:
Receive search daily record, described search daily record comprises and the event data by the obtainable multiple suggestion association of application market;
For each suggestion application, based on described event data determination feedback score to provide multiple feedback score;
Described multiple feedback score is stored in the index of suggestion application, the suggestion association in feedback score and described index of advising applying;
Receive in order to the one or more requests of advising apply of display with selected association;
Based on selected application and described suggestion application index identify suggestion application set; And
To client computing device transfer instruction with the suggestion application in the set according to the described suggestion application of the order display of marking based on respective feedback.
2. system according to claim 1, the feedback score wherein for corresponding suggestion application is determined based on the event associated with described respective application.
3. system according to claim 2, wherein said event comprises the installation of applying click and the described suggestion of described suggestion application.
4. system according to claim 2, wherein said event is just being provided in the list of suggestion application based on described corresponding suggestion application and is being generated.
5. system according to claim 1, wherein for the feedback score of corresponding suggestion application based on the click number to described corresponding suggestion association and determined with the installation number of described corresponding suggestion association.
6. system according to claim 5, wherein said feedback score is also determined based at least one item installed in multiplier, position multiplier and payment applications multiplier.
7. system according to claim 6, wherein said installation multiplier is applied to described installation number and is greater than one.
8. system according to claim 6, wherein operates and also comprises:
Determine that described corresponding suggestion is applied as payment applications;
Described payment applications multiplier is provided as the value being greater than; And
Described payment applications multiplier is applied to described installation number.
9. system according to claim 6, wherein operates and also comprises:
Determine that described corresponding suggestion application is not payment applications;
Described payment applications multiplier is provided as the value equaling; And
Described payment applications multiplier is applied to described installation number.
10. system according to claim 6, wherein for each click in described click number, the position that described position multiplier is applied in the list of suggestion application based on described corresponding suggestion is determined.
11. systems according to claim 6, wherein for each installation in described installation number, the position that described position multiplier is applied in the list of suggestion application based on described corresponding suggestion is determined.
12. 1 kinds of codings have the computer-readable storage medium of computer program, and described program comprises instruction, and described instruction makes described one or more computing machine executable operations when being performed by one or more computing machine, and described operation comprises:
Receive search daily record, described search daily record comprises and the event data by the obtainable multiple suggestion association of application market;
For each suggestion application, based on described event data determination feedback score to provide multiple feedback score;
Described multiple feedback score is stored in the index of suggestion application, the suggestion association in feedback score and described index of advising applying;
Receive in order to the one or more requests of advising apply of display with selected association;
Based on selected application and described suggestion application index identify suggestion application set; And
To client computing device transfer instruction with the suggestion application in the set according to the described suggestion application of order display based on each feedback score.
13. computer-readable storage mediums according to claim 12, the feedback score wherein for corresponding suggestion application is determined based on the event associated with described respective application.
14. computer-readable storage mediums according to claim 13, wherein said event comprises the installation of applying click and the described suggestion of described suggestion application.
15. computer-readable storage mediums according to claim 13, wherein said event is just being provided in the list of suggestion application based on described corresponding suggestion application and is being generated.
16. computer-readable storage mediums according to claim 12, wherein for the feedback score of corresponding suggestion application based on the click number to described corresponding suggestion association and determined with the installation number of described corresponding suggestion association.
17. 1 kinds of computer implemented methods, comprising:
Receive search daily record, described search daily record comprises and the event data by the obtainable multiple suggestion association of application market;
For each suggestion application, based on described event data determination feedback score to provide multiple feedback score;
Described multiple feedback score is stored in the index of suggestion application, the suggestion association in feedback score and described index of advising applying;
Receive in order to the one or more requests of advising apply of display with selected association;
Based on selected application and described suggestion application index identify suggestion application set; And
To client computing device transfer instruction with the suggestion application in the set according to the described suggestion application of order display based on each feedback score.
18. computer implemented methods according to claim 17, the feedback score wherein for corresponding suggestion application is determined based on the event associated with described respective application.
19. computer implemented methods according to claim 18, wherein said event comprises the installation of applying click and the described suggestion of described suggestion application.
20. computer implemented methods according to claim 18, wherein said event is just being provided in the list of suggestion application based on described corresponding suggestion application and is being generated.
CN201280074559.8A 2012-05-09 2012-05-09 The computer implemented system and method that application is recommended are generated based on user feedback Active CN104871193B (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/US2012/037122 WO2013169245A2 (en) 2012-05-09 2012-05-09 Generating application recommendations based on user feedback

Publications (2)

Publication Number Publication Date
CN104871193A true CN104871193A (en) 2015-08-26
CN104871193B CN104871193B (en) 2019-01-04

Family

ID=46124762

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201280074559.8A Active CN104871193B (en) 2012-05-09 2012-05-09 The computer implemented system and method that application is recommended are generated based on user feedback

Country Status (3)

Country Link
EP (1) EP2864945A4 (en)
CN (1) CN104871193B (en)
WO (1) WO2013169245A2 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105373887A (en) * 2015-11-12 2016-03-02 腾讯科技（深圳）有限公司 Quality evaluation method and system for terminal application
CN106878041A (en) * 2015-12-11 2017-06-20 广州市动景计算机科技有限公司 Log information processing method, apparatus and system
CN107563679A (en) * 2017-10-17 2018-01-09 广东小天才科技有限公司 The detection method and service equipment of a kind of application software

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012154848A1 (en) 2011-05-09 2012-11-15 Google Inc. Recommending applications for mobile devices based on installation histories
WO2012154838A2 (en) 2011-05-09 2012-11-15 Google Inc. Generating application recommendations based on user installed applications
EP2710466A1 (en) 2011-05-09 2014-03-26 Google, Inc. Identifying applications of interest based on application metadata
US11538095B2 (en) 2016-03-22 2022-12-27 Tupl Inc. Virtual marketplace for distributed tools in an enterprise environment
US10929912B2 (en) 2016-03-22 2021-02-23 Tupl Inc. Virtual marketplace for distributed tools in an enterprise environment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101828185A (en) * 2007-10-18 2010-09-08 微软公司 Ranking and providing search results based in part on a number of click-through features
EP2230605A1 (en) * 2009-03-16 2010-09-22 Apple Inc. Accessory and mobile computing device communication using an application communication protocol
US20110087975A1 (en) * 2009-10-13 2011-04-14 Sony Ericsson Mobile Communications Ab Method and arrangement in a data
US20110320307A1 (en) * 2010-06-18 2011-12-29 Google Inc. Context-influenced application recommendations
US20110320441A1 (en) * 2010-06-25 2011-12-29 Microsoft Corporation Adjusting search results based on user social profiles

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7523099B1 (en) * 2004-12-30 2009-04-21 Google Inc. Category suggestions relating to a search

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101828185A (en) * 2007-10-18 2010-09-08 微软公司 Ranking and providing search results based in part on a number of click-through features
EP2230605A1 (en) * 2009-03-16 2010-09-22 Apple Inc. Accessory and mobile computing device communication using an application communication protocol
US20110087975A1 (en) * 2009-10-13 2011-04-14 Sony Ericsson Mobile Communications Ab Method and arrangement in a data
US20110320307A1 (en) * 2010-06-18 2011-12-29 Google Inc. Context-influenced application recommendations
US20110320441A1 (en) * 2010-06-25 2011-12-29 Microsoft Corporation Adjusting search results based on user social profiles

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105373887A (en) * 2015-11-12 2016-03-02 腾讯科技（深圳）有限公司 Quality evaluation method and system for terminal application
CN106878041A (en) * 2015-12-11 2017-06-20 广州市动景计算机科技有限公司 Log information processing method, apparatus and system
CN107563679A (en) * 2017-10-17 2018-01-09 广东小天才科技有限公司 The detection method and service equipment of a kind of application software
CN107563679B (en) * 2017-10-17 2020-05-22 广东小天才科技有限公司 Application software detection method and service equipment

Also Published As

Publication number Publication date
WO2013169245A3 (en) 2015-03-19
EP2864945A2 (en) 2015-04-29
EP2864945A4 (en) 2016-04-20
WO2013169245A2 (en) 2013-11-14
CN104871193B (en) 2019-01-04

Similar Documents

Publication Publication Date Title
US8825663B2 (en) Using application metadata to identify applications of interest
US8566173B2 (en) Using application market log data to identify applications of interest
US8819025B2 (en) Recommending applications for mobile devices based on installation histories
CN104871193A (en) Generating application recommendations based on user feedback
US8924955B2 (en) Generating application recommendations based on user installed applications
US8290818B1 (en) System for recommending item bundles
US8285602B1 (en) System for recommending item bundles
US8914399B1 (en) Personalized recommendations based on item usage
CN106415537B (en) Locally applied search result is inserted into WEB search result
CN103608811B (en) For the context-aware applications model of the equipment connected
US8489577B2 (en) System and method for defined searching and web crawling
US20170147659A1 (en) Systems and Methods for Accessing Applications in Grouped Search Results
US9043351B1 (en) Determining search query specificity
US20150324868A1 (en) Query Categorizer
CN103620583A (en) Surfacing applications based on browsing activity
CN104428767A (en) Related entities
AU2015301043B2 (en) Item maps for app store apps
JP2013077152A (en) Application recommendation device and application recommendation method
US20120203765A1 (en) Online catalog with integrated content
US11636313B2 (en) Recommendation system based on neural network models to improve efficiencies in interacting with e-commerce platforms
Davidsson Mobile application recommender system
CN102855582A (en) Method, device and server for obtaining data

Legal Events

Date Code Title Description
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: American California

Applicant after: Google limited liability company

Address before: American California

Applicant before: Google Inc.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant