CN105653543A - Method and device for setting user label in information system - Google Patents
Method and device for setting user label in information system Download PDFInfo
- Publication number
- CN105653543A CN105653543A CN201410643929.6A CN201410643929A CN105653543A CN 105653543 A CN105653543 A CN 105653543A CN 201410643929 A CN201410643929 A CN 201410643929A CN 105653543 A CN105653543 A CN 105653543A
- Authority
- CN
- China
- Prior art keywords
- user
- label
- role
- historical operation
- information
- 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.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and device for setting a user label in an information system. The method includes: analyzing personal databases of users to acquire valid historical operating data of all the users; respectively performing calculation and treatment on the valid historical operating data of all the users to obtain preference characteristics of all the users; and setting the preference characteristics of all the users as role labels of all the users, and transmitting object information corresponding to the role labels through a client. The method can perform role label setting on the users, the object information can be transmitted to the user client according to the role labels of the users, and the time that the users search the objects can be saved.
Description
Technical field
The application relates to areas of information technology, particularly relates to the user tag method to set up in a kind of infosystem and device thereof.
Background technology
Along with the development of Internet technology, user selects the object meeting operational requirements to operate by the network platform, it is achieved corresponding object. But the enormous amount of object in the common network platform, all kinds of descriptions of object also vary, and user wants to search the object satisfied the demands in the object of magnanimity, often to be spent a large amount of time. Therefore, when user carries out object search by the common network platform, length consuming time, inefficiency, poor user experience.
Meanwhile, the network platform also cannot will be transferred to the client terminal of user in the object information short period of time meeting user operation demand, and the object in the network platform needs to expend more times and just can be user-operably, and hinders the raising of network platform efficiency.
Summary of the invention
In view of this, the application provides the user tag method to set up in a kind of infosystem and device thereof, user can be carried out role's label setting by it, thus according to role's label, the object information meeting demand is sent to subscription client, it is to increase Consumer's Experience and network platform efficiency.
The application provides the user tag method to set up in a kind of infosystem, and described method comprises:
Resolve users personal data storehouse, obtain effective historical operation data of each user;
Respectively effective historical operation data of described each user are carried out computing, obtain the preference profiles of each user;
Role's label that the preference profiles of described each user is set to each user, transmits the object information corresponding with described role's label by described role's label to subscription client.
In the application one embodiment, described users personal data storehouse comprises operation history data storehouse, the object information of effective historical operation of effective historical operation data comprise user of described user;
Described respectively effective historical operation data of each user being carried out computing, the preference profiles obtaining each user comprises:
The proportion of homogeneous object shared by the object of each descriptor feature described in the descriptor feature calculation of the object of the object information acquisition effective historical operation of user according to the effective historical operation of user;
The descriptor feature-set that the proportion of homogeneous object shared by described object is greater than the first predetermined threshold value is the preference profiles of described user.
In the application one embodiment, described users personal data storehouse also comprises operation and revises database, role's label of effective historical operation all previous correction of data comprise user of described user;
Role's label that the described preference profiles by each user is set to each user comprises:
Each descriptor feature in described preference profiles is multiplied by the first weighted value;
Each descriptor feature in role's label of described all previous correction is multiplied by the 2nd weighted value;
The cumulative each descriptor characteristic sum being multiplied by the first weighted value is multiplied by each descriptor feature of the 2nd weighted value, and the descriptor feature that weight accumulation is greater than the 2nd predetermined threshold value is set to role's label of user.
In the application one embodiment, role's label of all previous correction of described user is the input instruction according to user, initiatively selects the role's label revised in default role's tag library.
In the application one embodiment, described first weighted value is adjust according to the role's label of user arranged and the similarity of described preference profiles;
Described 2nd weighted value is adjust according to the similarity of the role's label of user arranged and role's label of described all previous correction.
In the application one embodiment, described users personal data storehouse also comprises object feedback database, and effective historical operation data comprise user of described user is to the evaluation information of bought commodity;
The historical operation data comprise of described user is stored in described object feedback database user to the feedback information of operated object.
Role's label that the described preference profiles by each user is set to each user also comprises:
According to user, the feedback information of operated object and the object information fed back are obtained label adjustment information;
Described role's label is adjusted according to described label adjustment information.
The application also provides the user tag in a kind of infosystem to arrange device, and described device comprises:
Parsing module, for resolving users personal data storehouse, obtains effective historical operation data of each user;
Calculate module, for respectively effective historical operation data of described each user being carried out computing, obtain the preference profiles of each user;
Module being set, for the preference profiles of described each user being set to role's label of each user, transmitting the object information corresponding with described role's label by described role's label to subscription client.
In the application one embodiment, described users personal data storehouse comprises operation history data storehouse, the object information of effective historical operation of effective historical operation data comprise user of described user;
Described calculating module comprises:
Information obtainment unit, the object information for effectively operating according to user obtains the descriptor feature of the object that user effectively operates;
Proportion calculates unit, for calculating the proportion of homogeneous object shared by the object of described each descriptor feature;
Feature-set unit, the descriptor feature-set being greater than the first predetermined threshold value for the proportion of homogeneous object shared by described object is the preference profiles of described user.
In the application one embodiment, described users personal data storehouse also comprises operation and revises database, role's label of effective historical operation all previous correction of data comprise user of described user;
The described module that arranges comprises:
First weighted units, for being multiplied by the first weighted value by each descriptor feature in described preference profiles;
2nd weighted units, for being multiplied by the 2nd weighted value by each descriptor feature in role's label of described all previous correction;
Weighting adds up unit, is multiplied by each descriptor feature of the 2nd weighted value for the cumulative each descriptor characteristic sum being multiplied by the first weighted value, and the descriptor feature that weight accumulation is greater than the 2nd predetermined threshold value is set to role's label of user.
In the application one embodiment, role's label of all previous correction of described user is the input instruction according to user, initiatively selects the role's label revised in default role's tag library.
In the application one embodiment, described first weighted value is adjust according to the role's label of user arranged and the similarity of described preference profiles;
Described 2nd weighted value is adjust according to the similarity of the role's label of user arranged and role's label of described all previous correction.
In the application one embodiment, described users personal data storehouse also comprises object feedback database, and effective historical operation data comprise user of described user is to the evaluation information of bought commodity;
The historical operation data comprise of described user is stored in described object feedback database user to the feedback information of operated object.
The described module that arranges also comprises:
Fine setting obtaining unit, for obtaining label adjustment information according to user to the evaluation information of operated object and the object information fed back;
Label adjustment unit, for adjusting described role's label according to described label adjustment information.
From above technical scheme, the application resolves users personal data storehouse, obtains effective historical operation data of each user, and respectively effective historical operation data of described each user is carried out computing, obtains the preference profiles of each user. The preference profiles of described each user is set to role's label of each user by the application, by described role's label, the object information meeting demand is sent to subscription client. Thus the role's label connection object information according to user that realizes is to subscription client, save the time that user carries out object search, allow user select to meet the object of demand more accurately, also help the network platform accurately to suitable subscription client sending object information. The application reduces the time cost that user carries out object search, increases the validity of Object Operations, reduces the probability that object is changed, improves platform efficiency and Consumer's Experience.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present application or technical scheme of the prior art, it is briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, the accompanying drawing that the following describes is only some embodiments recorded in the application, for those of ordinary skill in the art, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the schema of user tag method to set up one embodiment in the application's infosystem;
Fig. 2 is the schema of step S2 in user tag method to set up one embodiment in the application's infosystem;
Fig. 3 is the schema of step S3 in another embodiment of user tag method to set up in the application's infosystem;
Fig. 4 is the schema of step S3 in the user tag method to set up another embodiment in the application's infosystem;
Fig. 5 is the structure iron that the user tag in the application's infosystem arranges device one embodiment;
Fig. 6 is that the user tag in the application's infosystem arranges the structure iron calculating module in device one embodiment;
Fig. 7 is that the user tag in the application's infosystem arranges the structure iron arranging module in another embodiment of device;
Fig. 8 is that the user tag in the application's infosystem arranges the structure iron arranging module in device another embodiment.
Embodiment
The application resolves users personal data storehouse, obtains effective historical operation data of each user, and respectively effective historical operation data of described each user is carried out computing, obtains the preference profiles of each user. The preference profiles of described each user is set to role's label of each user by the application, by described role's label, the object information meeting demand is sent to subscription client. Thus realize the role's label according to user, automatic sending object information is to subscription client, save the time that user carries out object search, allow user select to meet the object of demand more accurately, also help the network platform accurately to suitable subscription client sending object information. The application reduces the time cost that user carries out Object Selection, increases the validity of Object Operations, reduces the probability that object is changed, improves platform efficiency and Consumer's Experience.
Certainly, any technology scheme implementing the application must not necessarily need to reach above-described all advantages simultaneously.
In order to make those skilled in the art understand the technical scheme in the application better, below in conjunction with the accompanying drawing in the embodiment of the present application, technical scheme in the embodiment of the present application is clearly and completely described, obviously, described embodiment is only some embodiments of the present application, instead of whole embodiments. Based on the embodiment in the application, other embodiments all that those of ordinary skill in the art obtain, all should belong to the scope of the application's protection.
User tag method to set up in a kind of infosystem that the embodiment of the present application provides, is applied in the Distributed Services system of infosystem. Each database in the application's device can be stored in database server, and each function module can be stored in Control Server. Certainly, the application's each function module and database can be stored in same or different server respectively, carry out selecting arranging according to demand by those skilled in the art.
Referring to Fig. 1, method described in the application one embodiment comprises:
S1, parsing users personal data storehouse, obtain effective historical operation data of each user.
In the application one specific implementation, user's logging in network platform carries out Object Operations, the historical operation data of described user are all stored in users personal data storehouse, and described users personal data storehouse is generally held in the different server in the Distributed Services system of infosystem. User's historical operation data in the users personal data storehouse preserved in different server, by on-line operation, are resolved, are obtained effective historical operation data of each user by the application's infosystem. Described effective historical operation data refer to get rid of user misoperation, the historical operation data of the service datas such as object replacement.
Specifically, described in the application, users personal data storehouse comprises operation history data storehouse.
The object information of effective operation of the user that effective historical operation data comprise of described user is stored in described operation history data storehouse.
Effective operation object information of described user generally includes the descriptor of number of objects that user operated and object, the information such as the size of described object factory information object, style and operation module.
Wherein, the size of object can refer to the size of clothes, such as the size of S code, M code, L code etc. or shoes, such as 35 yards etc. Wherein, the style of object is often referred to quality (linen-cotton, silk, snow spin), design feature (gentlewoman, pseudo-classic, fashion etc.), quality (high-quality, low-quality etc.) and brand etc. Wherein, operation module is often referred to each operation module of the network platform, and such as Taobao website comprises a day cat, Taobao, everyday special price, gathers shopping modules such as calculating.
S2, respectively effective historical operation data of described each user are carried out computing, obtain the preference profiles of each user.
Specifically, referring to Fig. 2, described step S2 comprises:
S21, the object information effectively operated according to user obtain the descriptor feature of the object that user effectively operates.
The information such as size according to object, style and operation module, obtain the descriptor features such as the size of the object that user had operated, style and operation module. Such as, user operation 6 pairs of shoes, 5 pairs is 35 yards, and 1 pair is 36 yards, then the size descriptor of the shoes of user is characterized as " 35 yards " and " 36 yards ".
The proportion of homogeneous object shared by S22, the object calculating described each descriptor feature.
The object information operated is classified according to the attribute of object, such as shoes, clothes, case and bag, electronic product etc.Respectively for the quantity of object of descriptor feature each in every class object, the total quantity of the object operated by calculating and object. The proportion of the object total quantity of the number of objects of each descriptor feature of calculating operation its place shared classification.
Such as, in specific implementation, user have purchased 6 pairs of shoes, 5 pairs is 35 yards, 1 pair is 36 yards, then the shared total proportion buying shoes of the shoes of " 35 yards " descriptor feature is 83%, and the shared total proportion buying shoes of the shoes of " 36 yards " descriptor feature is 17%.
S23, the descriptor feature-set that the proportion of homogeneous object shared by described object is greater than the first predetermined threshold value are the preference profiles of described user.
As shared by the object of described descriptor feature, the proportion of the homogeneous object of operation exceedes predetermined threshold value, then the object of descriptor feature described in user preference is described, namely the object of described descriptor feature is applicable to user. Therefore, by described descriptor feature-set it is the preference profiles of described user.
Described first predetermined threshold value is set as required by those of ordinary skill in the art, is usually set as 50%. In above-mentioned example, it is the preference profiles of user by " 35 yards " descriptor feature-set.
S3, preference profiles by described each user are set to role's label of each user, by described role's label to the subscription client transmission object information corresponding with described role's label.
The preference profiles of user is the historical operation data acquisition by user, is obtain according to user's historical operation behavioural analysis. The preference profiles of each user is set to role's label of each user by the application, thus when user operation object, according to set role's label to subscription client sending object information, save the time that user carries out object search, allow user select to meet the object of oneself demand more accurately, also help the network platform accurately to suitable subscription client sending object information. The application reduces the time cost that user carries out object search, increases the validity of Object Operations, reduces the probability that object is changed, improves platform efficiency and customer experience.
Method described in another embodiment of the application still comprises above-mentioned steps S1-S3, and users personal data storehouse described in it is except operation history data storehouse, also comprises operation and revises database.
The historical operation data comprise of described user is stored in role's label that all previous correction of user in data is revised in described operation.
Specifically, user can revise the role's label of oneself according to demand, namely according to the input instruction of user, initiatively selects the role's label revised in default role's tag library. Described role's tag library comprises at least one label keyword, and described label keyword is the descriptor feature of object, such as, leisure style dress, just fills class clothes etc. Role's label that user selects can be used for replacing the role's label arranged for user, also can be used as the role's label newly increased.
Such as, the existing role's label of user is for just filling class clothes, and this purchase of user wishes to buy leisure clothes, then user can click leisure clothes in role's tag library by input instruction and replace the original role's label just filling class clothes. The operation correction database of described user preserves the role's label just filling class clothes that user replaces.
Referring to Fig. 3, described step S3 comprises in the embodiment of the present application:
S31, each descriptor feature in described preference profiles is multiplied by the first weighted value.
S32, each descriptor feature in role's label of described all previous correction is multiplied by the 2nd weighted value.
S33, the cumulative each descriptor characteristic sum being multiplied by the first weighted value are multiplied by each descriptor feature of the 2nd weighted value, and the descriptor feature that weight accumulation is greater than the 2nd predetermined threshold value is set to role's label of user.
Effective historical operation operation information that each descriptor feature in described preference profiles is the user in the historical operation information storage according to user obtains, that is each descriptor feature in described preference profiles be user historical operation object in the descriptor feature of object of institute's preference. And role's label of all previous correction be user as required at role's label of all previous active correction before operation, this role's label is the descriptor feature of object of user's expectation operation.
The initial value of described first weighted value and the 2nd weighted value is set as required by those of ordinary skill in the art, is usually set as 50%. The degree of approximation of role's label of the more described setting of the application's infosystem and role's label of preference profiles and all previous correction, adjusts described first weighted value and described 2nd weighted value according to the described degree of approximation. If role's label of described setting is more close to preference profiles, then heighten described first weighted value, turn down described 2nd weighted value. If role's label of described setting is more close to role's label of all previous correction, then turn down described first weighted value, heighten described 2nd weighted value.
Described 2nd predetermined threshold value is set as required by those of ordinary skill in the art, is usually set as 50%.
In another specific implementation of the application, as described preference profiles comprises descriptor feature: " just filling style dress ", " brand ", " high-grade fabric ". Role's label of described all previous correction comprises descriptor feature: " leisure style dress ", " brand ", " motion ". Described first weighted value is set as 70%, and the 2nd weighted value is set as 30%. Each descriptor feature is weighted and obtains after adding up: " just filling style dress " 70%, " leisure style dress " 30%, " brand " 100%, " high-grade fabric " 70%, " motion " 30%. If described 2nd predetermined threshold value is 50%, then " will just fill style dress ", " brand ", " high-grade fabric " be set as user role's label.
The present embodiment can arrange role's label of user with reference to role's label comprehensive consideration of the preference profiles of the historical operation data acquisition according to user and all previous correction of user. The application according to the similarity of role's label and role's label of preference profiles and all previous correction, can adjust both weighted values, thus the role's label making acquisition meets the actual demand of user operation more further. The application to subscription client sending object information according to set role's label, saves the time that user carries out object search, allows user select to meet the object of demand more accurately, also helps network platform sending object information to subscription client. The application reduces the time cost that user carries out object search, increases the validity of Object Operations, improves platform efficiency and customer experience.
Method described in another embodiment of the application still comprises above-mentioned steps S1-S3, and described in it, users personal data storehouse also comprises object feedback database.
The historical operation data comprise of described user is stored in described object feedback database user to the feedback information of operated object.
Referring to Fig. 4, role's label that the preference profiles by each user in step S3 described in the application is set to each user also comprises:
S34, according to user, the evaluation information of operated object and the object information evaluated are obtained label adjustment information.
In the application's specific implementation, being fed back by operated object after user operation object, described feedback generally includes that object size is bigger than normal or less than normal, the quality etc. of object style and object. The application can obtain label adjustment information according to described object feedback in conjunction with object information. Such as, in object information, the number of shoes is No. 35, and user is evaluated as partially fertile, then can obtain label adjustment information is " 35 yards of partially thin shoes ".
S35, adjust described role's label according to described label adjustment information.
The application's label adjustment information obtains for the evaluation of operated object according to user, according to label adjustment information adjust described role's label can make adjustment after role's label more meet the demand of user. Such as, adjusting role's label " 35 yards " according to label adjustment information " 35 yards partially thin " in upper example, the role's label after adjustment is " 35 yards partially thin ".
The present embodiment, according to the role label of user for the further adjustment user of feedback of operated object, makes described role's label more meet the demand of user. The application according to set role's label to subscription client sending object information, save the time that user carries out object search, allow user select to meet the object of oneself demand more accurately, also help the network platform that the object information meeting demand is sent to subscription client. The application reduces the time cost that user carries out object search, increases the validity of Object Operations, reduces the probability that object is changed, improves platform efficiency and customer experience.
Corresponding to aforesaid method, the application also provides the user tag in a kind of infosystem to arrange device, is applied in the Distributed Services system of infosystem. Each database in the application's device can be stored in database server, and each function module can be stored in Control Server. Certainly, the application's each function module and database can be stored in same or different server respectively, carry out selecting arranging according to demand by those skilled in the art.
Referring to Fig. 5, device 5 described in the application one embodiment comprises:
Parsing module 51, for resolving users personal data storehouse, obtains effective historical operation data of each user;
Calculate module 52, for respectively effective historical operation data of described each user being carried out computing, obtain the preference profiles of each user;
Module 53 being set, for the preference profiles of described each user being set to role's label of each user, transmitting the object information corresponding with described role's label by described role's label to subscription client.
In the application one specific implementation, user's logging in network platform operations object, the historical operation data of described user are all stored in users personal data storehouse, and described users personal data storehouse is generally held in the different server in the Distributed Services system of infosystem. User's historical operation data in the users personal data storehouse preserved in different server, by on-line operation, are resolved, are obtained effective historical operation data of each user by the application's infosystem. Described effective historical operation data refer to get rid of user misoperation, the historical operation data of the service datas such as object replacing.
Specifically, described in the application, users personal data storehouse comprises operation history data storehouse.
Effective operation information of the user that effective historical operation data comprise of described user is stored in described operation history data storehouse.
Effective operation information of described user generally includes number of objects and the object factory information that user has operated, the information such as the size of described object factory information object, style and operation module. Wherein, the size of object is often referred to the size of clothes, such as the size of S code, M code, L code etc. or shoes, such as 35 yards etc. Wherein, the style of object is often referred to quality (linen-cotton, silk, snow spin), design feature (gentlewoman, pseudo-classic, fashion etc.), quality (high-quality, low-quality etc.) and brand etc. Wherein, operation module is often referred to each Sales module of shopping website, and such as Taobao website comprises a day cat, Taobao, everyday special price, gathers shopping modules such as calculating.
Specifically, referring to Fig. 6, described calculating module 52 comprises:
Information obtainment unit 521, the object information for effectively operating according to user obtains the descriptor feature of the object that user effectively operates.
Proportion calculates unit 522, for calculating the proportion of homogeneous object shared by the object of described each descriptor feature.
Feature-set unit 523, the descriptor feature-set being greater than the first predetermined threshold value for the proportion of homogeneous object shared by described object is the preference profiles of described user.
The present embodiment is according to size, the style of object and operates the information such as module, obtains size, the style of the object that user had operated and operates the descriptor features such as module. Such as, user operation 6 pairs of shoes, 5 pairs is 35 yards, and 1 pair is 36 yards, then the size descriptor of the shoes of user is characterized as " 35 yards " and " 36 yards ".
The object information operated is classified according to the attribute of object, such as shoes, clothes, case and bag, electronic product etc. Respectively for the quantity of object of descriptor feature each in every class object, the total quantity of the object operated by calculating and object. The proportion of the object total quantity of the number of objects of each descriptor feature of calculating operation its place shared classification.
Such as, user operation 6 pairs of shoes, 5 pairs is 35 yards, 1 pair is 36 yards, then the proportion of the shared total operation shoes of the shoes of " 35 yards " descriptor feature is 83%, and the proportion of the shared total operation shoes of the shoes of " 36 yards " descriptor feature is 17%.
As shared by the object of described descriptor feature, the proportion of the homogeneous object of operation exceedes predetermined threshold value, then the object of descriptor feature described in user preference is described, namely the object of described descriptor feature is applicable to user. Therefore, by described descriptor feature-set it is the preference profiles of described user.
Described first predetermined threshold value is set as required by those of ordinary skill in the art, is usually set as 50%. In above-mentioned example, it is the preference profiles of user by " 35 yards " descriptor feature-set.
The preference profiles of user is the historical operation data acquisition by user, is obtain according to user's historical operation behavioural analysis. The preference profiles of each user is set to role's label of each user by the application, thus when user operation object, according to set role's label to subscription client sending object information, save the time that user carries out object search, allow user select to meet the object of oneself demand more accurately, also help the network platform to suitable subscription client sending object information. The application reduces the time cost that user carries out object search, increases the validity of Object Operations, reduces the probability that object is changed, improves platform efficiency and customer experience.
Device described in another embodiment of the application still comprises above-mentioned module, and users personal data storehouse described in it is except operation history data storehouse, also comprises operation and revises database.
The historical operation data comprise of described user is stored in role's label that all previous correction of user in data is revised in described operation.
Specifically, user can revise the role's label of oneself according to demand, namely according to the input instruction of user, initiatively selects the role's label revised in default role's tag library. Described role's tag library comprises at least one label keyword, and described label keyword is the descriptor feature of object, such as, leisure style dress, just fills class clothes etc. Role's label that user selects can be used for replacing the role's label arranged for user, also can be used as the role's label newly increased.
Such as, the existing role's label of user is for just filling class clothes, and this purchase of user wishes to buy leisure clothes, then user can click leisure clothes in role's tag library by input instruction and replace the original role's label just filling class clothes. The purchase correction database of described user preserves the role's label just filling class clothes that user replaces.
Referring to Fig. 7, the described module 53 that arranges comprises in the embodiment of the present application:
First weighted units 531, for being multiplied by the first weighted value by each descriptor feature in described preference profiles.
2nd weighted units 532, for being multiplied by the 2nd weighted value by each descriptor feature in role's label of described all previous correction.
Weighting adds up unit 533, is multiplied by each descriptor feature of the 2nd weighted value for the cumulative each descriptor characteristic sum being multiplied by the first weighted value, and the descriptor feature that weight accumulation is greater than the 2nd predetermined threshold value is set to role's label of user.
Effective historical operation operation information that each descriptor feature in described preference profiles is the user in the historical operation information storage according to user obtains, that is each descriptor feature in described preference profiles be user historical operation object in the descriptor feature of object of institute's preference. And role's label of all previous correction be user as required at role's label of all previous active correction before operation, this role's label is the descriptor feature of object of user's expectation operation.
The initial value of described first weighted value and the 2nd weighted value is set as required by those of ordinary skill in the art, is usually set as 50%. The degree of approximation of role's label of the more described setting of the application's infosystem and role's label of preference profiles and all previous correction, adjusts described first weighted value and described 2nd weighted value according to the described degree of approximation. If role's label of described setting is more close to preference profiles, then heighten described first weighted value, turn down described 2nd weighted value. If role's label of described setting is more close to role's label of all previous correction, then turn down described first weighted value, heighten described 2nd weighted value.
Described 2nd predetermined threshold value is set as required by those of ordinary skill in the art, is usually set as 50%.
In another specific implementation of the application, as described preference profiles comprises descriptor feature: " just filling style dress ", " brand ", " high-grade fabric ". Role's label of described all previous correction comprises descriptor feature: " leisure style dress ", " brand ", " motion ". Described first weighted value is set as 70%, and the 2nd weighted value is set as 30%. Each descriptor feature is weighted and obtains after adding up: " just filling style dress " 70%, " leisure style dress " 30%, " brand " 100%, " high-grade fabric " 70%, " motion " 30%.If described 2nd predetermined threshold value is 50%, then " will just fill style dress ", " brand ", " high-grade fabric " be set as user role's label.
The present embodiment can arrange role's label of user with reference to role's label comprehensive consideration of the preference profiles of the historical operation data acquisition according to user and all previous correction of user. The application according to the similarity of role's label and role's label of preference profiles and all previous correction, can adjust both weighted values, thus the role's label making acquisition meets the actual demand of user operation more further. The application according to set role's label to subscription client sending object information, save the time that user carries out object search, allow user select to meet the object of oneself demand more accurately, also help the network platform to suitable subscription client sending object information. The application reduces the time cost that user carries out object search, increases the validity of Object Operations, reduces the probability that object is replaced, improves platform efficiency and customer experience.
Device described in another embodiment of the application still comprises above-mentioned module, and described in it, users personal data storehouse also comprises object feedback database.
The historical operation data comprise of described user is stored in described object feedback database user to the evaluation information of operated object.
Referring to Fig. 8, module 53 is set described in the application and also comprises:
Fine setting obtaining unit 534, for obtaining label adjustment information according to user to the feedback information of operated object and the object information fed back.
Label adjustment unit 535, for adjusting described role's label according to described label adjustment information.
In the application's specific implementation, being fed back by operated object after user operation object, described feedback generally includes that object size is bigger than normal or less than normal, the quality etc. of object style and object. The application can obtain label adjustment information according to described object evaluation in conjunction with object information. Such as, in object information, the number of shoes is No. 35, and user is evaluated as partially fertile, then can obtain label adjustment information is " 35 yards of partially thin shoes ".
The application's label adjustment information obtains for the evaluation of operated object according to user, according to label adjustment information adjust described role's label can make adjustment after role's label more meet the demand of user. Such as, adjusting role's label " 35 yards " according to label adjustment information " 35 yards partially thin " in upper example, the role's label after adjustment is " 35 yards partially thin ".
The present embodiment, according to the role label of user for the further adjustment user of feedback of operated object, makes described role's label more meet the demand of user. The application according to set role's label to subscription client sending object information, save the time that user carries out object search, allow user select to meet the object of oneself demand more accurately, also help the network platform to suitable subscription client sending object information. The application reduces the time cost that user carries out object search, increases the validity of Object Operations, reduces the probability that object is changed, improves platform efficiency and customer experience.
Illustrate that the application realizes further below by an embody rule scene of the embodiment of the present application.
User operates 8 objects by the application's infosystem, and object information is respectively: just filling wool Western-style clothes jacket S code/1, positive fitted lining shirt S code/3, slacks M code/1, leather shoes 35 yards/2 pairs, sports shoes 36 yards/1 pair.Described object information is stored in operation history data storehouse.
The application's infosystem resolves described operation history data storehouse, obtains the object information of effective historical operation of user, is namely just filling wool Western-style clothes jacket S code/1, positive fitted lining shirt S code/3, slacks M code/1, leather shoes 35 yards/2 pairs, sports shoes 36 yards/1 pair.
The characteristic information " just filling " of the object of acquisition user operation, " S code ", " M code ", " 35 yards ", " 36 yards " " leather shoes ", " sports shoes ". Calculating the proportion of homogeneous object shared by the object of described each descriptor feature, " just filling " is 80%, and " Sportswear " is 20%, " S code " is 80%, and " M code " is 20%, and " leather shoes " are 67%, " sports shoes " is 33%, and " 35 yards " are 67%, and " 36 yards " are 33%.
If the first predetermined threshold value is 50%, then " just fill ", preference profiles that " S code ", " leather shoes ", " 35 yards " are set as described user.
To " just fill ", role's label that " S code ", " leather shoes ", " 35 yards " are set to each user, by described role's label to subscription client sending object information.
When user operation object, according to set role's label " just filling ", " S code ", " leather shoes ", " 35 yards " to subscription client sending object information, save the time that user carries out object search, allow user select to meet the object of oneself demand more accurately, also help the subscription client sending object information that the network platform finds oneself suitable. The application reduces the time cost that user carries out object search, increases the validity of Object Operations, reduces the probability that object is changed, improves platform efficiency and customer experience.
In the Another Application scene of the application, operational movement class clothes are wished in this operation of described user, user's active diagonal angle colour code label are revised, and initiatively select " Sportswear ", " sports shoes " to replace role's label " just filling ", " leather shoes " in default role's tag library. The role's label " Sportswear " revised, " sports shoes " according to role's label " just filling " of this correction, " leather shoes " to subscription client sending object information, and can be saved in operation and revise data by user.
When user carries out Object Operations by the application's infosystem again, each descriptor feature " just filling " in described preference profiles, " S code ", " leather shoes ", " 35 yards " are multiplied by the first weighted value 70%, each descriptor feature " Sportswear " in role's label of described all previous correction, " sports shoes " are multiplied by the 2nd weighted value and are multiplied by the first weighted value 30%. Weight accumulation and the 2nd predetermined threshold value 50% according to both compare, and obtain " just filling ", " S code ", " leather shoes ", " 35 yards " as role's label.
Role's label and the preference profiles similarity of the application's setting are higher, and to adjust the first weighted value be the 80%, two weighted value is 20%.
Like this, set angle colour code label can be carried out with reference to the amendment of user diagonal angle colour code label, role's label of order setting meets the hobby of user more, better to subscription client sending object information, save the time that user carries out object search further, allow user select to meet the object of oneself demand more accurately, also help the subscription client sending object information that the network platform precisely finds oneself suitable.
The application again one application scene in, preserve user to the evaluation of operated object in object feedback database.The evaluation information of operated object and the object information evaluated are obtained label adjustment information according to user by the application's infosystem. User aligns dress wool Western-style clothes jacket S code/1, being evaluated as " suitable " of positive fitted lining shirt S code/3, the evaluation of leather shoes 35 yards/2 pairs is " partially thin ", to being evaluated as " suitable " of slacks M code/1 and sports shoes 36 yards/1 pair. The label adjustment information of described " leather shoes " is " partially fertile ", then adjust according to described label adjustment information " partially fertile " diagonal angle colour code label " 35 yards ", and set angle colour code label are " 35 yards partially fertile ".
Thus realize making described role's label more meet the demand of user according to the role's label evaluating further adjustment user of user for operated object.
The device that the embodiment of the application provides realizes by computer program. Those skilled in the art should be understood that; above-mentioned unit and Module Division mode are only the one in numerous dividing mode; if being divided into other unit or module or non-divided block, as long as information object has above-mentioned functions, all should within the protection domain of the application.
It will be understood by those skilled in the art that, the embodiment of the application can be provided as method, device (equipment) or computer program. Therefore, the application can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect. And, the application can adopt the form at one or more upper computer program implemented of computer-usable storage medium (including but not limited to multiple head unit, CD-ROM, optical memory etc.) wherein including computer usable program code.
The application is that schema and/or skeleton diagram with reference to the method according to the embodiment of the present application, device (equipment) and computer program describe. Should understand can by the combination of the flow process in each flow process in computer program instructions flowchart and/or skeleton diagram and/or square frame and schema and/or skeleton diagram and/or square frame. These computer program instructions can be provided to the treater of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine so that the instruction performed by the treater of computer or other programmable data processing device is produced for realizing the device of function specified in schema flow process or multiple flow process and/or skeleton diagram square frame or multiple square frame.
These computer program instructions also can be stored in and can guide in computer-readable memory that computer or other programmable data processing device work in a specific way, making the instruction that is stored in this computer-readable memory produce the manufacture comprising instruction device, this instruction device realizes the function specified in schema flow process or multiple flow process and/or skeleton diagram square frame or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform a series of operation steps to produce computer implemented process, thus the instruction performed on computer or other programmable devices is provided for realizing the step of the function specified in schema flow process or multiple flow process and/or skeleton diagram square frame or multiple square frame.
Although having described the preferred embodiment of the application, but those skilled in the art once the substantially creative concept of cicada, then these embodiments can be made other change and amendment.Therefore, it is intended that the appended claims shall be construed comprise preferred embodiment and fall into all changes and the amendment of the application's scope. Obviously, the application can be carried out various change and modification and not depart from the spirit and scope of the application by the technician of this area. Like this, if these amendments of the application and modification belong within the scope of the application's claim and equivalent technologies thereof, then the application also is intended to comprise these change and modification.
Claims (12)
1. the user tag method to set up in an infosystem, it is characterised in that, described method comprises:
Resolve users personal data storehouse, obtain effective historical operation data of each user;
Respectively effective historical operation data of described each user are carried out computing, obtain the preference profiles of each user;
Role's label that the preference profiles of described each user is set to each user, transmits the object information corresponding with described role's label by described role's label to subscription client.
2. method according to claim 1, it is characterised in that, described users personal data storehouse comprises operation history data storehouse, the object information of effective historical operation of effective historical operation data comprise user of described user;
Described respectively effective historical operation data of each user being carried out computing, the preference profiles obtaining each user comprises:
The proportion of homogeneous object shared by the object of each descriptor feature described in the descriptor feature calculation of the object of the object information acquisition effective historical operation of user according to the effective historical operation of user;
The descriptor feature-set that the proportion of homogeneous object shared by described object is greater than the first predetermined threshold value is the preference profiles of described user.
3. method according to claim 2, it is characterised in that, described users personal data storehouse also comprises operation and revises database, role's label of effective historical operation all previous correction of data comprise user of described user;
Role's label that the described preference profiles by each user is set to each user comprises:
Each descriptor feature in described preference profiles is multiplied by the first weighted value;
Each descriptor feature in role's label of described all previous correction is multiplied by the 2nd weighted value;
The cumulative each descriptor characteristic sum being multiplied by the first weighted value is multiplied by each descriptor feature of the 2nd weighted value, and the descriptor feature that weight accumulation is greater than the 2nd predetermined threshold value is set to role's label of user.
4. method according to claim 3, it is characterised in that, role's label of all previous correction of described user is the input instruction according to user, initiatively selects the role's label revised in default role's tag library.
5. method according to claim 3, it is characterised in that, described first weighted value is adjust according to the role's label of user arranged and the similarity of described preference profiles;
Described 2nd weighted value is adjust according to the similarity of the role's label of user arranged and role's label of described all previous correction.
6. according to the method in claim 2 or 3, it is characterised in that, described users personal data storehouse also comprises object feedback database, and effective historical operation data comprise user of described user is to the evaluation information of bought commodity;
The historical operation data comprise of described user is stored in described object feedback database user to the feedback information of operated object.
Role's label that the described preference profiles by each user is set to each user also comprises:
According to user, the feedback information of operated object and the object information fed back are obtained label adjustment information;
Described role's label is adjusted according to described label adjustment information.
7. the user tag in an infosystem arranges device, it is characterised in that, described device comprises:
Parsing module, for resolving users personal data storehouse, obtains effective historical operation data of each user;
Calculate module, for respectively effective historical operation data of described each user being carried out computing, obtain the preference profiles of each user;
Module being set, for the preference profiles of described each user being set to role's label of each user, transmitting the object information corresponding with described role's label by described role's label to subscription client.
8. device according to claim 7, it is characterised in that, described users personal data storehouse comprises operation history data storehouse, the object information of effective historical operation of effective historical operation data comprise user of described user;
Described calculating module comprises:
Information obtainment unit, the object information for effectively operating according to user obtains the descriptor feature of the object that user effectively operates;
Proportion calculates unit, for calculating the proportion of homogeneous object shared by the object of described each descriptor feature;
Feature-set unit, the descriptor feature-set being greater than the first predetermined threshold value for the proportion of homogeneous object shared by described object is the preference profiles of described user.
9. device according to claim 8, it is characterised in that, described users personal data storehouse also comprises operation and revises database, role's label of effective historical operation all previous correction of data comprise user of described user;
The described module that arranges comprises:
First weighted units, for being multiplied by the first weighted value by each descriptor feature in described preference profiles;
2nd weighted units, for being multiplied by the 2nd weighted value by each descriptor feature in role's label of described all previous correction;
Weighting adds up unit, is multiplied by each descriptor feature of the 2nd weighted value for the cumulative each descriptor characteristic sum being multiplied by the first weighted value, and the descriptor feature that weight accumulation is greater than the 2nd predetermined threshold value is set to role's label of user.
10. device according to claim 9, it is characterised in that, role's label of all previous correction of described user is the input instruction according to user, initiatively selects the role's label revised in default role's tag library.
11. devices according to claim 9, it is characterised in that, described first weighted value is adjust according to the role's label of user arranged and the similarity of described preference profiles;
Described 2nd weighted value is adjust according to the similarity of the role's label of user arranged and role's label of described all previous correction.
12. devices according to claim 7 or 8, it is characterised in that, described users personal data storehouse also comprises object feedback database, and effective historical operation data comprise user of described user is to the evaluation information of bought commodity;
The historical operation data comprise of described user is stored in described object feedback database user to the feedback information of operated object.
The described module that arranges also comprises:
Fine setting obtaining unit, for obtaining label adjustment information according to user to the evaluation information of operated object and the object information fed back;
Label adjustment unit, for adjusting described role's label according to described label adjustment information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410643929.6A CN105653543A (en) | 2014-11-11 | 2014-11-11 | Method and device for setting user label in information system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410643929.6A CN105653543A (en) | 2014-11-11 | 2014-11-11 | Method and device for setting user label in information system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105653543A true CN105653543A (en) | 2016-06-08 |
Family
ID=56479580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410643929.6A Pending CN105653543A (en) | 2014-11-11 | 2014-11-11 | Method and device for setting user label in information system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105653543A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106131688A (en) * | 2016-07-25 | 2016-11-16 | 黄新勇 | The individual character display packing of historical operation and system |
| CN107798543A (en) * | 2016-12-15 | 2018-03-13 | 平安科技（深圳）有限公司 | A kind of scheme intelligent Matching method and apparatus |
| CN109951512A (en) * | 2019-01-09 | 2019-06-28 | 平安科技（深圳）有限公司 | User preference determines method, system, electronic equipment and storage medium |
| CN110968765A (en) * | 2019-12-04 | 2020-04-07 | 掌阅科技股份有限公司 | Book searching method, computing device and computer storage medium |
| CN112862327A (en) * | 2021-02-19 | 2021-05-28 | 杭州拼便宜网络科技有限公司 | Service label generation method, device and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070061332A1 (en) * | 2005-09-14 | 2007-03-15 | Jorey Ramer | User history influenced search results |
| CN101271558A (en) * | 2008-05-16 | 2008-09-24 | 华东师范大学 | Multi-policy commercial product recommending system based on context information |
| CN102254028A (en) * | 2011-07-22 | 2011-11-23 | 青岛理工大学 | Personalized commodity recommendation method and system integrating attributes and structural similarity |
| CN102306298A (en) * | 2011-07-19 | 2012-01-04 | 北京航空航天大学 | Wiki-based dynamic evolution method of image classification system |
| CN102567511A (en) * | 2011-12-27 | 2012-07-11 | 奇智软件（北京）有限公司 | Method and device for automatically recommending application |
| CN103914550A (en) * | 2014-04-11 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Recommended content displaying method and recommended content displaying device |
-
2014
- 2014-11-11 CN CN201410643929.6A patent/CN105653543A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070061332A1 (en) * | 2005-09-14 | 2007-03-15 | Jorey Ramer | User history influenced search results |
| CN101271558A (en) * | 2008-05-16 | 2008-09-24 | 华东师范大学 | Multi-policy commercial product recommending system based on context information |
| CN102306298A (en) * | 2011-07-19 | 2012-01-04 | 北京航空航天大学 | Wiki-based dynamic evolution method of image classification system |
| CN102254028A (en) * | 2011-07-22 | 2011-11-23 | 青岛理工大学 | Personalized commodity recommendation method and system integrating attributes and structural similarity |
| CN102567511A (en) * | 2011-12-27 | 2012-07-11 | 奇智软件（北京）有限公司 | Method and device for automatically recommending application |
| CN103914550A (en) * | 2014-04-11 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Recommended content displaying method and recommended content displaying device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106131688A (en) * | 2016-07-25 | 2016-11-16 | 黄新勇 | The individual character display packing of historical operation and system |
| CN107798543A (en) * | 2016-12-15 | 2018-03-13 | 平安科技（深圳）有限公司 | A kind of scheme intelligent Matching method and apparatus |
| CN109951512A (en) * | 2019-01-09 | 2019-06-28 | 平安科技（深圳）有限公司 | User preference determines method, system, electronic equipment and storage medium |
| CN109951512B (en) * | 2019-01-09 | 2022-01-28 | 平安科技（深圳）有限公司 | User preference determination method, system, electronic device and storage medium |
| CN110968765A (en) * | 2019-12-04 | 2020-04-07 | 掌阅科技股份有限公司 | Book searching method, computing device and computer storage medium |
| CN110968765B (en) * | 2019-12-04 | 2020-09-22 | 掌阅科技股份有限公司 | Book searching method, computing device and computer storage medium |
| CN112862327A (en) * | 2021-02-19 | 2021-05-28 | 杭州拼便宜网络科技有限公司 | Service label generation method, device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230421661A1 (en) | System for prefetching digital tags | |
| US11205218B2 (en) | Client user interface activity affinity scoring and tracking | |
| Costa-Montenegro et al. | Which App? A recommender system of applications in markets: Implementation of the service for monitoring users’ interaction | |
| CN110647921B (en) | User behavior prediction method, device, equipment and storage medium | |
| CN105653543A (en) | Method and device for setting user label in information system | |
| CN112307344B (en) | Object recommendation model, object recommendation method and device and electronic equipment | |
| CN106372961A (en) | Commodity recommendation method and device | |
| US20190012719A1 (en) | Scoring candidates for set recommendation problems | |
| Liu et al. | Balancing between accuracy and fairness for interactive recommendation with reinforcement learning | |
| CN108446297B (en) | Recommendation method and device and electronic equipment | |
| US12086820B2 (en) | Technology opportunity mapping | |
| CN103729775A (en) | Method and system for recommending product information | |
| CN111353843B (en) | Commodity pushing method, device and system | |
| JP2016042297A (en) | Learning device, learning method, and learning program | |
| CN112000326A (en) | Service providing method and device, electronic equipment and storage medium | |
| CN104239421A (en) | Method and system for pushing application to terminal | |
| US20150161549A1 (en) | Predicting outcomes of a modeled system using dynamic features adjustment | |
| CN118014684A (en) | Commodity recommendation method and system based on big data and artificial intelligence | |
| Choi et al. | Quality evaluation and best service choice for cloud computing based on user preference and weights of attributes using the analytic network process | |
| AU2019200721B2 (en) | Online training and update of factorization machines using alternating least squares optimization | |
| CN113570440A (en) | Information pushing method based on electronic commerce big data and electronic commerce system | |
| US9348613B2 (en) | User context and behavior based user interface recommendation | |
| KR102349825B1 (en) | Product purchase recommendation time calculation method for member of shopping mall related to e-commerce, apparatus and system using said method | |
| KR102576123B1 (en) | Product marketing linkage system and method | |
| US11928719B2 (en) | Facilitating user selection using trend-based joint embeddings |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201010 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20201010 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160608 |