CN108470023A - The recommendation method and device of business function - Google Patents
The recommendation method and device of business function Download PDFInfo
- Publication number
- CN108470023A CN108470023A CN201810050532.4A CN201810050532A CN108470023A CN 108470023 A CN108470023 A CN 108470023A CN 201810050532 A CN201810050532 A CN 201810050532A CN 108470023 A CN108470023 A CN 108470023A
- Authority
- CN
- China
- Prior art keywords
- user
- business
- business function
- feature
- feedback 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
- G06F16/337—Profile generation, learning or modification
-
- 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
-
- 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
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment that this specification discloses provides a kind of business function recommendation method.This method includes：The feedback information that user uses business is obtained, and determines user's public sentiment feature of user according to feedback information.The user property feature of user is obtained, and user's Figure Characteristics are determined according to user's public sentiment feature and user property feature.Then, the alternative business function for obtaining business determines the business function to match with user's Figure Characteristics from alternative business function, and using the business function as business function recommended to the user.
Description
Technical field
Multiple embodiments that this specification discloses are related to Internet technical field more particularly to a kind of recommendation of business function
Method and device.
Background technology
With the development of Internet technology, people more and more continually use the multinomial business that the network platform is released.For example,
The fee payment service provided using electronic bill payment platform, or the shopping service etc. that is provided using shopping at network platform.Currently, network
When platform provides a certain business to its all user, usually only a kind of business model.
But different user usually has more or less difference, single business to the use demand of same item business
Pattern cannot meet the diversified demand of user.Accordingly, it is desirable to provide a kind of more reasonably method, network is used to meet user
A variety of demands when the business that platform provides.
Invention content
Present specification describes a kind of recommendation method and devices of the business function of processing user, and business is used according to user
User's public sentiment feature for determining of feedback information, reconstruct user's Figure Characteristics of the user, and from the alternative business work(of the business
The determining and matched business function of user's Figure Characteristics in energy recommends personalized business function to user to realize.
In a first aspect, providing a kind of recommendation method of business function.This method includes：
The feedback information that user uses business is obtained, and determines user's public sentiment of the user according to the feedback information
Feature；
Obtain the user property feature of the user；
User's Figure Characteristics are determined according to user's public sentiment feature and the user property feature；
Obtain the alternative business function of the business；
Determine the business function to match with user's Figure Characteristics from the alternative business function, and by the business
Function is as the business function recommended to the user.
It is described to determine that user's public sentiment of the user is special according to the feedback information in a kind of possible embodiment
Sign, including：
Semantic analysis and/or sentiment analysis are carried out to the feedback information；
According to the semantic analysis and/or the analysis result of sentiment analysis, user's public sentiment feature is determined.
In a kind of possible embodiment, the feedback information includes the user identifier of the user, the acquisition institute
The user property feature of user is stated, including：
According to the user identifier, the user property feature of the user is obtained from user property feature database.
In a kind of possible embodiment, the feedback information includes the service identification of the business, the acquisition institute
The alternative business function of business is stated, including：
According to the service identification, the alternative business function of the business is obtained from business function library.
It is described to be determined and user's Figure Characteristics from the alternative business function in a kind of possible embodiment
The business function to match, including：
According to the mapping relations of the pre-stored alternative business function and user's Figure Characteristics, determine with it is described
The business function that user's Figure Characteristics match.
It is described to be determined and user's Figure Characteristics from the alternative business function in a kind of possible embodiment
The business function to match, including：
Using Feature Correspondence Algorithm, the industry to match with user's Figure Characteristics is determined from the alternative business function
Business function.
In a kind of possible embodiment, the user property feature include natural quality feature, social property feature,
At least one of service attribute feature and Regional Property feature.
Second aspect provides a kind of recommendation apparatus of business function.The device includes：
First acquisition unit uses the feedback information of business for obtaining user；
First determination unit, user's public sentiment feature for determining the user according to the feedback information；
Second acquisition unit, the user property feature for obtaining the user；
Second determination unit, for determining that the user draws according to user's public sentiment feature and the user property feature
As feature；
Third acquiring unit, the alternative business function for obtaining the business；
Processing unit, for determining the business work(to match with user's Figure Characteristics from the alternative business function
Can, and using the business function as the business function recommended to the user.
In a kind of possible design, first determination unit includes：
Subelement is analyzed, for carrying out semantic analysis and/or sentiment analysis to the feedback information；
Determination subelement determines the user carriage for the analysis result according to the semantic analysis and/or sentiment analysis
Feelings feature.
In a kind of possible design, the feedback information that the first acquisition unit obtains includes user's mark of the user
Know, the second acquisition unit is specifically used for：
According to the user identifier, the user property feature of the user is obtained from user property feature database.
In a kind of possible design, the feedback information that the first acquisition unit obtains includes the business mark of the business
Know, the third acquiring unit is specifically used for：
According to the service identification, the alternative business function of the business is obtained from business function library.
In a kind of possible design, the processing unit is specifically used for：
According to the mapping relations of the pre-stored alternative business function and user's Figure Characteristics, determine with it is described
The business function that user's Figure Characteristics match.
In a kind of possible design, the processing unit is specifically used for：
Using Feature Correspondence Algorithm, the industry to match with user's Figure Characteristics is determined from the alternative business function
Business function.
In a kind of possible design, the user property feature that the second acquisition unit obtains includes natural quality spy
At least one of sign, social property feature, service attribute feature and Regional Property feature.
The third aspect provides a kind of computer readable storage medium, is stored thereon with computer program.When the calculating
When machine program executes in a computer, computer is enabled to execute the method that any embodiment provides in above-mentioned first aspect.
Fourth aspect provides a kind of computing device, including memory and processor.Being stored in the memory can hold
Line code when the processor executes the executable code, realizes any embodiment offer in above-mentioned first aspect
Method.
A kind of recommendation method and device for business function that this specification provides uses the feedback of business by obtaining user
Information, and determine according to feedback information user's public sentiment feature of the user.Then, according to user's public sentiment feature of user and obtaining
The user property feature taken determines user's Figure Characteristics.Then, it from the alternative business function of the business of acquisition, determines and uses
The business function that family Figure Characteristics match.Recommend personalized business function to user to realize, to meet different user
To the different demands of business.
Description of the drawings
In order to illustrate more clearly of the technical solution for multiple embodiments that this specification discloses, embodiment will be described below
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description be only this specification disclose
Multiple embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is that a kind of application scenarios of the recommendation method for business function that one embodiment that this specification discloses provides show
It is intended to；
Fig. 2 is a kind of flow chart of the recommendation method for business function that one embodiment that this specification discloses provides；
Fig. 3 is that the frame structure of a kind of user characteristics that one embodiment that this specification discloses provides and business function is shown
It is intended to；
Fig. 4 is a kind of recommendation page schematic diagram for business function that one embodiment that this specification discloses provides；
Fig. 5 is the recommendation page schematic diagram for another business function that one embodiment that this specification discloses provides；
Fig. 6 is the recommendation page schematic diagram for another business function that one embodiment that this specification discloses provides；
Fig. 7 is a kind of structure chart of the recommendation apparatus for business function that one embodiment that this specification discloses provides.
Specific implementation mode
Below in conjunction with the accompanying drawings, the multiple embodiments disclosed this specification are described.
Fig. 1 is that a kind of application scenarios of the recommendation method for business function that one embodiment that this specification discloses provides show
It is intended to.The executive agent of the recommendation method can be server.In Fig. 1, (e.g., server can answer server for Alipay
Server) can obtaining user, (terminal can set for fixed-line telephone, mobile phone, tablet computer, wearable intelligence by terminal
It is standby etc.) (e.g., feedback information can be use for feedback information when using business (e.g., business can be fee payment service, net purchase business)
Family applied by Alipay in customer service entrance feedack " why owe so more electricity charge ").
At this point it is possible to the recommendation method of the business function provided using multiple embodiments that this specification discloses, according to anti-
Feedforward information determines that (e.g., user's public sentiment feature may include the expectation of user " it is desirable that learning that expense is detailed for user's public sentiment feature of user
The emotion " feel uncertain, is dissatisfied " of feelings " and user).Meanwhile (e.g., user identifier can be according to the user identifier in feedback information
The Alipay account of user), from the user property feature database built in advance, (e.g., user property feature database may include multiple use
The user property feature of family or catergories of user) in obtain user user property feature (e.g., the user property feature of the user can
To include：Age, gender, occupation etc.), and determine that user draws a portrait according to user's public sentiment feature of the user and user property feature
(e.g., user's Figure Characteristics may include feature：" it is desirable that learning expense details ", " dissatisfied ", " 25 years old ", " man ", " programmer "
Deng).Also according to the service identification of the used business of the user in feedback information, (e.g., service identification can be the business to server
Unique number), alternative business function (e.g., the alternative business work(of the business of the business is obtained from alternative business function library
Can may include：The premium notice of brief version, the premium notice of detailed version, big font size premium notice and medium font size payment
Notice etc.).Then, determine that the business function to match with user's Figure Characteristics (e.g., matches from these alternative business functions
Business function may include：The premium notice of detailed version, the premium notice of medium font size).
The recommendation method for the business function that multiple embodiments that this specification discloses provide uses business by obtaining user
Feedback information, and determine according to feedback information user's public sentiment feature of the user.Then, special according to user's public sentiment of user
The user property feature of acquisition of seeking peace determines user's Figure Characteristics.Then, from the alternative business function of the business of acquisition, really
The business function that fixed and user's Figure Characteristics match.Recommend personalized business function to user to realize, to meet not
With user to the different demands of business.
Fig. 2 is a kind of flow chart of the recommendation method for business function that one embodiment that this specification discloses provides.Institute
The executive agent for stating method can be the equipment with processing capacity：Server either system or device or software platform.
Such as, the server in Fig. 1.
Fig. 3 is that the frame structure of a kind of user characteristics that one embodiment that this specification discloses provides and business function is shown
It is intended to.In the following, in conjunction with Fig. 2 and Fig. 3, the recommendation method of the business function provided in the multiple embodiments disclosed this specification into
Row explanation.
As shown in Fig. 2, the method specifically includes step S210- steps S260：
Step S210 obtains the feedback information that user uses business, as shown in 310 in Fig. 3.
Specifically, the business that user uses may include a variety of Internet-related business, such as：Electronic bill payment, network
Shopping and shared service etc..May include to the in-service evaluation of this business and/or suggestion etc. in feedback information.Server obtains
Feedback information may come from using business user participate in questionnaire survey, send feedback mail and this business visitor
Take platform (e.g., phone customer service platform or APP customer service entrances etc.).
In addition, can also include user information (e.g., user identifier, user account, address name, phone in feedback information
Number or identification card number etc.) and/or business information (e.g., service identification, Business Name etc.).For example, user asks filling in investigation
Oneself name, telephone number and account information are filled in when volume.In another example user has input when being linked up with artificial customer service
The Business Name of its consultation service.
Alternatively, server while obtaining feedback information of the user using business, can also obtain user's mark of user
Know (e.g., can be with the Customs Assigned Number etc. of unique mark user) and/or the service identification of the business (e.g., can be with unique mark business
Business number).For example, user seeks advice from having for its used business after logging in application by the customer service entrance of the application
Pass problem.At this point, the server of the application can obtain the Customs Assigned Number of user in the application, and user is obtained using visitor
Take the business number of used business before entrance.
In one embodiment, server obtains the feedback information that user uses business, feedback from network surveying questionnaire
Information includes the account of user, and the in-service evaluation of the Business Name of used business, business.In one example, it takes
Business device obtains the information in the questionnaire that user has filled in, which includes：Account " 12388888888 ", the business of user
Title " life payment ", business in-service evaluation " during use, repeatedly show ' mechanism is busy, can not pay the fees ', and pay the fees and lose
It loses ".
In another embodiment, application server obtains the feedback information that user uses business from the customer service entrance of application
With the service identification of involved business in feedback information, meanwhile, obtain the user identifier of the user.In one example, it pays
The server of Baoying County obtains why user " is owed using the feedback information of business from the customer service entrance in Alipay client
So more electricity charge ", and " 123 " are numbered with the business of " electricity charge " relevant business " electricity charge are paid " in feedback information, meanwhile, it obtains
Take the Customs Assigned Number " 456 " of the user.
In yet another embodiment, server obtains user from the return visit record to user using business and uses business
Feedback information.In one example, pay a return visit record include Business Name " life pay the fees ", user telephone number
" 123888888 " and feedback information " word is somewhat small, does not see Chu ".
In a still further embodiment, server obtains the feedback information that user uses business from the evaluation record of user.
In one example, evaluation record includes Business Name " life payment ", the account " 12345678@qq.com " of user and instead
Feedforward information " is paid the fees very convenient, very well online！”.
Then, in step S220, user's public sentiment feature of the user is determined according to the feedback information, in Fig. 3
Shown in 320.
Specifically, it is determined that user's public sentiment feature includes carrying out semantic analysis to the feedback information of user, and according to semanteme point
The analysis result of analysis determines user's public sentiment feature of user.Wherein semantic analysis refers to analyzing expressed by the text of feedback information
Meaning, to determine expectation of the user to business.Correspondingly, user's public sentiment feature includes it is expected relevant feature with user.
In one embodiment, determine that user's public sentiment feature includes carrying out sentiment analysis, and root to the feedback information of user
According to the analysis result of sentiment analysis, user's public sentiment feature of user is determined.Sentiment analysis refers to the text institute according to feedback information
There are many affective styles by text for the meaning and emotion information of expression, such as praise, complain, interrogate, to determine user's
The grade of mood and mood.Correspondingly, user's public sentiment feature includes and the relevant feature of user emotion.
It is appreciated that a variety of sides in the prior art may be used in the semantic analysis and/or sentiment analysis in the present embodiment
Method is not construed as limiting this.For example, when the feedback information of user is voice messaging, first voice messaging can be converted to text
Then information carries out semantic analysis and sentiment analysis to text information, wherein sentiment analysis can also include directly according to language
Voice, intonation in message breath determine the mood of user.
In one example, user includes using the feedback information of fee payment service：" during use, repeatedly show ' mechanism
It is busy, can not pay the fees ', and failure of paying the fees ".Semantic analysis and sentiment analysis are carried out to the feedback information, can obtain user's
It is expected that being respectively " it is desirable that improving payment success rate ", " dissatisfied " with mood.
In another example, the feedback information that user pays business using the electricity charge includes：" owe so mostly electric why
Take ".Expectation and the mood that can obtain user accordingly are respectively " to want to know about the charging regulation of the electricity charge and specific electricity consumption
Situation ", " querying, be unsatisfied with ".
In another example, user includes using the feedback information of fee payment service：" word is somewhat small, does not see Chu ".According to
This can obtain the expectation of user and mood is respectively " it is desirable that increasing font size ", " dissatisfied ".
In yet another example, user includes using the feedback information of life fee payment service：" it pays the fees online very convenient,
Very well！”.It is respectively " being interested in continuing with use ", " satisfaction " that can obtain the expectation of user and mood accordingly.
Step S230 obtains the user property feature of user, as shown in 330 in Fig. 3.
Specifically, the user property that multiple users or catergories of user can be previously stored in user property feature database is special
Sign.Server can be according to the user information (e.g., user identifier or telephone number etc.) obtained in step S210, in user property
The user property feature of the user or the user property feature of user's owning user classification are obtained in feature database.
Wherein, user property feature may include natural quality feature (e.g., age, gender, health status etc.), society's category
Property feature (e.g., hobby, occupation, the monthly average consumption amount of money, house property situation), the service attribute feature (industry e.g., being commonly used
Business, business operation preference etc.) and Regional Property feature (e.g., most normal residence etc.).
In one embodiment, the user property feature of acquisition include age of user, gender, most normal residence, occupation,
The monthly average consumption amount of money.In one example, the user property feature of user includes：30 years old, female, Guizhou mountainous area, teacher, 2000
Member.
In another embodiment, the user property feature of acquisition includes the age of user, house property situation, occupation.One
In a example, the user property feature of user includes：25 years old, rent a house, programmer.
In yet another embodiment, the user property feature of acquisition include the age of user, house property situation, health status,
The business being commonly used.In one example, the user property feature of user includes：70 years old, self-owned house, presbyopia, often
The software of voice is converted to using text.
In a still further embodiment, the user property feature of acquisition includes age, occupation, hobby and the house property of user
Situation.In one example, the user property feature of user includes：40 years old, full-time housewife, knit a sweater, self-owned house.
Step S240 determines user's Figure Characteristics, such as 340 in Fig. 3 according to user's public sentiment feature and user property feature
It is shown.
Specifically, user's Figure Characteristics may include the user's public sentiment feature determined in step S220 and be obtained in step S230
The user property feature taken.
In one example, user's public sentiment feature of user includes：" it is desirable that improving payment success rate ", " dissatisfied ", should
The user property feature of user includes：" 30 years old ", " female ", " Guizhou mountainous area ", " teacher ", " 2000 yuan ".So, the use of the user
Family Figure Characteristics may include：" 30 years old ", " female ", " teacher ", " 2000 yuan ", " pay the fees successfully at " Guizhou mountainous area " it is desirable that improving
Rate ", " dissatisfied ".
In another example, user's Figure Characteristics of user may include user property feature：" 25 years old ", " renting a house ",
" programmer " and user's public sentiment feature：" wanting to know about the charging regulation of the electricity charge and specific electricity consumption situation ", " dissatisfied ".
In another example, user's Figure Characteristics of user may include user property feature：" 70 years old " " has by oneself
Room ", " presbyopia ", " software that voice is converted to commonly using text " and user's public sentiment feature：" it is desirable that increasing font size ", " no
It is satisfied ".
Again in yet another example, user's Figure Characteristics of user may include user property feature：" 40 years old ", " full-time family
Front yard housewife ", " knitting a sweater ", " self-owned house ", and " user's public sentiment feature "：" being interested in continuing with use ", " satisfaction ".
Step S250 obtains the alternative business function of business, as shown in 350 in Fig. 3.
Specifically, the alternative business function of multiple business can be previously stored in alternative business function library..Server can
According to the business information (e.g., Business Name or service identification etc.) obtained in step S210, to be obtained in alternative business function library
Take the alternative business function of business used by a user.
In one embodiment, a business may include multiple alternative business functions.In one example, fee payment service
May include multiple alternative business functions, such as " the brief version of premium notice ", " the detailed version of premium notice ", " the general font size page ",
" increase font size the page ", " voice broadcast ", " withholding service automatically ", " automatic value-charging service ", " balance reminding service ", " under line
The service of paying ", " service is payed on behalf under line ", " discount coupon Push Service " etc..
User's Figure Characteristics of user are determined in step S240, and obtain industry used by a user in step s 250
After the alternative business function of business, in step S260, the function of matching with user's Figure Characteristics is determined from alternative business function,
And using the business function as business function recommended to the user, as shown in 360 in Fig. 3.
Specifically, the mapping relations of alternative business function and user's Figure Characteristics can be previously stored in server, then
Server can determine the business function that match with user's Figure Characteristics according to the mapping relations, and using the business function as
Business function recommended to the user.Alternatively, Feature Correspondence Algorithm may be used in server, by user's Figure Characteristics and alternative industry
The functional character of business function matches, to determine the business work(to match with user's Figure Characteristics from alternative business function
Can, and using the business function as business function recommended to the user.
In one embodiment, pre-stored mapping relations can be presented as the form of mapping table in server.For example,
As shown in table 1, for each alternative business function in table 1, when the user's Figure Characteristics determined in step S240 include in table 1
When with corresponding to the alternative business function partly or completely with family Figure Characteristics, can using the alternative business function as to
The business function that user recommends.
Table 1
In one example, user's Figure Characteristics of user include：" 30 years old ", " female ", " Guizhou mountainous area ", " teacher ",
" 2000 yuan ", " it is desirable that improving payment success rate ", " dissatisfied ".Mapping table as shown in Table 1 is previously stored in server.Phase
Answer, server can according to the mapping table determine with user's Figure Characteristics, e.g., " 30 years old ", " Guizhou mountainous area ", " it is desirable that improve
The business function that payment success rate " matches, such as " the general font size page ", " service is payed on behalf under line " and " preferential activity ", and to
The user recommends this business function.As shown in figure 4, to recommend the customer terminal webpage of " paying on behalf service under line " to user in Fig. 4,
The page includes the content shown using general font size：" service details：Every time using need pay expense to be paid and
Run errands expense and the preferential activity of Flat Amount：Run errands expense using release for the first time.”
In another example, user's Figure Characteristics of user include：" 25 years old ", " renting a house ", " programmer " and user carriage
Feelings feature：" wanting to know about the charging regulation of the electricity charge and specific electricity consumption situation ", " dissatisfied ".It is prestored in server
There is mapping table as shown in Table 1.Correspondingly, server can be determined according to the mapping table and user's Figure Characteristics, such as " 25 years old ",
" wanting to know about the charging regulation of the electricity charge and specific electricity consumption situation ", " renting a house ", the business function to match, such as " general words
Number page ", " the detailed version of premium notice " and " preferential activity ", and recommend this business function to the user.As shown in figure 5, Fig. 5
In to push premium notice to user when customer terminal webpage, which includes the electricity consumption " 200 shown using general font size
Degree ", the amount of money to be paid " 100.00 yuan ", charging regulation and coupon information.
In another example, user's Figure Characteristics of user include：" 70 years old ", " self-owned house ", " presbyopia ", " warp
It is often used the software that text is converted to voice " and user's public sentiment feature：" it is desirable that increasing font size ", " dissatisfied ".It is pre- in server
First it is stored with mapping table as shown in Table 1.Correspondingly, server can be determined according to the mapping table and user's Figure Characteristics, such as
" 70 years old ", " presbyopia ", " software that voice is converted to commonly using text ", " it is desirable that increasing font size ", the business work(to match
Can, such as " the brief version of premium notice ", " increasing the font size page " and " voice broadcast ".As shown in fig. 6, being to be pushed to user in Fig. 6
Customer terminal webpage when premium notice, the page include the amount of money to be paid " 120 yuan " shown using font size is increased.In addition,
When user's point opens this page, client can carry out voice broadcast to the relevant information of payment automatically, or click language in user
Voice broadcast is carried out after the button that sound is reported.
In yet another example, user's Figure Characteristics of user include：" 40 years old ", " full-time housewife ", " knitting a sweater ",
" self-owned house ", " being interested in continuing with use ", " satisfaction ".Server can continue according to user's Figure Characteristics " satisfaction " to the user
Recommended user's business function currently in use.
In another embodiment, server can train a characteristic matching model, this feature Matching Model root in advance
The various features in user's Figure Characteristics are matched with the various functions feature of alternative business function according to pre-defined rule.Such as
This, server inputs user's Figure Characteristics in features described above Matching Model, and root after determining user's Figure Characteristics of user
The business function to match with user's Figure Characteristics is determined according to the output result of this feature Matching Model.
It should be noted that in step S260, on the basis of embodiment described above, may be incorporated into artificial
The mode of intervention determines business function recommended to the user according further to user's Figure Characteristics of user.In an example
In, in server according to the feedback information of user, determines user's Figure Characteristics and recommend to match with user's Figure Characteristics to user
Business function after, be received again by the feedback information of user, to the feedback information carry out sentiment analysis analysis result from the point of view of,
" dissatisfaction " of user increases, at this point it is possible to take the mode of manual intervention.In one example, server draws user
It as feature is supplied to contact staff, is analyzed by contact staff, and determines business function recommended to the user.In an example
In, server will automatically analyze the recommendation business function of generation, and the recommendation business function determined by contact staff integrates,
Determine that final recommendation business can with this., can be as needed during comprehensive analysis, it is pushed away for what contact staff provided
It recommends business function and assigns different weights, to adjust the proportion of manual intervention.In another example, business provider needs pair
Certain business functions are tested, at this point it is possible to user's Figure Characteristics are supplied to business provider, by business provider according to
User's Figure Characteristics specify some users, and recommending to these users need to business function to be tested.
In addition, in step S220, step S230 and step S250 any two step may be performed simultaneously, can also successively
It executes, above-mentioned multiple embodiments are not construed as limiting the execution sequence of these three steps.
The recommendation method for the business function that multiple embodiments that this specification discloses provide uses business by obtaining user
Feedback information, and determine according to feedback information user's public sentiment feature of the user.Then, special according to user's public sentiment of user
The user property feature of acquisition of seeking peace determines user's Figure Characteristics.Then, it from the alternative business function of the business of acquisition, determines
The business function to match with user's Figure Characteristics.Recommend personalized business function to user to realize, to meet difference
Different demands of the user to business.
Accordingly with the recommendation method of above-mentioned business function, multiple embodiments that this specification discloses also provide a kind of business
The recommendation apparatus of function, as shown in fig. 7, the device includes：
First acquisition unit 710 uses the feedback information of business for obtaining user；
First determination unit 720, user's public sentiment feature for determining user according to feedback information；
Second acquisition unit 730, the user property feature for obtaining user；
Second determination unit 740, for determining user's Figure Characteristics according to user's public sentiment feature and user property feature；
Third acquiring unit 750, the alternative business function for obtaining business；
Processing unit 760, for determining the business function to match with user's Figure Characteristics from alternative business function, and
Using the business function as business function recommended to the user.
In a kind of possible design, the first determination unit 720 includes：
Subelement 721 is analyzed, for carrying out semantic analysis and sentiment analysis to feedback information；
Determination subelement 722 determines user's public sentiment feature for the analysis result according to semantic analysis and sentiment analysis.
In a kind of possible design, the feedback information that first acquisition unit 710 obtains includes the user identifier of user, the
Two acquiring units 730 are specifically used for：
According to user identifier, the user property feature of user is obtained from user property feature database.
In a kind of possible design, the feedback information that first acquisition unit 710 obtains includes the service identification of business, the
Three acquiring units 750 are specifically used for：
According to service identification, the alternative business function of business is obtained from business function library.
In a kind of possible design, processing unit 760 is specifically used for：
According to the mapping relations of pre-stored alternative business function and user's Figure Characteristics, determine and user's Figure Characteristics
The business function to match.
In a kind of possible design, processing unit 760 is specifically used for：
Using Feature Correspondence Algorithm, the business function to match with user's Figure Characteristics is determined from alternative business function.
In a kind of possible design, second acquisition unit 730 obtain user property feature include natural quality feature,
At least one of social property feature, service attribute feature and Regional Property feature.
The recommendation apparatus for the business function that multiple embodiments that this specification discloses provide, first acquisition unit 710 obtain
User uses the feedback information of business, the first determination unit 720 to determine user's public sentiment feature of the user according to feedback information.
Then, the user property feature that the second determination unit 710 is obtained according to the user's public sentiment feature and second acquisition unit 730 of user
Determine user's Figure Characteristics.Then, processing unit 760 is from the alternative business function for the business that third acquiring unit 750 obtains,
Determine the business function to match with user's Figure Characteristics.Recommend personalized business function to user to realize, to meet
Different demands of the different user to business.
It will be appreciated that in said one or multiple examples, this specification discloses more those skilled in the art
A embodiment described function can be realized with hardware, software, firmware or their arbitrary combination.When using software realization
When, these functions can be stored in computer-readable medium or be referred to as the one or more on computer-readable medium
It enables or code is transmitted.
Above-described specific implementation mode to the purpose of multiple embodiments of this specification disclosure, technical solution and has
Beneficial effect has been further described, it should be understood that the foregoing is merely multiple embodiments that this specification discloses
Specific implementation mode, be not used to limit this specification disclose multiple embodiments protection domain, it is all in this explanation
On the basis of the technical solution for multiple embodiments that book discloses, any modification, equivalent substitution, improvement and etc. done should all wrap
It includes within the protection domain for multiple embodiments that this specification discloses.
Claims (14)
1. a kind of recommendation method of business function, which is characterized in that including：
The feedback information that user uses business is obtained, and determines that user's public sentiment of the user is special according to the feedback information
Sign；
Obtain the user property feature of the user；
User's Figure Characteristics are determined according to user's public sentiment feature and the user property feature；
Obtain the alternative business function of the business；
Determine the business function to match with user's Figure Characteristics from the alternative business function, and by the business function
As the business function recommended to the user.
2. according to the method described in claim 1, it is characterized in that, the use for determining the user according to the feedback information
Family public sentiment feature, including：
Semantic analysis and/or sentiment analysis are carried out to the feedback information；
According to the semantic analysis and/or the analysis result of sentiment analysis, user's public sentiment feature is determined.
3. according to the method described in claim 1, it is characterized in that, the feedback information includes the user identifier of the user,
The user property feature for obtaining the user, including：
According to the user identifier, the user property feature of the user is obtained from user property feature database.
4. according to the method described in claim 1, it is characterized in that, the feedback information includes the service identification of the business,
The alternative business function for obtaining the business, including：
According to the service identification, the alternative business function of the business is obtained from business function library.
5. according to the method described in claim 1, it is characterized in that, described determine and the use from the alternative business function
The business function that family Figure Characteristics match, including：
According to the mapping relations of the pre-stored alternative business function and user's Figure Characteristics, determine and the user
The business function that Figure Characteristics match.
6. according to the method described in claim 1, it is characterized in that, described determine and the use from the alternative business function
The business function that family Figure Characteristics match, including：
Using Feature Correspondence Algorithm, the business work(to match with user's Figure Characteristics is determined from the alternative business function
Energy.
7. according to claim 1-6 any one of them methods, which is characterized in that the user property feature includes natural quality
At least one of feature, social property feature, service attribute feature and Regional Property feature.
8. a kind of recommendation apparatus of business function, which is characterized in that including：
First acquisition unit uses the feedback information of business for obtaining user；
First determination unit, user's public sentiment feature for determining the user according to the feedback information；
Second acquisition unit, the user property feature for obtaining the user；
Second determination unit, it is special for determining that the user draws a portrait according to user's public sentiment feature and the user property feature
Sign；
Third acquiring unit, the alternative business function for obtaining the business；
Processing unit, for determining the business function to match with user's Figure Characteristics from the alternative business function,
And using the business function as the business function recommended to the user.
9. device according to claim 8, which is characterized in that first determination unit includes：
Subelement is analyzed, for carrying out semantic analysis and/or sentiment analysis to the feedback information；
Determination subelement determines that user's public sentiment is special for the analysis result according to the semantic analysis and/or sentiment analysis
Sign.
10. device according to claim 8, which is characterized in that the feedback information that the first acquisition unit obtains includes
The user identifier of the user, the second acquisition unit are specifically used for：
According to the user identifier, the user property feature of the user is obtained from user property feature database.
11. device according to claim 8, which is characterized in that the feedback information that the first acquisition unit obtains includes
The service identification of the business, the third acquiring unit are specifically used for：
According to the service identification, the alternative business function of the business is obtained from business function library.
12. device according to claim 8, which is characterized in that the processing unit is specifically used for：
According to the mapping relations of the pre-stored alternative business function and user's Figure Characteristics, determine and the user
The business function that Figure Characteristics match.
13. device according to claim 8, which is characterized in that the processing unit is specifically used for：
Using Feature Correspondence Algorithm, the business work(to match with user's Figure Characteristics is determined from the alternative business function
Energy.
14. according to claim 8-13 any one of them devices, which is characterized in that the user that the second acquisition unit obtains
Attributive character includes at least one of natural quality feature, social property feature, service attribute feature and Regional Property feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810050532.4A CN108470023A (en) | 2018-01-18 | 2018-01-18 | The recommendation method and device of business function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810050532.4A CN108470023A (en) | 2018-01-18 | 2018-01-18 | The recommendation method and device of business function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108470023A true CN108470023A (en) | 2018-08-31 |
Family
ID=63265938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810050532.4A Pending CN108470023A (en) | 2018-01-18 | 2018-01-18 | The recommendation method and device of business function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108470023A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615494A (en) * | 2018-09-29 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Business derived method, device, electronic equipment and computer readable storage medium |
| CN110750733A (en) * | 2019-10-15 | 2020-02-04 | 赛尔网络有限公司 | Service recommendation method, device, equipment and medium based on school identity portrait |
| CN110852338A (en) * | 2019-07-26 | 2020-02-28 | 平安科技（深圳）有限公司 | User portrait construction method and device |
| CN111127060A (en) * | 2018-10-31 | 2020-05-08 | 百度在线网络技术（北京）有限公司 | Method and device for determining promotion user of service |
| CN111507774A (en) * | 2020-04-28 | 2020-08-07 | 上海依图网络科技有限公司 | Data processing method and device |
| CN111667317A (en) * | 2020-06-16 | 2020-09-15 | 中国银行股份有限公司 | Service processing method, device and system |
| CN113742199A (en) * | 2020-05-28 | 2021-12-03 | 北京达佳互联信息技术有限公司 | Function testing method and device, electronic equipment and storage medium |
| CN114493792A (en) * | 2022-01-29 | 2022-05-13 | 深圳市小满科技有限公司 | Foreign trade CRM recommendation method and related equipment |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102300163A (en) * | 2011-09-22 | 2011-12-28 | 宇龙计算机通信科技(深圳)有限公司 | Information pushing method, mobile terminal and system |
| CN104166713A (en) * | 2014-08-14 | 2014-11-26 | 百度在线网络技术（北京）有限公司 | Network service recommending method and device |
| CN105205699A (en) * | 2015-09-17 | 2015-12-30 | 北京众荟信息技术有限公司 | User label and hotel label matching method and device based on hotel comments |
| CN105915438A (en) * | 2016-04-15 | 2016-08-31 | 北京奇虎科技有限公司 | Message pushing method, apparatus, and system |
| CN106126499A (en) * | 2016-06-22 | 2016-11-16 | 青岛海信传媒网络技术有限公司 | User satisfaction and loyalty analyze method and device |
| CN106126582A (en) * | 2016-06-20 | 2016-11-16 | 乐视控股（北京）有限公司 | Recommend method and device |
| CN106851349A (en) * | 2017-03-21 | 2017-06-13 | 上海星红桉数据科技有限公司 | Based on magnanimity across the live recommendation method for shielding viewing behavior data |
| CN106897884A (en) * | 2017-01-24 | 2017-06-27 | 武汉奇米网络科技有限公司 | The method and system of quick guiding visitor consulting |
| CN107423442A (en) * | 2017-08-07 | 2017-12-01 | 火烈鸟网络(广州)股份有限公司 | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis |
| CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
| US20170368683A1 (en) * | 2016-06-28 | 2017-12-28 | Shenzhen Gowild Robotics Co., Ltd. | User portrait based skill package recommendation device and method |
-
2018
- 2018-01-18 CN CN201810050532.4A patent/CN108470023A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102300163A (en) * | 2011-09-22 | 2011-12-28 | 宇龙计算机通信科技(深圳)有限公司 | Information pushing method, mobile terminal and system |
| CN104166713A (en) * | 2014-08-14 | 2014-11-26 | 百度在线网络技术（北京）有限公司 | Network service recommending method and device |
| CN105205699A (en) * | 2015-09-17 | 2015-12-30 | 北京众荟信息技术有限公司 | User label and hotel label matching method and device based on hotel comments |
| CN105915438A (en) * | 2016-04-15 | 2016-08-31 | 北京奇虎科技有限公司 | Message pushing method, apparatus, and system |
| CN106126582A (en) * | 2016-06-20 | 2016-11-16 | 乐视控股（北京）有限公司 | Recommend method and device |
| CN106126499A (en) * | 2016-06-22 | 2016-11-16 | 青岛海信传媒网络技术有限公司 | User satisfaction and loyalty analyze method and device |
| US20170368683A1 (en) * | 2016-06-28 | 2017-12-28 | Shenzhen Gowild Robotics Co., Ltd. | User portrait based skill package recommendation device and method |
| CN106897884A (en) * | 2017-01-24 | 2017-06-27 | 武汉奇米网络科技有限公司 | The method and system of quick guiding visitor consulting |
| CN106851349A (en) * | 2017-03-21 | 2017-06-13 | 上海星红桉数据科技有限公司 | Based on magnanimity across the live recommendation method for shielding viewing behavior data |
| CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
| CN107423442A (en) * | 2017-08-07 | 2017-12-01 | 火烈鸟网络(广州)股份有限公司 | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615494A (en) * | 2018-09-29 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Business derived method, device, electronic equipment and computer readable storage medium |
| CN111127060A (en) * | 2018-10-31 | 2020-05-08 | 百度在线网络技术（北京）有限公司 | Method and device for determining promotion user of service |
| CN111127060B (en) * | 2018-10-31 | 2023-08-08 | 百度在线网络技术（北京）有限公司 | Method and device for determining popularization users of service |
| CN110852338A (en) * | 2019-07-26 | 2020-02-28 | 平安科技（深圳）有限公司 | User portrait construction method and device |
| CN110750733A (en) * | 2019-10-15 | 2020-02-04 | 赛尔网络有限公司 | Service recommendation method, device, equipment and medium based on school identity portrait |
| CN111507774A (en) * | 2020-04-28 | 2020-08-07 | 上海依图网络科技有限公司 | Data processing method and device |
| CN113742199A (en) * | 2020-05-28 | 2021-12-03 | 北京达佳互联信息技术有限公司 | Function testing method and device, electronic equipment and storage medium |
| CN111667317A (en) * | 2020-06-16 | 2020-09-15 | 中国银行股份有限公司 | Service processing method, device and system |
| CN111667317B (en) * | 2020-06-16 | 2023-11-10 | 中国银行股份有限公司 | Service processing method, device and system |
| CN114493792A (en) * | 2022-01-29 | 2022-05-13 | 深圳市小满科技有限公司 | Foreign trade CRM recommendation method and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108470023A (en) | The recommendation method and device of business function | |
| Yılmazdoğan et al. | The impact of the source credibility of Instagram influencers on travel intention: The mediating role of parasocial interaction | |
| Chahal et al. | How trust moderates social media engagement and brand equity | |
| US10719883B2 (en) | Web property generator | |
| Rao et al. | Bank selection criteria employed by MBA students in Delhi: An empirical analysis | |
| Zhu et al. | A new theoretical framework of technology acceptance and empirical investigation on self‐efficacy‐based value adoption model | |
| CN109615408B (en) | Advertisement putting method and device based on big data, storage medium and electronic equipment | |
| US20110179116A1 (en) | System and method for providing personality-based content and advertisements | |
| CN110019699B (en) | Classification of inter-domain through grammar slots | |
| US20150127565A1 (en) | Social Match Platform Apparatuses, Methods and Systems | |
| WO2011019852A1 (en) | Method and apparatus for expert quality control | |
| US11270068B2 (en) | System and interface for electronic communication generation and tracking | |
| Lu et al. | [Retracted] Influencing Factors of Cross‐Border E‐Commerce Consumer Purchase Intention Based on Wireless Network and Machine Learning | |
| CN109118243B (en) | Product sharing, useful evaluation identification and pushing method and server | |
| Zhang et al. | Who, what, why and how? towards the monetary incentive in crowd collaboration: A case study of github’s sponsor mechanism | |
| US10976901B1 (en) | Method and system to share information | |
| Lisnik et al. | Aspects of strategic management and online marketing | |
| CN112433725A (en) | Interface generation method and device, electronic equipment and storage medium | |
| CN116823410A (en) | Data processing method, object processing method, recommending method and computing device | |
| JP2010186283A (en) | Information processor, information processing method, and information processing program | |
| JP2002230344A (en) | Consultation intermediary agent system and program of the same system | |
| Sahu et al. | Factors influencing consumer’s behavioral intention to adopt irctc connect mobile application | |
| Hyrynsalmi et al. | The emerging mobile ecosystems: An introductory analysis of Android Market | |
| CN113536103A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| KR20090101704A (en) | System for administering a user opinion and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200928 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: 20200928 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: 20180831 |