CN108537644A - A kind of method and apparatus of customer service recommended products - Google Patents
A kind of method and apparatus of customer service recommended products Download PDFInfo
- Publication number
- CN108537644A CN108537644A CN201810366792.2A CN201810366792A CN108537644A CN 108537644 A CN108537644 A CN 108537644A CN 201810366792 A CN201810366792 A CN 201810366792A CN 108537644 A CN108537644 A CN 108537644A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- response
- time
- content
- 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
- 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]
- G06Q30/0613—Third-party assisted
-
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of method and apparatus of customer service recommended products, this method includes:In response to triggering the operation of customer service control, the current browsing record of acquisition and user's portrait information including user base information, value relevant information and historical viewings track;According to current browsing record and historical viewings track, obtains prediction consulting and be intended to and generate response content for the first time;Obtain the user of corresponding response content for the first time reply content for the first time;According to user for the first time reply content and value relevant information, carry out response and recommend relevant product information.As it can be seen that current browsing record and the historical viewings track of analysis user, prediction user, which seeks advice from, to be intended to, and based on the reaction that user is intended to prediction consulting, recommends relevant product information to user according to the value relevant information of user.On the basis of having professional response, in conjunction with the personalized value relevant information of user, realizes that personalization of product, reasonability are recommended, improve customer service intelligence degree, promote the susceptibility and satisfaction of client.
Description
Technical field
This application involves intelligent customer service interaction technique field more particularly to a kind of method and apparatus of customer service recommended products.
Background technology
With science and technology and economic fast development, community service quality is higher and higher, website, wechat, microblogging and other
The channels such as application program are provided with smart client service, for example, online customer service, phone customer service etc..Especially for financial industry
Website, be generally arranged at the certain professional sex chromosome mosaicisms etc. of line customer service for answering user's consulting.
In the prior art, the method for service of online customer service is:When user wants to understand certain product informations in depth, click
After " online customer service " control, the problem of needing consulting is inputted, text robot is based on preset content response in professional question and answer dictionary
The above problem realizes the function of providing counseling services to the user online.
Inventor has found that in the service process of existing online customer service, text robot can only be directed to and fix
, professional problem carry out response, for example, for finance product, response content is only the term of validity of finance product, wind
Dangerous grade applies to purchase redemption mode etc..Response content pertains only to the product referred in customer problem, no other personalized products letter
Breath, it is relatively simple, fixed and inflexible, that is, there is no, to generate personalized response content, caused based on user personalized information
The acknowledgement mechanism intelligence degree of entire online customer service is relatively low, and then influences the experience sense and satisfaction of user.
Invention content
Technical problems to be solved in this application are to provide a kind of method and apparatus of customer service recommended products, realize product
Personalized, reasonability marketing is recommended, and customer service intelligence degree is improved, to promote the susceptibility and satisfaction of client.
In a first aspect, the embodiment of the present application provides a kind of method of customer service recommended products, this method includes:
In response to triggering the operation of customer service control, obtains user's portrait information and current browsing records;User's portrait
Information includes value relevant information and historical viewings track;
According to the current browsing record and the historical viewings track, obtains prediction consulting and be intended to and generate reply for the first time
Content;
Obtain it is corresponding described in response content for the first time user's reply content for the first time;
According to the user reply content and the value relevant information for the first time, carries out response and Related product is recommended to believe
Breath.
Preferably, the value relevant information includes proprietary information and historical transaction record;The historical viewings track packet
Track is browsed for several times before including.
Preferably, the relevant product information, which is shown in, recommends in column and/or response content.
Preferably, when reply content includes the content that the prediction consulting is intended to certainly to the user for the first time, described
According to the user reply content and the value relevant information for the first time, carries out response and recommend relevant product information, including:
According to user reply content for the first time, response is carried out;
According to the proprietary information, recommend to be intended to relevant product information with prediction consulting in due course.
Preferably, described according to the proprietary information, recommend to be intended to relevant product information with prediction consulting in due course,
Specially:
If user's reply content has not been obtained in the preset time after response, recommend to be intended to prediction consulting relevant
Product information.
Preferably, when reply content includes the content that the negative prediction consulting is intended to the user for the first time, described
According to the user reply content and the value relevant information for the first time, carries out response and recommend relevant product information in due course, specifically
For:
According to the user reply content and historical transaction record for the first time, carries out response and recommend relevant product information.
Preferably, described according to the current browsing record and the historical viewings track, it obtains prediction consulting and is intended to simultaneously
It generates response content for the first time and generates response content for the first time, including:
Record and the historical viewings track are currently browsed described in comparative analysis, obtaining prediction using fuzzy algorithmic approach seeks advice from meaning
Figure;
It is seeked advice from and is intended to according to the prediction, generate response content for the first time.
Preferably, the operation in response to triggering customer service control, obtains user's portrait information and current browsing records, and wraps
It includes:
In response to triggering the operation of customer service control, current browsing record and User Identity are obtained;
Data mining is carried out according to the User Identity, obtains user's portrait information.
Preferably, user's portrait information further includes user base information, and the user base information includes user's surname
Name and/or user's gender, then the method further include:
According to the user base information and default greeting corpus, greeting sentence is determined.
Preferably, described seeked advice from according to the prediction is intended to, and generates response content for the first time, specially:
According to prediction consulting intention and the greeting sentence, response content for the first time is generated.
Preferably, described according to the user reply content and the value relevant information for the first time, it carries out response and recommends
Relevant product information, specially:
According to the user reply content, the value relevant information and the greeting sentence for the first time, carries out response and push away
Recommend relevant product information.
Second aspect, the embodiment of the present application provide a kind of device of customer service recommended products, which includes:
First obtains unit obtains user's portrait information and current browsing for the operation in response to triggering customer service control
Record;The user draws a portrait information including being worth relevant information and historical viewings track;
Second obtaining unit, for according to the current browsing record and the historical viewings track, obtaining prediction consulting
It is intended to and generates response content for the first time;
First acquisition unit, for obtain it is corresponding described in response content for the first time user's reply content for the first time;
Response recommendation unit, for according to the user reply content and the value relevant information for the first time, carrying out response
And recommend relevant product information.
The third aspect, the embodiment of the present application provide a kind of server apparatus, which includes:It is at least one to deposit
Reservoir and at least one processor;
Wherein, memory is for storing program code, and processor is for calling the program code that the memory is stored
The method for executing customer service recommended products described in above-mentioned first aspect any one.
Fourth aspect, the embodiment of the present application provide a kind of storage medium, and the storage medium is used to store program code,
The method that said program code is used to execute customer service recommended products described in above-mentioned first aspect any one.
5th aspect, it includes the computer program product instructed that the embodiment of the present application, which provides a kind of, when it is in computer
When upper operation so that the method that the computer executes customer service recommended products described in above-mentioned first aspect any one.
Compared with prior art, the application has at least the following advantages:
Using the technical solution of the embodiment of the present application, first, in response to triggering the operation of customer service control, current browsing is obtained
Record and including user base information, value relevant information and historical viewings track user draw a portrait information;Secondly, according to described
Current browsing record and the historical viewings track obtain prediction consulting and are intended to and generate response content for the first time;Then, acquisition pair
Answer the user of the response content for the first time reply content for the first time;Finally, according to the user reply content and the value for the first time
Relevant information carries out response and recommends relevant product information.It can be seen that currently browsing record and historical viewings rail based on user
The analysis of mark, prediction user, which seeks advice from, to be intended to, and based on the reaction that user is intended to prediction consulting, gives the same of the professional response of user
When, relevant product information is recommended to user according to the value relevant information of user.The application on the basis of having professional response,
In conjunction with the personalized value relevant information of user, realizes that personalization of product, reasonability marketing are recommended, improve customer service intelligence journey
Degree, to promote the susceptibility and satisfaction of client.
Description of the drawings
It is required in being described below to the embodiment of the present application in order to illustrate more clearly of the technical solution of the embodiment of the present application
Attached drawing to be used is briefly described, it should be apparent that, the accompanying drawings in the following description is only some described in the application
Embodiment for those of ordinary skill in the art without creative efforts, can also be attached according to these
Figure obtains other attached drawings.
Fig. 1 is the system framework schematic diagram involved by a kind of application scenarios in the embodiment of the present application;
Fig. 2 is a kind of flow diagram of the method for customer service recommended products provided by the embodiments of the present application;
Fig. 3 is the flow diagram of the method for another customer service recommended products provided by the embodiments of the present application;
Fig. 4 is a kind of structural schematic diagram of the device of customer service recommended products provided by the embodiments of the present application.
Specific implementation mode
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, technical solutions in the embodiments of the present application are clearly and completely described, it is clear that described embodiment is only this
Apply for a part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
The every other embodiment obtained under the premise of creative work is not made, shall fall in the protection scope of this application.
Usually, in the service process of existing online customer service, after receiving input by user ask questions, text machine
People is based on preset content in professional question and answer dictionary and carries out response, inventor has found that text robot can only be directed to admittedly
Fixed, professional problem carries out response, for example, for finance product, response content be only finance product the term of validity,
Risk class applies to purchase redemption mode etc..Response content pertains only to the product referred in customer problem, no other personalized products letter
Breath, it is relatively simple, fixed and inflexible, that is, there is no, to generate personalized response content, caused based on user personalized information
The acknowledgement mechanism intelligence degree of entire online customer service is relatively low, and then influences the experience sense and satisfaction of user.
In order to solve this problem, in the embodiment of the present application, first, in response to the operation of triggering customer service control, obtain
Information that current browsing records and the user including user base information, value relevant information and historical viewings track draws a portrait;Secondly,
According to the current browsing record and the historical viewings track, obtains prediction consulting and be intended to and generate response content for the first time;So
Afterwards, obtain it is corresponding described in response content for the first time user's reply content for the first time;Finally, according to the user for the first time reply content and
The value relevant information carries out response and recommends relevant product information.It can be seen that currently browsing record based on user and going through
History browses the analysis of track, and prediction user, which seeks advice from, to be intended to, and based on the reaction that user is intended to prediction consulting, it is professional to give user
While response, relevant product information is recommended to user according to the value relevant information of user.The application is having professional response
On the basis of, in conjunction with the personalized value relevant information of user, realizes that personalization of product, reasonability marketing are recommended, improve customer service
Intelligence degree, to promote the susceptibility and satisfaction of client.
For example, one of the scene of the embodiment of the present application, can be applied in scene as shown in Figure 1, the scene
Include terminal 101 and server 102.User is shown in end when terminal 101 logs in website of bank, by web page browsing click
After holding " online customer service " control on 101 interfaces, server 102 obtains user's portrait in response to the operation of triggering customer service control
Information and current browsing record;The user draws a portrait information including being worth relevant information and historical viewings track;Server 102
According to the current browsing record and the historical viewings track, obtains prediction consulting and be intended to and generate response content for the first time;Service
Device 102 obtain it is corresponding described in response content for the first time user's reply content for the first time;Server 102 is replied for the first time according to the user
Content and the value relevant information, carry out response and recommend relevant product information.Response content and relevant product information are at end
It holds and is shown to user on 101 interfaces.
It is understood that in above application scene, although by the action description of the application embodiment by server
102 execute, and still, the application is unrestricted in terms of executive agent, as long as performing dynamic disclosed in the application embodiment
Work.
It is understood that above-mentioned scene is only a Sample Scenario provided by the embodiments of the present application, the embodiment of the present application
It is not limited to this scene.
Below in conjunction with the accompanying drawings, the method and dress of customer service recommended products in the embodiment of the present application are described in detail by embodiment
The specific implementation set.
Illustrative methods
Referring to Fig. 2, a kind of flow diagram of the method for customer service recommended products in the embodiment of the present application is shown.In this reality
It applies in example, the method for example may comprise steps of:
Step 201:In response to triggering the operation of customer service control, obtains user's portrait information and current browsing records;It is described
User draws a portrait information including being worth relevant information and historical viewings track.
It is understood that after user clicks the customer service control operation on terminal interface, customer service request, the customer service are initiated
Request carries user and receives the request in the current browsing record and User Identity, server of terminal and can directly obtain
Current browsing record and User Identity, are then based on the User Identity, identify user and are searched based on big data
The information drawn a portrait to some information of the user as description user.Therefore, in some embodiments of the present embodiment, step
201 for example may comprise steps of:
Step 2011:In response to triggering the operation of customer service control, current browsing record and User Identity are obtained;
Step 2012:Data mining is carried out according to the User Identity, obtains user's portrait information.
Wherein, it should be noted that for the website of bank's class, need to excavate the wealth under user name based on big data
What production information, user had completed is related to transaction records such as finance etc., this is to belong to value relevant information;It can also excavate
Browsing record is formed by historical viewings track several times before user.Therefore, in some embodiments of the present embodiment, the valence
Value relevant information includes proprietary information and historical transaction record;The historical viewings track browses track for several times before including.For example,
The historical viewings track browses track three times before being preset as.
Step 202:According to the current browsing record and the historical viewings track, obtains prediction consulting and be intended to and generate
Response content for the first time.
It should be noted that after the historical viewings track that step 201 excavates to user, record and institute will be currently browsed
The comparative analysis of historical viewings track is stated, can predict that user triggers the consulting intention of customer service control, to the consulting based on prediction
It is intended to generate response content for the first time and is sent to terminal device, after the operation that user triggers customer service control, to be set in terminal
It is shown to user on standby interface.Therefore, in some embodiments of the present embodiment, the step 202 for example may include
Following steps:
Step 2021:Record and the historical viewings track are currently browsed described in comparative analysis, are obtained using fuzzy algorithmic approach
Prediction consulting is intended to;
Step 2022:It is seeked advice from and is intended to according to the prediction, generate response content for the first time.
For example, user has first clicked on " exchange rate inquiry " control, " finance product special column " control and then point are then clicked
It has hit " finance product A ", end user clicks the operation of " online customer service " control, and current browsing record refers to being looked into according to the exchange rate
It askes, the browsing record in finance product special column and finance product A sequences;Before data mining acquisition being carried out according to User Identity
Browsing track is " exchange rate inquiry-finance product special column-finance product A " three times;Consulting meaning can must be predicted by comparative analysis
Figure is " consulting finance product A correlation circumstances ", then can generate and " may I ask whether you seek advice from the correlation circumstance of finance product A"
Response content for the first time;Terminal device is sent it to, and after the operation that user clicks " online customer service " control, in terminal device
It is shown on the online customer service interactive interface of display.
Step 203:Obtain it is corresponding described in response content for the first time user's reply content for the first time.
It is understood that after showing response content for the first time on the online customer service interactive interface of terminal device, Yong Huji
In this, response content can be replied for the first time, and specifically, server obtains in reply for the first time of the user using terminal device input
Hold.
Step 204:According to the user reply content and the value relevant information for the first time, carries out response and recommend correlation
Product information.
It is analyzed it after reply content for the first time it should be noted that getting user in step 203, due to user head
Secondary reply content is the reply for response content for the first time, and response content is to be seeked advice to be intended to generate according to prediction for the first time, because
This, reply content can be divided into two classes to user for the first time, and one kind is that prediction consulting is intended to certainly;Another kind of is negative prediction consulting meaning
Figure.Based on different classes of user reply content for the first time, the corresponding value relevant information that selecting step 201 excavates,
Relevant product information is inquired in Products Show library to be recommended.
For example, for " may I ask whether you seek advice from the correlation circumstance of finance product A" response content for the first time, user is for the first time
Reply content may include the content that prediction consulting is intended to certainly such as " correlation circumstance for yes, seeking advice from finance product A ", Huo Zheke
To include the content of the prediction consulting intention such as " not being ... ... " negatives.
First, when reply content includes the content that the prediction consulting is intended to certainly to the user for the first time, indicate prediction
Consulting is intended that correctly, can be based on the proprietary information of user, such as financing note while carrying out taking turns professional response more
Record, risk class and risk partiality etc. choose be consistent with proprietary information and financing in preset finance product library
The relevant product informations of product A are recommended.Therefore, in some embodiments of the present embodiment, the step 204 for example may be used
To include the following steps:
Step 2041:According to user reply content for the first time, response is carried out;
Step 2042:According to the proprietary information, recommend to be intended to relevant product information with prediction consulting in due course.
Wherein, it should be noted that necessary reasonable assurance recommends the opportunity of relevant product information, avoids influencing more wheel professions
Answering, to improve the susceptibility of user, being typically chosen in user's long period carries out Related product letter when not replying response
The recommendation of breath.Therefore, in some embodiments of the present embodiment, the step 2042 is for example specifically as follows:If in response
User's reply content has not been obtained in preset time afterwards, recommends to be intended to relevant product information with prediction consulting.
For example, in the term of validity of response finance product A, risk class, apply to purchase redemption mode etc. after, user does not have in half a minute
Have and reply above-mentioned response, can recommend product information similar with finance product A according to user's proprietary information at this time.
It is of course also possible to which user's reply in acquisition includes actively inquiring that other product informations or negative produce financing
When the certain response contents of product A, for example, it is " having other finance products or not " or " the financing time is too long " etc., root that user, which replys,
Recommend product information similar with finance product A according to user's proprietary information.
Second, when reply content includes the content that the negative prediction consulting is intended to the user for the first time, indicate prediction
Consulting is intended that mistake, at this point it is possible to be based on historical transaction record, that is, the completed transaction such as related finance product of user
Record, especially in the consumer record of the website of bank, specifies the product type etc. involved by it, is produced in preset financing
It chooses in product library and is recommended with the relevant product information of the said goods type, therefore, in some embodiments of the present embodiment
In, the step 204 is for example specifically as follows:According to the user reply content and historical transaction record for the first time, response is carried out
And recommend relevant product information.Certainly.It can also recommend relevant product information on rational opportunity.
It should be noted that due to being to recommend relevant product information in multiple answering, it is contemplated that Related product is believed
The display of breath can preset a recommendation column on the online customer service interactive interface of terminal device, for showing that Related product is believed
Breath to avoid multiple answering is influenced, and then promotes user experience degree of impression;Response content can certainly be directly displayed at
In, so as to user it can directly be seen that relevant product information.Therefore, in some embodiments of the present embodiment, the correlation
Product information, which is shown in, recommends in column and/or response content.
It should also be noted that, in some embodiments of the present embodiment, such as can also include:It converts to artificial visitor
The problem of taking, cannot being replied with manual answering's server etc..At this point, user draws a portrait, information is sent to artificial customer service system for artificial
Customer service is referred to.
The various embodiments provided through this embodiment in response to triggering the operation of customer service control, obtain current first
Information that browsing records and the user including user base information, value relevant information and historical viewings track draws a portrait;Next, according to
The current browsing record and the historical viewings track obtain prediction consulting and are intended to and generate response content for the first time;Then, it obtains
Take it is corresponding described in response content for the first time user's reply content for the first time;Finally, according to user reply content and described for the first time
It is worth relevant information, response is carried out and recommends relevant product information.It can be seen that it is clear with history currently to browse record based on user
Look at the analysis of track, prediction user, which seeks advice from, to be intended to, and based on the reaction that user is intended to prediction consulting, gives the professional response of user
While, relevant product information is recommended to user according to the value relevant information of user.The application is in the base for having professional response
On plinth, in conjunction with the personalized value relevant information of user, realizes that personalization of product, reasonability marketing are recommended, improve customer service intelligence
Change degree, to promote the susceptibility and satisfaction of client.
It should be noted that can only be directed to fixed, professional problem in the prior art carries out the response of stiff ground, do not include
Any greeting sentence, interaction friendly is relatively low, causes user experience poor, in order to solve this problem, can pass through user's body
Part mark excavates user base information, and the greeting language material preset in greeting corpus, Ke Yisheng are combined according to user base information
At some greeting sentences, greeting sentence is added in response so that response content is vividly friendly.For the step in above-described embodiment
Rapid 2022 and step 204, greeting sentence can be added.
Referring to Fig. 3, the flow diagram of the method for another customer service recommended products in the embodiment of the present application is shown.At this
In embodiment, the method for example may comprise steps of:
Step 301:In response to triggering the operation of customer service control, obtains user's portrait information and current browsing records;It is described
User's portrait information further includes user base information, value relevant information and historical viewings track.
Step 302:According to the user base information and default greeting corpus, greeting sentence is determined.
It should be noted that in some embodiments of the present embodiment, compared to step 201, the user of excavation draws a portrait
Information increases user base information, so that step 302 is based on user base information and the generation of default greeting corpus to application
The greeting sentence at family.Wherein, the user base information includes address name and/or user's gender.
Step 303:Record and the historical viewings track are currently browsed described in comparative analysis, are obtained using fuzzy algorithmic approach pre-
Consulting is surveyed to be intended to.
It is understood that step 303 is identical as step 2021, details are not described herein.
Step 304:According to prediction consulting intention and the greeting sentence, response content for the first time is generated.
It should be noted that in some embodiments of the present embodiment, step 304 is being generated compared to step 2022
Greeting sentence is increased in response content for the first time, user can be replied more with open arms, promotes the experience susceptibility of user.For example,
According to prediction consulting intention and the greeting sentence, " you are good, and beauty (handsome boy, Mr. Zhang and Mrs Liu etc.), may I ask you is for generation
The correlation circumstance of no consulting finance product A" response content for the first time.
Step 305:Obtain it is corresponding described in response content for the first time user's reply content for the first time.
It is understood that step 305 is identical as step 203, details are not described herein.
Step 306:According to the user reply content, the value relevant information and the greeting sentence for the first time, carry out
Response simultaneously recommends relevant product information.
It should be noted that in some embodiments of the present embodiment, step 306 is compared to step 204, follow-up more
When taking turns response and recommending relevant product information, greeting sentence is had also combined, so as to be interacted more with open arms with user, is carried
Rise the experience susceptibility of user.For example, according to user reply content, the value relevant information and the greeting sentence for the first time,
Carry out response " you are good, beauty (handsome boy, Mr. Zhang and Mrs Liu etc.), the term of validity of finance product A be ... ", the correlation of recommendation
Product information is that " you are good, beauty (handsome boy, Mr. Zhang and Mrs Liu etc.), and the correlation circumstance of finance product B is ...”.
The various embodiments provided through this embodiment in response to triggering the operation of customer service control, obtain current first
Information that browsing records and the user including user base information, value relevant information and historical viewings track draws a portrait;Next, according to
The current browsing record and the historical viewings track obtain prediction consulting and are intended to and generate response content for the first time;Then, it obtains
Take it is corresponding described in response content for the first time user's reply content for the first time;Finally, according to user reply content and described for the first time
It is worth relevant information, response is carried out and recommends relevant product information.It can be seen that it is clear with history currently to browse record based on user
Look at the analysis of track, prediction user, which seeks advice from, to be intended to, and based on the reaction that user is intended to prediction consulting, gives the professional response of user
While, relevant product information is recommended to user according to the value relevant information of user.The application is in the base for having professional response
On plinth, in conjunction with the personalized value relevant information of user, realizes that personalization of product, reasonability marketing are recommended, improve customer service intelligence
Change degree, to promote the susceptibility and satisfaction of client.
Example devices
Referring to Fig. 4, a kind of structural schematic diagram of the device of customer service recommended products in the embodiment of the present application is shown.In this reality
It applies in example, described device for example can specifically include:
First obtains unit 401 obtains user and draws a portrait information and current clear for the operation in response to triggering customer service control
Look at record;The user draws a portrait information including being worth relevant information and historical viewings track;
Second obtaining unit 402, for according to the current browsing record and the historical viewings track, obtaining prediction and consulting
It askes and is intended to and generates response content for the first time;
First acquisition unit 403, for obtain it is corresponding described in response content for the first time user's reply content for the first time;
Response recommendation unit 404, for according to the user reply content and the value relevant information for the first time, being answered
It answers and recommends relevant product information.
Optionally, the value relevant information includes proprietary information and historical transaction record;The historical viewings track packet
Track is browsed for several times before including.
Optionally, the relevant product information, which is shown in, recommends in column and/or response content.
Optionally, described to answer when reply content includes the content that the prediction consulting is intended to certainly to the user for the first time
Answering recommendation unit 404 includes:
Response subelement, for according to user reply content for the first time, carrying out response;
Recommend subelement, is intended to relevant product with prediction consulting for according to the proprietary information, recommending in due course
Information.
Optionally, the recommendation subelement is specifically used for:
If user's reply content has not been obtained in the preset time after response, recommend to be intended to prediction consulting relevant
Product information.
Optionally, described to answer when reply content includes the content that the negative prediction consulting is intended to the user for the first time
Recommendation unit 404 is answered to be specifically used for:
According to the user reply content and historical transaction record for the first time, carries out response and recommend relevant product information.
Optionally, second obtaining unit 402 includes:
First obtains subelement, for currently browsing record and the historical viewings track described in comparative analysis, using mould
It pastes algorithm and obtains prediction consulting intention;
Subelement is generated, is intended to for being seeked advice from according to the prediction, response content for the first time is generated.
Optionally, the first obtains unit 401 includes:
Subelement is obtained, for the operation in response to triggering customer service control, obtains current browsing record and user identity mark
Know;
Second obtains subelement, for carrying out data mining according to the User Identity, obtains user's portrait information.
Optionally, described device further includes:
Determination unit, for according to the user base information and default greeting corpus, determining greeting sentence.
Optionally, the generation subelement is specifically used for:
According to prediction consulting intention and the greeting sentence, response content for the first time is generated.
Optionally, the response recommendation unit 404 is specifically used for:
According to the user reply content, the value relevant information and the greeting sentence for the first time, carries out response and push away
Recommend relevant product information.
The various embodiments provided through this embodiment, first obtains unit are used for the behaviour in response to triggering customer service control
Make, obtains including currently browsing record and user base information, the user's portrait letter for being worth relevant information and historical viewings track
Breath;Second obtaining unit is used to, according to the current browsing record and the historical viewings track, obtain prediction consulting and be intended to simultaneously
Generate response content for the first time;First acquisition unit be used to obtain it is corresponding described in response content for the first time user's reply content for the first time;
Response recommendation unit is used to, according to the user reply content and the value relevant information for the first time, carry out response and recommend correlation
Product information.It can be seen that currently browsing the analysis of record and historical viewings track based on user, prediction user, which seeks advice from, to be intended to,
Based on the reaction that user is intended to prediction consulting, while giving user's professional response, according to the value relevant information of user
Recommend relevant product information to user.For the application on the basis of having professional response, the personalized value in conjunction with user is related
Information, realize personalization of product, reasonability marketing recommend, improve customer service intelligence degree, to promoted client susceptibility and
Satisfaction.
The embodiment of the present application also provides a kind of server apparatus, which includes:At least one processor and extremely
A few processor;
Wherein, memory is for storing program code, and processor is for calling the program code that the memory is stored
The method for executing the customer service recommended products that above-described embodiment provides.
In addition, the embodiment of the present application also provides a kind of storage medium, the storage medium is described for storing program code
The method that program code is used to execute the customer service recommended products of above-described embodiment offer.
In addition, it includes the computer program product instructed that the embodiment of the present application, which also provides a kind of, when it is transported on computers
When row so that the method that the computer executes the customer service recommended products of above-described embodiment offer.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with other
The difference of embodiment, just to refer each other for identical similar portion between each embodiment.For device disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related place is said referring to method part
It is bright.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, depends on the specific application and design constraint of technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think to exceed scope of the present application.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.The terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or equipment including a series of elements includes not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including institute
State in the process, method, article or equipment of element that there is also other identical elements.
The above is only the preferred embodiment of the application, is not made any form of restriction to the application.Though
Right the application is disclosed above with preferred embodiment, however is not limited to the application.It is any to be familiar with those skilled in the art
Member, in the case where not departing from technical scheme ambit, all using the methods and technical content of the disclosure above to the application
Technical solution makes many possible changes and modifications, or is revised as the equivalent embodiment of equivalent variations.Therefore, it is every without departing from
The content of technical scheme, technical spirit any simple modification made to the above embodiment of foundation the application are equal
Variation and modification, still fall within technical scheme protection in the range of.
Claims (15)
1. a kind of method of customer service recommended products, which is characterized in that including:
In response to triggering the operation of customer service control, obtains user's portrait information and current browsing records;User's portrait information
Including value relevant information and historical viewings track;
According to the current browsing record and the historical viewings track, obtain in prediction consulting is intended to and generates and reply for the first time
Hold;
Obtain it is corresponding described in response content for the first time user's reply content for the first time;
According to the user reply content and the value relevant information for the first time, carries out response and recommend relevant product information.
2. according to the method described in claim 1, it is characterized in that, the value relevant information includes proprietary information and history friendship
Easily record;The historical viewings track browses track for several times before including.
3. according to the method described in claim 1, it is characterized in that, the relevant product information is shown in recommendation column and/or answers
It answers in content.
4. according to the method described in claim 2, it is characterized in that, when reply content includes certainly described pre- to the user for the first time
It is described according to the user reply content and the value relevant information for the first time when surveying the content that consulting is intended to, carry out response simultaneously
Recommend relevant product information, including:
According to user reply content for the first time, response is carried out;
According to the proprietary information, recommend to be intended to relevant product information with prediction consulting in due course.
5. according to the method described in claim 4, it is characterized in that, described according to the proprietary information, recommend in due course with it is described
Prediction consulting is intended to relevant product information, specially:
If user's reply content has not been obtained in the preset time after response, recommend to be intended to relevant product with prediction consulting
Information.
6. according to the method described in claim 2, it is characterized in that, when reply content includes that negative is described pre- to the user for the first time
It is described according to the user reply content and the value relevant information for the first time when surveying the content that consulting is intended to, carry out response simultaneously
Recommend relevant product information in due course, specially:
According to the user reply content and historical transaction record for the first time, carries out response and recommend relevant product information.
7. according to the method described in claim 1, it is characterized in that, described clear according to the current browsing record and the history
It lookes at track, obtains prediction consulting and be intended to simultaneously generate response content for the first time and generate response content for the first time, including:
Record and the historical viewings track are currently browsed described in comparative analysis, are seeked advice from and are intended to using fuzzy algorithmic approach acquisition prediction;
It is seeked advice from and is intended to according to the prediction, generate response content for the first time.
8. according to the method described in claim 1, it is characterized in that, the operation in response to triggering customer service control, is used
Family portrait information and current browsing record, including:
In response to triggering the operation of customer service control, current browsing record and User Identity are obtained;
Data mining is carried out according to the User Identity, obtains user's portrait information.
9. the method according to the description of claim 7 is characterized in that the user draws a portrait, information further includes user base information,
The user base information includes address name and/or user's gender, then the method further includes:
According to the user base information and default greeting corpus, greeting sentence is determined.
10. according to the method described in claim 9, it is characterized in that, described seeked advice from according to the prediction is intended to, generation is answered for the first time
Content is answered, specially:
According to prediction consulting intention and the greeting sentence, response content for the first time is generated.
11. according to the method described in claim 9, it is characterized in that, described according to user reply content and described for the first time
It is worth relevant information, response is carried out and recommends relevant product information, specially:
According to the user reply content, the value relevant information and the greeting sentence for the first time, carries out response and recommend phase
Close product information.
12. a kind of device of customer service recommended products, which is characterized in that including:
First obtains unit obtains user's portrait information and current browsing records for the operation in response to triggering customer service control;
The user draws a portrait information including being worth relevant information and historical viewings track;
Second obtaining unit, for according to the current browsing record and the historical viewings track, obtaining prediction consulting and being intended to
And generate response content for the first time;
First acquisition unit, for obtain it is corresponding described in response content for the first time user's reply content for the first time;
Response recommendation unit, for according to the user reply content and the value relevant information for the first time, carrying out response and pushing away
Recommend relevant product information.
13. a kind of server apparatus, which is characterized in that including:At least one processor and at least one processor;
Wherein, memory is executed for storing program code, the program code that processor is used to that the memory to be called to be stored
The method of customer service recommended products described in claim 1-11 any one.
14. a kind of storage medium, the storage medium is for storing program code, and said program code is for perform claim requirement
The method of customer service recommended products described in 1-11 any one.
15. a kind of includes the computer program product of instruction, when run on a computer so that the computer right of execution
The method that profit requires customer service recommended products described in 1-11 any one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810366792.2A CN108537644A (en) | 2018-04-23 | 2018-04-23 | A kind of method and apparatus of customer service recommended products |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810366792.2A CN108537644A (en) | 2018-04-23 | 2018-04-23 | A kind of method and apparatus of customer service recommended products |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108537644A true CN108537644A (en) | 2018-09-14 |
Family
ID=63477466
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810366792.2A Pending CN108537644A (en) | 2018-04-23 | 2018-04-23 | A kind of method and apparatus of customer service recommended products |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108537644A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109635271A (en) * | 2018-10-22 | 2019-04-16 | 阿里巴巴集团控股有限公司 | A kind of user's intension recognizing method, customer service system, device and electronic equipment |
CN109710941A (en) * | 2018-12-29 | 2019-05-03 | 上海点融信息科技有限责任公司 | User's intension recognizing method and device based on artificial intelligence |
CN109787881A (en) * | 2018-12-26 | 2019-05-21 | 广州灵聚信息科技有限公司 | A kind of dialogue method and device with forecast function |
CN110009397A (en) * | 2019-03-11 | 2019-07-12 | 深圳前海微众银行股份有限公司 | A kind of method and device of precision marketing |
CN111179019A (en) * | 2019-12-02 | 2020-05-19 | 泰康保险集团股份有限公司 | Client data processing method and related equipment |
CN111369303A (en) * | 2020-04-07 | 2020-07-03 | 贵州轻工职业技术学院 | E-commerce promotion system based on cloud computing |
CN111625632A (en) * | 2020-04-17 | 2020-09-04 | 北京捷通华声科技股份有限公司 | Question-answer pair recommendation method, device, equipment and storage medium |
CN111709746A (en) * | 2020-06-09 | 2020-09-25 | 支付宝(杭州)信息技术有限公司 | Risk processing method and device and electronic equipment |
CN113127316A (en) * | 2021-03-18 | 2021-07-16 | 北京沃东天骏信息技术有限公司 | Information processing method and device and storage medium |
CN113469710A (en) * | 2021-07-06 | 2021-10-01 | 携程商旅信息服务(上海)有限公司 | Method, system, electronic device and storage medium for predicting consultation order |
CN113766067A (en) * | 2020-07-27 | 2021-12-07 | 北京京东尚科信息技术有限公司 | Outbound method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105095357A (en) * | 2015-06-24 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Method and device for processing consultation data |
CN105630878A (en) * | 2015-12-17 | 2016-06-01 | 小米科技有限责任公司 | Method and apparatus for displaying application service information |
CN106790004A (en) * | 2016-12-12 | 2017-05-31 | 北京易掌云峰科技有限公司 | Customer service auxiliary real-time prompt system based on artificial intelligence |
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 |
-
2018
- 2018-04-23 CN CN201810366792.2A patent/CN108537644A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105095357A (en) * | 2015-06-24 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Method and device for processing consultation data |
CN105630878A (en) * | 2015-12-17 | 2016-06-01 | 小米科技有限责任公司 | Method and apparatus for displaying application service information |
CN106790004A (en) * | 2016-12-12 | 2017-05-31 | 北京易掌云峰科技有限公司 | Customer service auxiliary real-time prompt system based on artificial intelligence |
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 |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109635271A (en) * | 2018-10-22 | 2019-04-16 | 阿里巴巴集团控股有限公司 | A kind of user's intension recognizing method, customer service system, device and electronic equipment |
CN109787881A (en) * | 2018-12-26 | 2019-05-21 | 广州灵聚信息科技有限公司 | A kind of dialogue method and device with forecast function |
CN109710941A (en) * | 2018-12-29 | 2019-05-03 | 上海点融信息科技有限责任公司 | User's intension recognizing method and device based on artificial intelligence |
CN110009397A (en) * | 2019-03-11 | 2019-07-12 | 深圳前海微众银行股份有限公司 | A kind of method and device of precision marketing |
CN111179019A (en) * | 2019-12-02 | 2020-05-19 | 泰康保险集团股份有限公司 | Client data processing method and related equipment |
CN111369303A (en) * | 2020-04-07 | 2020-07-03 | 贵州轻工职业技术学院 | E-commerce promotion system based on cloud computing |
CN111625632A (en) * | 2020-04-17 | 2020-09-04 | 北京捷通华声科技股份有限公司 | Question-answer pair recommendation method, device, equipment and storage medium |
CN111709746A (en) * | 2020-06-09 | 2020-09-25 | 支付宝(杭州)信息技术有限公司 | Risk processing method and device and electronic equipment |
CN113766067A (en) * | 2020-07-27 | 2021-12-07 | 北京京东尚科信息技术有限公司 | Outbound method and device |
CN113127316A (en) * | 2021-03-18 | 2021-07-16 | 北京沃东天骏信息技术有限公司 | Information processing method and device and storage medium |
CN113469710A (en) * | 2021-07-06 | 2021-10-01 | 携程商旅信息服务(上海)有限公司 | Method, system, electronic device and storage medium for predicting consultation order |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108537644A (en) | A kind of method and apparatus of customer service recommended products | |
US11294968B2 (en) | Combining website characteristics in an automatically generated website | |
CA3040101C (en) | Method and system for searching for and navigating to user content and other user experience pages in a financial management system with a customer self-service system for the financial management system | |
AU2021202128B2 (en) | Method and system for providing domain-specific incremental search results with a customer self-service system for a financial management system | |
US20210042662A1 (en) | Interactive Information Capture and Retrieval with User-Defined and/or Machine Intelligence Augmented Prompts and Prompt Processing | |
Ganguli et al. | Generic technology‐based service quality dimensions in banking: Impact on customer satisfaction and loyalty | |
US6671692B1 (en) | System for facilitating the navigation of data | |
Weber et al. | Coding the News: The role of computer code in filtering and distributing news | |
US20150026075A1 (en) | Control of crm data based on spreadsheet actions | |
US10748157B1 (en) | Method and system for determining levels of search sophistication for users of a customer self-help system to personalize a content search user experience provided to the users and to increase a likelihood of user satisfaction with the search experience | |
US20130117204A1 (en) | Inferring procedural knowledge from data sources | |
US20070050752A1 (en) | Quick-creating objects in an application | |
CN104199648A (en) | General mobile information system adaptation method and device | |
CN109710634A (en) | For generating the method and device of information | |
US8429541B1 (en) | Method and system for video sharing between users of an application | |
CA3157721A1 (en) | Web task automation with vectorization | |
US10387553B2 (en) | Determining and assisting with document or design code completeness | |
Lu | Discovering Microsoft Self-service BI solution: Power BI | |
JP7050830B2 (en) | Information processing system | |
JP4733991B2 (en) | Database management system and database management method | |
US20220350860A1 (en) | Web task automation | |
Kozma et al. | Design of Information System for Bookstore support Student paper | |
JP2007280238A (en) | Data display defining information making device and method, data display device and method, and program used for realizing these devices | |
CN118093801A (en) | Information interaction method and device based on large language model and electronic equipment | |
CN115099211A (en) | Method and system for generating silver insurance proposal |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180914 |
|
RJ01 | Rejection of invention patent application after publication |