CN110019693A - Information recommendation method, server and the computer-readable medium of intelligent customer service - Google Patents

Information recommendation method, server and the computer-readable medium of intelligent customer service Download PDF

Info

Publication number
CN110019693A
CN110019693A CN201710610706.3A CN201710610706A CN110019693A CN 110019693 A CN110019693 A CN 110019693A CN 201710610706 A CN201710610706 A CN 201710610706A CN 110019693 A CN110019693 A CN 110019693A
Authority
CN
China
Prior art keywords
user
node
customer service
intelligent customer
knowledge base
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201710610706.3A
Other languages
Chinese (zh)
Other versions
CN110019693B (en
Inventor
傅星雅
刘警君
曾宝庆
刘玉忠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu Online Network Technology Beijing Co Ltd
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201710610706.3A priority Critical patent/CN110019693B/en
Publication of CN110019693A publication Critical patent/CN110019693A/en
Application granted granted Critical
Publication of CN110019693B publication Critical patent/CN110019693B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Mathematical Physics (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Game Theory and Decision Science (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention provides the information recommendation method, server and computer-readable medium of a kind of intelligent customer service.Its method includes: to obtain the characteristic parameter that user enters intelligent customer service when detecting that user enters intelligent customer service；Obtain the service condition of user；Enter the characteristic parameter of intelligent customer service and the service condition of user according to user, corresponding N number of target problem is obtained from knowledge base；Recommend N number of target problem to user.With in the prior art according to the access action trail forecasting problem of user compared with, technical solution of the present invention, according to the characteristic parameter of the service condition of user and entrance intelligent customer service, the N number of target problem obtained, the problem of user wishes consulting more can be accurately predicted, to effectively improve the accuracy of forecasting problem.Moreover, because effectively increasing the accuracy of forecasting problem, so as to be effectively reduced the operating cost of user, and then the using experience degree of user can be effectively improved.

Description

Information recommendation method, server and the computer-readable medium of intelligent customer service
[technical field]
The present invention relates to computer application technology more particularly to a kind of information recommendation methods of intelligent customer service, service Device and computer-readable medium.
[background technique]
In order to more easily provide the application program (Application of service, many websites and website for user； App) client etc. is the service that user is provided with online customer service.User can carry out problem consulting by online customer service, make With very convenient.
The server end of online customer service in the prior art can be monitored by artificial customer service, receive user by After the problem of line customer service is sent, artificial customer service gives to answer by online mode.It is more next but as the use of network is universal More users carries out problem consulting by selection online customer service, causes artificial customer service operating pressure larger, is unable to satisfy and explodes On-line annealing consulting gradually there is a kind of online intelligent customer service thereupon.Intelligent customer service enters intelligent customer service in user When, it obtains user and enters intelligent customer service before to the access action trail of website or application page, and according to the access of user Action trail, one or more problem that prediction user is likely to be encountered in access process, is sent to user.If user enters It when intelligent customer service, does want to seek advice from one of problem, the problem can be clicked, intelligent customer service returns to user's problem Answer, to complete the on-line consulting of user, on-line consulting process is very intelligent, and user's use is also very convenient.
But in the prior art, user enters intelligent customer service before to the access action trail of website or application page It may be only presentation, have deviated from the problem of being seeked advice from, for example, user enters before intelligent customer service to website or application The access of the page may be that user wants to try to tackle problems on one's own, and if prediction is used according to the access action trail of user Family problem can deviate the real problems of user.Therefore, in the prior art, entered before intelligent customer service to website according to user or The access action trail of application page predicts user's the problem of being seeked advice from, causes the accuracy of forecasting problem lower.
[summary of the invention]
The present invention provides a kind of information recommendation method of intelligent customer service, server and computer-readable mediums, for mentioning The accuracy of high problem prediction.
The present invention provides a kind of information recommendation method of intelligent customer service, which comprises
When detecting that user enters intelligent customer service, the characteristic parameter that the user enters the intelligent customer service is obtained；
Obtain the service condition of the user；
Enter the characteristic parameter of the intelligent customer service and the service condition of the user according to the user, from knowledge base Obtain corresponding N number of target problem；The N is positive integer；
Recommend N number of target problem to the user.
Still optionally further, described after Xiang Suoshu user recommends N number of target problem in method as described above Method further include:
If the first object problem in N number of problem is selected by the user, the first object problem pair is obtained The answer answered:
To the corresponding answer of first object problem described in the user feedback.
Still optionally further, in method as described above, the service condition of the user is obtained, is specifically included:
Obtain the mark of the user；
According to the mark of the user, the service condition of the user is obtained from user information database.
Still optionally further, in method as described above, the characteristic parameter of the intelligent customer service is entered according to the user With the service condition of the user, corresponding N number of target problem is obtained from knowledge base, is specifically included:
Enter the characteristic parameter of the intelligent customer service and the service condition of the user according to the user, from the knowledge Corresponding multiple alternative questions are obtained in library；
Alternative question described in the consulting highest top n of the frequency is obtained from the multiple alternative question, as corresponding institute State N number of target problem.
Still optionally further, in method as described above, the characteristic parameter that the user enters the intelligent customer service is obtained, It specifically includes:
Obtain the entry position that the user enters the intelligent customer service；
Accordingly, the characteristic parameter of the intelligent customer service and the service condition of the user are entered according to the user, from Corresponding multiple alternative questions are obtained in the knowledge base, are specifically included:
The entry position for entering the intelligent customer service according to the user, gets corresponding multiple from the knowledge base First node；
According to the service condition of user described in the service condition of the user and the information table pre-established with it is described The corresponding relationship between node in knowledge base obtains at least one corresponding second node from the multiple first node；
From the second node each in the knowledge base, corresponding the multiple alternative question is obtained.
Still optionally further, in method as described above, the characteristic parameter that the user enters the intelligent customer service is also wrapped Include the consulting time；Accordingly, the characteristic parameter that the user enters the intelligent customer service is obtained, is specifically included:
Obtain entry position and the consulting time of the user into the intelligent customer service；
Accordingly, the user enters the characteristic parameter of the intelligent customer service and the service condition of the user, from described Corresponding multiple alternative questions are obtained in knowledge base, are specifically included:
The entry position for entering the intelligent customer service according to the user is got corresponding described from the knowledge base Multiple first nodes；
According to the service condition of user described in the service condition of the user and the information table pre-established with it is described The corresponding relationship between node in knowledge base obtains at least one corresponding described second section from the multiple first node Point；
According to the corresponding relationship of the consulting peak period in the information table and the node in the knowledge base, obtain each described The corresponding consulting peak period of second node；
According to the consulting time, the official communication of the consulting time hit is obtained from least one described second node Ask at least one third node of peak period；
From the third node each in the knowledge base, corresponding the multiple alternative question is obtained.
Still optionally further, in method as described above, the characteristic parameter of the intelligent customer service is entered according to the user With the service condition of the user, before obtaining corresponding N number of target problem in knowledge base, the method also includes:
The level of the problems in the classification of the product serviced according to the intelligent customer service and every kind of product classification Relationship creates the knowledge base of tree；
According to the history consultation information of the intelligent customer service, all problems of each node in the knowledge base, each institute are excavated State the consulting frequency of the corresponding answer of problem and each described problem；
It is right in the knowledge base that each described problem, the corresponding answer and the corresponding consulting frequency are stored in On the node answered；
According to the history consultation information of the intelligent customer service, each described problem for seeking advice from each node in the knowledge base is excavated The service condition of corresponding user and enters the entry position of the intelligent customer service and asked described in consulting characteristic with concentrating The consulting peak period of topic；
The corresponding entry position into the intelligent customer service is mounted on each node in the knowledge base；
According to the service condition of the corresponding user of each described problem of each node in the knowledge base of excavation, described in acquisition The corresponding relationship between the node in the service condition of user and the knowledge base, and be stored in the information table；
According to the consulting peak period with the described problem for concentrating consulting characteristic of excavation, obtains to have and concentrate consulting characteristic Described problem consulting peak period and the node in the knowledge base corresponding relationship, and be stored in the information table In.
The present invention provides a kind of server of intelligent customer service, and the server includes:
Characteristic parameter obtains module, when for detecting that user enters intelligent customer service, obtains the user into the intelligence The characteristic parameter of energy customer service；
Service condition obtains module, for obtaining the service condition of the user；
Problem obtains module, for entering the characteristic parameter of the intelligent customer service and the industry of the user according to the user Business state obtains corresponding N number of target problem from knowledge base；The N is positive integer；
Recommending module, for recommending N number of target problem to the user.
Still optionally further, in server as described above, the server further include:
Answer obtains module, if the first object problem in N number of problem is selected by the user, obtains institute State the corresponding answer of first object problem:
The recommending module is also used to the corresponding answer of first object problem described in the user feedback.
Still optionally further, in server as described above, the service condition obtains module, is specifically used for:
Obtain the mark of the user；
According to the mark of the user, the service condition of the user is obtained from user information database.
Still optionally further, in server as described above, described problem obtains module, is specifically used for:
Enter the characteristic parameter of the intelligent customer service and the service condition of the user according to the user, from the knowledge Corresponding multiple alternative questions are obtained in library；
Alternative question described in the consulting highest top n of the frequency is obtained from the multiple alternative question, as corresponding institute State N number of target problem.
Still optionally further, in server as described above, the characteristic parameter obtains module, is specifically used for described in acquisition User enters the entry position of the intelligent customer service；
Accordingly, described problem obtains module, is specifically used for:
The entry position for entering the intelligent customer service according to the user, gets corresponding multiple from the knowledge base First node；
According to the service condition of user described in the service condition of the user and the information table pre-established with it is described The corresponding relationship between node in knowledge base obtains at least one corresponding second node from the multiple first node；
From the second node each in the knowledge base, corresponding the multiple alternative question is obtained.
Still optionally further, in server as described above, the characteristic parameter obtains module, is specifically used for described in acquisition Entry position and the consulting time of the user into the intelligent customer service；
Accordingly, described problem obtains module, is specifically used for:
The entry position for entering the intelligent customer service according to the user is got corresponding described from the knowledge base Multiple first nodes；
According to the service condition of user described in the service condition of the user and the information table pre-established with it is described The corresponding relationship between node in knowledge base obtains at least one corresponding described second section from the multiple first node Point；
According to the corresponding relationship of the consulting peak period in the information table and the node in the knowledge base, obtain each described The corresponding consulting peak period of second node；
According to the consulting time, the official communication of the consulting time hit is obtained from least one described second node Ask at least one third node of peak period；
From the third node each in the knowledge base, corresponding the multiple alternative question is obtained.
Still optionally further, in server as described above, the server further include:
Asking in creation module, the classification of the product for being serviced according to the intelligent customer service and every kind of product The hierarchical relationship for inscribing classification, creates the knowledge base of tree；
It excavates module and excavates each node in the knowledge base for the history consultation information according to the intelligent customer service The consulting frequency of all problems, the corresponding answer of each described problem and each described problem；
Memory module, for each described problem, the corresponding answer and the corresponding consulting frequency to be stored in In the knowledge base on corresponding node；
The excavation module is also used to the history consultation information according to the intelligent customer service, excavates and seeks advice from the knowledge base In each node the corresponding user of each described problem service condition and enter the intelligent customer service entry position and have Concentrate the consulting peak period of the described problem of consulting characteristic；
The memory module is also used to mount on each node in the knowledge base corresponding into the intelligence The entry position of customer service；
The memory module is also used to the corresponding user of each described problem of each node in the knowledge base according to excavation Service condition, obtain the corresponding relationship between the node in the service condition and the knowledge base of the user, and deposit Storage is in the information table；
The memory module is also used to the consulting peak period with the described problem for concentrating consulting characteristic according to excavation, The corresponding relationship of the consulting peak period and the node in the knowledge base with the described problem for concentrating consulting characteristic is obtained, And it is stored in the information table.
The present invention also provides a kind of server apparatus, the equipment includes:
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing Device realizes the information recommendation method of intelligent customer service as described above.
The present invention also provides a kind of computer-readable mediums, are stored thereon with computer program, which is held by processor The information recommendation method of intelligent customer service as described above is realized when row.
Information recommendation method, server and the computer-readable medium of intelligent customer service of the invention detect that user enters When intelligent customer service, the characteristic parameter of intelligent customer service is entered by obtaining user；Obtain the service condition of user；Entered according to user The characteristic parameter of intelligent customer service and the service condition of user obtain corresponding N number of target problem from knowledge base；Recommend to user N number of target problem.With in the prior art according to the access action trail forecasting problem of user compared with, technical solution of the present invention, According to the service condition of user and into the characteristic parameter of intelligent customer service, N number of target problem of acquisition more can be predicted accurately User wishes the problem of consulting, to effectively improve the accuracy of forecasting problem.Moreover, because effectively increasing prediction The accuracy of problem so as to be effectively reduced the operating cost of user, and then can effectively improve the use body of user Degree of testing.
[Detailed description of the invention]
Fig. 1 is the flow chart of the information recommendation method embodiment one of intelligent customer service of the invention.
Fig. 2 is the structure chart of the server example one of intelligent customer service of the invention.
Fig. 3 is the structure chart of the server example two of intelligent customer service of the invention.
Fig. 4 is the structure chart of server apparatus embodiment of the invention.
Fig. 5 is a kind of exemplary diagram of server apparatus provided by the invention.
[specific embodiment]
To make the objectives, technical solutions, and advantages of the present invention clearer, right in the following with reference to the drawings and specific embodiments The present invention is described in detail.
Fig. 1 is the flow chart of the information recommendation method embodiment one of intelligent customer service of the invention.As shown in Figure 1, this implementation The information recommendation method of the intelligent customer service of example, can specifically include following steps:
100, when detecting that user enters intelligent customer service, the characteristic parameter that user enters intelligent customer service is obtained；
The executing subject of the information recommendation method of the intelligent customer service of the present embodiment is the server of intelligent customer service.Intelligence visitor The server of clothes can with the website of the network company serviced or App client or other Platform communications, for the network The online customer service that the various entrances of company are come in provides service.
In the present embodiment, user, which enters intelligent customer service, has certain characteristic, for example, user can provide the net of website Online customer service entrance on page enters intelligent customer service, can also enter intelligence by the online customer service entrance in the APP of the website Customer service, or intelligent customer service can also be entered by the online customer service entrance for other service platforms that the website provides.If such as Certain financing website, publication have a plurality of finance products and insurance products, per a product introduction page all can chain be connected to intelligent visitor The entrance of clothes.Equally, in App, also the entrance of intelligent customer service can be connected in the introduction page chain of each product.Therefore, may be used Selection of land, in the present embodiment, the characteristic parameter into intelligent customer service may include the entry position of intelligent customer service, it is generally the case that User wants the problem of consulting which aspect, usually will enter intelligent customer service in the page for the product for generating relevant issues, therefore, It can predict the direction for the problem of user wants consulting more accurately into the entry position of intelligent customer service.No matter user passes through Which kind of mode enters intelligent customer service, available to use when the server of intelligent customer service detects that user enters intelligent customer service Family enters the characteristic parameter of intelligent customer service, such as entry position.
101, the service condition of user is obtained；
The service condition of user can be each stage of the user in the business used in the present embodiment.Such as purchase one The service condition of item service may include unactivated state, state of activation etc. after not buying state, purchase.Such as one loan again The service condition of money application may include copending state after non-application status, application, examination & approval by state to be made loans, refund shape State, releasing loan status etc..In a comparable manner, can be according to the characteristic of business for each business, determining should The state of business.
Such as the step 101, it can specifically include: obtaining the mark of user；According to the mark of user, from user information database The middle service condition for obtaining user.
In the present embodiment, the user for seeking advice from intelligent customer service can be login user, and the mark of the user can be to be somebody's turn to do at this time The account of user.In the server of intelligent customer service, it can store user information database, the website be stored in user information database The information of all users serviced, such as may include the service identification handled of account, contact method and user of user And the service condition of every kind of business.Such as to Mr. Yu's loan application website, user can be borrowed by App or website application Money in the user information database stored in the server of the intelligent customer service of the website, can recorde user of each application Information, such as account, name and the contact method information of user can also be stored with the service condition of the user, such as Shen It please stage, approval stage and refund stage etc..For different business, the service condition of corresponding different user, herein No longer citing repeats one by one.In addition, if user has applied for multinomial business simultaneously in certain website, it accordingly, can be according to the use The mark at family can obtain the service condition of each single item business of user's application from the user information database of intelligent customer service.
Need to illustrate when, for the mark of some user, if the also not stored information for having the user in user information database, Then indicate that the user does not carry out any related service also, service condition at this time can be identified as 0, i.e., do not have any business into Exhibition.
Optionally, in the present embodiment, for entering intelligent customer service with tourist's identity, that is, be not logged in user or not infusing The user of volume account, the mark of the service condition of corresponding user all can be 0, i.e., do not there is any business to be in progress.
102, enter the characteristic parameter of intelligent customer service and the service condition of user according to user, obtain and correspond to from knowledge base N number of target problem；
103, recommend N number of target problem to user.
In the present embodiment, the characteristic parameter of intelligent customer service and the service condition of user are entered according to user, from knowledge base When obtaining corresponding N number of target problem, it is acquisition N that wherein user, which enters the characteristic parameter of intelligent customer service and the service condition of user, Two conditions of a target problem.N number of target problem for obtaining needs while meeting the two conditions just can be with.Obtaining N A problem, the two conditions can first screen the characteristic parameter met into intelligent customer service, can also first screen and meet user's Service condition.If the characteristic parameter into intelligent customer service is into the entry position of intelligent customer service, the two conditions are preferentially sieved Choosing meets the alternative question into the entry position condition of intelligent customer service, and then screening meets use from obtained alternative question again The problem of condition of the service condition at family, finally obtains N number of target problem.
Optionally, the step 102 in the present embodiment " enters the characteristic parameter of intelligent customer service and the business of user according to user State obtains corresponding N number of target problem from knowledge base " it can specifically include: enter the feature of intelligent customer service according to user The service condition of parameter and user obtains corresponding multiple alternative questions from knowledge base；It obtains and consults from multiple alternative questions The highest top n alternative question of the frequency is ask, as corresponding N number of target problem.That is, if directly by multiple alternative questions If target problem, the quantity of alternative question may be more, causes Important Problems not prominent enough, can be from the present embodiment The higher top n of the consulting frequency that history is obtained in multiple alternative questions, as target problem.
It should be noted that if the lazy weight of alternative question it is N number of or be equal to it is N number of, then all by all alternative questions As target problem.If it is user when entering the entry position of intelligent customer service that user, which enters the characteristic parameter of intelligent customer service, according to User enters the characteristic parameter of intelligent customer service and the service condition of user, and corresponding multiple alternative questions are obtained from knowledge base When, it is preferable that first according to the entry position for entering intelligent customer service, corresponding several problems are obtained from knowledge base, then root again Corresponding multiple alternative questions are obtained from several problems according to the service condition of user.Finally obtained from multiple alternative questions again The highest top n alternative question of the frequency is seeked advice from,
The knowledge base of the present embodiment can be all productions included in the website that is serviced previously according to the intelligent customer service What various types of other problem under product and each product created.For example, the product for an education by stages, can have below The problem of classifications such as " amount applications ", " amount activation ", " consulting of making loans ", " refund problem " and " refund consulting ".Wherein, " refund problem " can have the problems such as " how refunding ", " repayment amount ", " overdue refund " and " payment beforehand " further below.Its In, " how refunding " has the problems such as " APP refund ", " exempting from close refund " and " automatic to refund " below.In this way, education by stages can be with As level-one father node, " amount application ", " amount activation ", " consulting of making loans ", " refund problem " and " refund consulting " is divided into Child node as father node " education is by stages "；Further, it " how refunding ", " repayment amount ", " overdue refund " and " mentions Preceding refund " is also used as the child node of " refund problem "；" APP refund ", " exempting from close refund " and " automatic refund " can be with Child node as " how refunding ".According to the set membership of the node of above-mentioned each problem, corresponding tree-shaped knot can be created The knowledge base of structure.According to the structure of above-mentioned knowledge base, the knowledge base of similar tree can be created in each website.
Wherein " how the refunding " of knowledge base, " repayment amount ", " overdue refund ", " payment beforehand ", " APP refund ", " exempting from close refund " and " automatic to refund " etc. can be in the most downstream site of tree of the knowledge base, in each most junior Node in can correspond to and be stored with one or more knowledge point, each knowledge point include a problem under corresponding node and Corresponding answer may include the consulting frequency of the knowledge point in the corresponding attribute information in each knowledge point.And in the knowledge In library, each node can mount multiple entry positions into intelligent customer service.Similarly, in the node in knowledge based library Also there are corresponding relationships with the service condition of user for problem, therefore, can pre-establish information table, store the business shape of user The corresponding relationship between node in state and knowledge base facilitates subsequent according to the service condition of user acquisition target problem.For There is the problem of concentration consulting characteristic, it can also be counted in advance and seek advice from peak period, while recording the official communication of problem in information table Ask peak period and the problem corresponding node in knowledge base corresponding relationship, facilitate it is subsequent according to seek advice from the time whether hit official communication Peak period is ask, to obtain target problem.
In the present embodiment, user, which is in different service conditions, can seek advice from different problems, public with the network for providing service For department, for not buying the user of service, the problem of service condition 0, user seeks advice from, can be more biased towards in how buying, buy Cost issues and payment problem etc. when the service enjoyed afterwards, purchase.And for having bought service but in unactivated industry The problem of user of business state, consulting, can be more biased towards the various mistakes in how activating, activate points for attention and activate such as The problems such as what reply etc..For the user of service condition for having bought service and having activated, the problem of consulting can be more biased towards in If the problems in using, subsequent continuing to use the problem of continuing to pay dues and if stop the problem of using refund etc. in advance.? That is can all have the downstream site of matched node and node in knowledge base for each service condition In multiple knowledge points in multiple problems.
Similarly, the entry position that intelligent customer service is entered for each, can all have matched section in knowledge base Multiple problems in multiple knowledge points in point and node downstream site.In this way, entering the entrance of intelligent customer service according to user The service condition of position and user obtains user from knowledge base and enters the entry position of intelligent customer service and the service condition of user Common corresponding N number of target problem.It is then possible to which the interface linked up by intelligent customer service and the user, recommends to obtain to user N number of target problem.In the present embodiment, the entry position of intelligent customer service and the service condition of user are entered according to user, from knowing The quantity that N in corresponding N number of target problem is obtained in knowledge library can be arranged according to actual needs, for example, can choose 3,5 A perhaps 10 or other integers.
Specifically, when the characteristic parameter for entering intelligent customer service for user is that user enters the entry position of intelligent customer service, " user enters the characteristic parameter of intelligent customer service and the service condition of user to step in above-described embodiment, obtains from knowledge base Corresponding multiple alternative questions ", can specifically include following steps:
(a1) entry position for entering intelligent customer service according to user gets corresponding multiple first segments from knowledge base Point；
(b1) according in the service condition of user and the information table pre-established in the service condition and knowledge base of user Node between corresponding relationship, at least one corresponding second node is obtained from multiple first nodes；
(c1) from second node each in knowledge base, corresponding multiple alternative questions are obtained.
Above-mentioned steps (a1)-(c1) realizes the successively screening when obtaining multiple alternative questions, to multiple conditions.For example, Screening meets the node that user enters the entry position condition of intelligent customer service first, and corresponding multiple the are got from knowledge base One node；Then according in the service condition of user and the information table pre-established in the service condition and knowledge base of user Node between corresponding relationship, from multiple first nodes screen user at least one corresponding second section of service condition Point.Wherein, each first node and each second node can may be lowest level node for the middle layer node in knowledge base.If When second node is the lowest level node in knowledge base, it may include multiple knowledge points in the second node, can know from multiple Know in point and obtains multiple problems alternately problem.And if second node be knowledge base intermediate node when, can be from the knowledge Corresponding multiple problems alternately problem is obtained in library in the corresponding lowest level child node of the second node.
Further optionally, it further includes the consulting time that the user of the present embodiment, which enters the characteristic parameter of intelligent customer service,；This The granularity of the consulting time of embodiment can be arranged according to the demand of product business.Such as using the moon as the loan of payment period Refund product, corresponding consulting time can accordingly seek advice from the peak of time using day as Grain Size Record using day as Grain Size Record Phase.If monthly No. 18 for refund the date, can be set monthly No. 13-18 for refund consulting peak period, for consulting the time exist Consulting during this, the relevant relevant N number of target problem of refunding of the service condition of preferably push user.
Specifically, the characteristic parameter for entering intelligent customer service for user is entry position and the official communication that user enters intelligent customer service When asking the time, " user enters the characteristic parameter of intelligent customer service and the service condition of user to the step in above-described embodiment, from knowledge Corresponding multiple alternative questions are obtained in library ", it can specifically include following steps:
(a2) entry position for entering intelligent customer service according to user gets corresponding multiple first segments from knowledge base Point；
(b2) according in the service condition of user and the information table pre-established in the service condition and knowledge base of user Node between corresponding relationship, at least one corresponding second node is obtained from multiple first nodes；
(c2) according to the corresponding relationship of the consulting peak period in information table and the node in knowledge base, each second node is obtained Corresponding consulting peak period；
(d2)) according to the consulting time, the consulting peak period of consulting time hit is obtained from least one second node At least one third node；
(e2) from third node each in knowledge base, the corresponding multiple default problems in the corresponding consulting peak period of acquisition are made For multiple alternative questions.
The step of the present embodiment (a2)-(e2) and above-mentioned steps (a1)-(c1) difference is, obtains in the present embodiment multiple When alternative question, screening conditions user enter intelligent customer service entry position and user service condition on the basis of, increase Screening conditions seek advice from times.Screening conditions pay the utmost attention to sequence are as follows: preferential screening meets the entrance that user enters intelligent customer service Secondly multiple first nodes of locality condition screen the service condition item for meeting user from the multiple first nodes screened Multiple second nodes of part, then again from obtained multiple second nodes screening meet consulting time conditions at least one the Three nodes.Wherein specifically can first it be obtained when screening at least one third node from multiple second nodes according to the consulting time The consulting peak period of each second node, then whether the judgement current consulting time hits the consulting peak of certain second nodes Phase, if hit, filters out corresponding second node as third node.If otherwise miss, the second node is abandoned.It can manage Xie Wei, the knowledge point stored in the most junior child node in third node or third node downstream are all that consulting peak period is corresponding The problem of and corresponding answer.For example, being the date of refunding for monthly No. 18, monthly No. 13-18 is consulting peak period of refunding, Consulting for the consulting time in this consulting peak period, can be defaulted as all being the consulting about refund relevant issues, can be with The knowledge point of the related problem of storage refund in the most downstream site in the corresponding node in consulting peak period or downstream, this Sample, when subsequent screening third node, if consulting time hit consulting peak period, can filter out the node, so as to obtain Relevant multiple problems of refunding are got, alternately problem.
Such as it is relevant multiple for refund using the moon as the loan repayment product in period, can be got in the manner described above Alternative question finally obtains the consulting highest top n alternative question of the frequency, as corresponding N number of mesh from multiple alternative questions Mark problem.Similarly, it if the lazy weight for the relevant multiple alternative questions of refunding is N number of or be equal to N number of, will refund relevant multiple Alternative question is all used as corresponding target problem.
In the present embodiment, for the consulting other than refund peak period, then enter the entrance of intelligent customer service also according to user The service condition of position and user obtains corresponding N number of target problem from knowledge base, and detailed implementation process is same as above, herein not It repeats again.
Above-described embodiment is seeked advice from the time by Grain Size Record of day,, can be according to production for other products in practical application The characteristic in the period of product itself is such as a cycle daily, and the granularity for seeking advice from the time can be hour.For the guarantor to continue to pay dues every year The product of dangerous class is a cycle every year, and the granularity for seeking advice from the time can be moon etc., and no longer citing repeats one by one herein.
Still optionally further, it in the present embodiment, after step 103 " recommending N number of target problem to user ", can also wrap It includes: if the first object problem in N number of target problem is easily selected by a user, obtaining the corresponding answer of first object problem: Xiang Yong Feed back the corresponding answer of first object problem in family.Specifically, the corresponding answer of acquisition first object problem from knowledge base, and to User feedback.
Still optionally further, the step 102 of the present embodiment " enters characteristic parameter and the user of intelligent customer service according to user Before service condition, from obtaining corresponding N number of target problem in knowledge base ", it can also include the following steps:
(a3) hierarchical relationship of the problems in the classification of the product serviced according to intelligent customer service and every kind of product classification, Create the knowledge base of tree；
(b3) according to the history consultation information of intelligent customer service, all problems of each node, each problem pair in Extracting Knowledge library The consulting frequency of the answer and each problem answered；
(c3) each problem, corresponding answer and the corresponding consulting frequency are stored in knowledge base on corresponding node；
It can be wherein stored in corresponding node using each problem and corresponding answer as a knowledge point, seek advice from the frequency Attribute information as the knowledge point is stored in the attribute of the knowledge point.
(d3) according to the history consultation information of intelligent customer service, the corresponding use of each problem of each node in knowledge information base is excavated The service condition at family and the entry position of entrance intelligent customer service and the consulting peak period with the problem of concentrating consulting characteristic；
(e3) the corresponding entry position into intelligent customer service is mounted on each node in knowledge base；
(f3) according to the service condition of the corresponding user of each problem of node each in the knowledge base of excavation, the industry of user is obtained The corresponding relationship between node in business state and knowledge base, and be stored in information table；
(g3) it according to the consulting peak period with the problem of concentrating consulting characteristic of excavation, obtains to have and concentrates consulting characteristic The problem of consulting peak period and the node in knowledge base corresponding relationship, and be stored in information table.
Above-mentioned steps (a3)-(g3) process is creation of knowledge library and establishes the process of information table according to knowledge base, with Convenient for subsequent according to screening conditions, and the information table for combining knowledge base and being established according to knowledge base, it obtains and corresponds to from knowledge base Target problem.Wherein the process of the tree in creation of knowledge library can refer to the explanation of above-mentioned related embodiment.Knowledge base In middle lowest level node when the generation and storage of stored knowledge point, need to acquire the history consultation information of intelligent customer service, such as this The history consultation information of embodiment not only includes the problem of intelligent customer service is user's push and answer.It further include simultaneously user in intelligence Can customer service push the problem of and answer in do not solve the problem of oneself and oneself is inputted, by the work of intelligent customer service Personnel's manual type answers the answer of the problem of user.That is, the server of intelligent customer service can also acquire user in the present embodiment The problem of answer of the problem is answered in the problem of oneself input and artificial customer service, enriches intelligent customer service information.Then intelligent customer service History consultation information excavates various types of other all problems in intelligent customer service and the corresponding answer of each problem.The present embodiment Classification can be intelligent customer service service classification, for example, some websites include 5 products, each product can correspond to one A classification, each classification there are problems that corresponding to be consulted.Further, for being wrapped inside each product again Include various junior's classifications, such as pre-sales (service condition for not buying service can be corresponded to), activation, payment, junior's class of refunding Not, there is also corresponding the problem of may being consulted for each junior's classification；Further, for it is pre-sales, activation, payment and Each of refund junior's classification further can also include the classification of lower-level.And so on, it is available to arrive the intelligence All hierarchical categories in the classification for the product that customer service is serviced and each product.According to the classification of each level, can be generated Tree-shaped knowledge base structure.It then can be by the corresponding each knowledge point of each classification, i.e. problem, corresponding answer and attribute letter The breath such as consulting frequency, is stored in a undermost corresponding node for the knowledge base.For example, in above-described embodiment The knowledge point of education product by stages is stored in the education by stages in corresponding most downstream site." refunding under wherein educating by stages It is all kinds of that problem " the corresponding knowledge point of classification is stored in " how refunding ", " repayment amount ", " overdue refund " and " payment beforehand " In not corresponding node；Further, for example, the corresponding knowledge point of " how refunding " classification is stored in " APP refund ", " exempts from close In refund " and " automatic to refund " corresponding knowledge point of all categories.In the manner described above, the corresponding each knowledge point of each classification It can be stored in corresponding most downstream site according to the corresponding relationship of the classification of each layer in knowledge base.
In addition, each problem of each node in knowledge information base can also be excavated according to the history consultation information of intelligent customer service The service condition of corresponding user and the entry position of entrance intelligent customer service and the consulting with the problem of concentrating consulting characteristic Peak period.Then according to the information of excavation, the corresponding entry position into intelligent customer service will be mounted on each node, that is, Will, each node establishes corresponding relationship with the corresponding entry position into intelligent customer service, and a node can be right in the present embodiment Answer one, two or more enter intelligent customer service entry position.Then according to the information of excavation, the business shape of user is established The corresponding relationship between node in state and knowledge base in the present embodiment, corresponding relationship can be stored in an information table, In the information table, the corresponding pass between the mark of the service condition of user and the node identification in knowledge base can be directly stored System, with the corresponding relationship between the node in the service condition and knowledge base of identity user.Meanwhile in the information table, may be used also To store the consulting peak period of certain nodes, since the problems in some knowledge points have the characteristic for concentrating consulting, the present embodiment In, it can establish the corresponding relationship of the consulting peak period and the corresponding node in knowledge base with the problem of concentrating consulting characteristic, And it stores in the information.That is, there is also corresponding consulting peak periods for some nodes in information table.It is high in the presence of corresponding consulting The problems in knowledge point in the node of peak phase has the characteristic for concentrating consulting.In the manner described above, knowledge base and information table be just It establishes.It is subsequent corresponding target to be obtained in the way of above-described embodiment from knowledge base according to knowledge base and information table Problem.
The information recommendation method of the intelligent customer service of the present embodiment when detecting that user enters intelligent customer service, is used by obtaining Family enters the characteristic parameter of intelligent customer service；Obtain the service condition of user；According to user enter intelligent customer service characteristic parameter and The service condition of user obtains corresponding N number of target problem from knowledge base；Recommend N number of target problem to user.With existing skill It is compared in art according to the access action trail forecasting problem of user, the technical solution of the present embodiment, according to the service condition of user With the characteristic parameter for entering intelligent customer service, N number of target problem of acquisition more can accurately predict that user wishes asking for consulting Topic, to effectively improve the accuracy of forecasting problem.Moreover, because the accuracy of forecasting problem is effectively increased, from And it can be effectively reduced the operating cost of user, and then the using experience degree of user can be effectively improved.
Fig. 2 is the structure chart of the server example one of intelligent customer service of the invention.As shown in Fig. 2, the intelligence of the present embodiment The server of energy customer service, can specifically include: characteristic parameter obtains module 10, service condition obtains module 11, problem obtains mould Block 12 and recommending module 13.
Wherein characteristic parameter obtains module 10 for when detecting that user enters intelligent customer service, acquisition user to enter intelligent visitor The characteristic parameter of clothes；
Service condition obtains the service condition that module 11 is used to obtain user；
Problem obtains module 12 and is used to obtain the characteristic parameter into intelligent customer service that module 10 obtains according to characteristic parameter The service condition that the user that module 11 obtains is obtained with service condition, obtains corresponding N number of target problem from knowledge base；N is Positive integer；
Recommending module 13 is used to recommend problem to obtain N number of target problem that module 12 obtains to user.
The server of the intelligent customer service of the present embodiment realizes the reality of the information recommendation of intelligent customer service by using above-mentioned module Existing principle and technical effect are identical as the realization of above-mentioned related method embodiment, can implement in detail with reference to above-mentioned correlation technique The record of example, details are not described herein.
Fig. 3 is the structure chart of the server example two of intelligent customer service of the invention.As shown in figure 3, the intelligence of the present embodiment The server of energy customer service further introduces this hair on the basis of the technical solution of above-mentioned embodiment illustrated in fig. 2 in further detail Bright technical solution.
As shown in figure 3, in the server of the intelligent customer service of the present embodiment, further includes:
If first object problem of the answer acquisition module 14 in N number of problem is easily selected by a user, first object is obtained The corresponding answer of problem:
Recommending module 13 is also used to obtain the corresponding answer of first object problem that module 14 obtains to user feedback answer.
Still optionally further, in the server of the intelligent customer service of the present embodiment, service condition obtains module 10 and is specifically used for:
Obtain the mark of user；
According to the mark of user, the service condition of user is obtained from user information database.
Still optionally further, in the server of the intelligent customer service of the present embodiment, problem obtains module 12 and is specifically used for:
Characteristic parameter and the service condition acquisition that the user that module 10 obtains enters intelligent customer service are obtained according to characteristic parameter The service condition for the user that module 11 obtains, obtains corresponding multiple alternative questions from knowledge base；
The consulting highest top n alternative question of the frequency is obtained from multiple alternative questions, is asked as corresponding N number of target Topic.
Still optionally further, in the server of the intelligent customer service of the present embodiment, characteristic parameter obtains module 10 and is specifically used for Obtain the entry position that user enters intelligent customer service；
Accordingly, problem obtains module 12 and is specifically used for:
The entry position that the user that module 10 obtains enters intelligent customer service is obtained according to characteristic parameter, is obtained from knowledge base To corresponding multiple first nodes；
According to user in the information table that service condition obtains the service condition for the user that module 11 obtains and pre-establishes Service condition and knowledge base in node between corresponding relationship, obtained from multiple first nodes it is corresponding at least one Two nodes；
From second node each in knowledge base, corresponding multiple alternative questions are obtained.
Still optionally further, in the server of the intelligent customer service of the present embodiment, characteristic parameter obtains module 11 and is specifically used for Obtain entry position and consulting time that user enters intelligent customer service；
Accordingly, problem obtains module 12 and is specifically used for:
The entry position that the user that module 10 obtains enters intelligent customer service is obtained according to characteristic parameter, is obtained from knowledge base To corresponding multiple first nodes；
According to user in the information table that service condition obtains the service condition for the user that module 11 obtains and pre-establishes Service condition and knowledge base in node between corresponding relationship, obtained from multiple first nodes it is corresponding at least one Two nodes；
According to the corresponding relationship of the consulting peak period in information table and the node in knowledge base, it is corresponding to obtain each second node Consulting peak period；
According to the consulting time, at least the one of the consulting peak period of consulting time hit is obtained from least one second node A third node；
From third node each in knowledge base, corresponding multiple alternative questions are obtained.
Still optionally further, as shown in figure 3, in the server of the intelligent customer service of the present embodiment, further includes:
The problems in the classification for the product that creation module 15 is used to be serviced according to intelligent customer service and every kind of product classification Hierarchical relationship, create the knowledge base of tree；
Module 16 is excavated for the history consultation information according to intelligent customer service, is excavated in the knowledge base that creation module 15 creates The consulting frequency of all problems of each node, the corresponding answer of each problem and each problem；
Memory module 17 is used to for each problem, corresponding answer and the corresponding consulting frequency being stored in corresponding in knowledge base Node on；
It excavates module 16 and is also used to the history consultation information according to intelligent customer service, excavate knowing for the consulting creation of creation module 15 Know the service condition of the corresponding user of each problem of each node and user in library to enter the entry position of intelligent customer service and have The consulting peak period for the problem of concentrating consulting characteristic；
Memory module 17 is also used to mount the corresponding entry position into intelligent customer service on each node in knowledge base；
Memory module 17 is also used to the service condition of the corresponding user of each problem of each node in the knowledge base according to excavation, The corresponding relationship between the node in the service condition and knowledge base of user is obtained, and is stored in information table；
Memory module 17 is also used to be had according to the consulting peak period with the problem of concentrating consulting characteristic of excavation, acquisition The consulting peak period for the problem of concentrating consulting characteristic and the corresponding relationship of the node in knowledge base, and be stored in information table.
Accordingly, problem obtains module 12 and is used to obtain the spy into intelligent customer service that module 10 obtains according to characteristic parameter It levies parameter and service condition obtains the service condition for the user that module 11 obtains, obtained from the knowledge base that creation module 15 creates Corresponding N number of target problem.
The server of the intelligent customer service of the present embodiment realizes the reality of the information recommendation of intelligent customer service by using above-mentioned module Existing principle and technical effect are identical as the realization of above-mentioned related method embodiment, can implement in detail with reference to above-mentioned correlation technique The record of example, details are not described herein.
Fig. 4 is the structure chart of server apparatus embodiment of the invention.As shown in figure 4, the server apparatus of the present embodiment, It include: one or more processors 30 and memory 40, memory 40 works as memory for storing one or more programs The one or more programs stored in 40 are executed by one or more processors 30, so that one or more processors 30 are realized such as The information recommendation method of figure 1 above-embodiment illustrated in fig. 3 intelligent customer service.To include multiple processors 30 in embodiment illustrated in fig. 4 For.
For example, Fig. 5 is a kind of exemplary diagram of server apparatus provided by the invention.Fig. 5, which is shown, to be suitable for being used to realizing this The block diagram of the example server device 12a of invention embodiment.The server apparatus 12a that Fig. 5 is shown is only an example, Should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 5, server apparatus 12a is showed in the form of universal computing device.The component of server apparatus 12a can To include but is not limited to: one or more processor 16a, system storage 28a connect different system components (including system Memory 28a and processor 16a) bus 18a.
Bus 18a indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller, Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC) Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Server apparatus 12a typically comprises a variety of computer system readable media.These media can be it is any can The usable medium accessed by server apparatus 12a, including volatile and non-volatile media, moveable and immovable Jie Matter.
System storage 28a may include the computer system readable media of form of volatile memory, such as deposit at random Access to memory (RAM) 30a and/or cache memory 32a.Server apparatus 12a may further include it is other it is removable/ Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 34a can be used for reading Write immovable, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 5, The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and non-easy to moving The CD drive that the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) is read and write.In these cases, each Driver can be connected by one or more data media interfaces with bus 18a.System storage 28a may include at least One program product, the program product have one group of (for example, at least one) program module, these program modules are configured to hold The function of the above-mentioned each embodiment of Fig. 1-Fig. 3 of the row present invention.
Program with one group of (at least one) program module 42a/utility 40a, can store and deposit in such as system In reservoir 28a, such program module 42a include --- but being not limited to --- operating system, one or more application program, It may include the reality of network environment in other program modules and program data, each of these examples or certain combination It is existing.Program module 42a usually executes the function and/or method in above-mentioned each embodiment of Fig. 1-Fig. 5 described in the invention.
Server apparatus 12a can also be with one or more external equipment 14a (such as keyboard, sensing equipment, display 24a etc.) communication, the equipment interacted with server apparatus 12a communication can be also enabled a user to one or more, and/or (such as network interface card is adjusted with any equipment for enabling server apparatus 12a to be communicated with one or more of the other calculating equipment Modulator-demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 22a.Also, server apparatus 12a can also by network adapter 20a and one or more network (such as local area network (LAN), wide area network (WAN) and/or Public network, such as internet) communication.As shown, network adapter 20a passes through its of bus 18a and server apparatus 12a The communication of its module.It should be understood that although not shown in the drawings, other hardware and/or software can be used in conjunction with server apparatus 12a Module, including but not limited to: microcode, device driver, redundant processor, external disk drive array, RAID system, tape Driver and data backup storage system etc..
Processor 16a by the program that is stored in system storage 28a of operation, thereby executing various function application and Data processing, such as realize the information recommendation method of intelligent customer service shown in above-described embodiment.
The present invention also provides a kind of computer-readable mediums, are stored thereon with computer program, which is held by processor The information recommendation method of the intelligent customer service as shown in above-described embodiment is realized when row.
The computer-readable medium of the present embodiment may include in the system storage 28a in above-mentioned embodiment illustrated in fig. 5 RAM30a, and/or cache memory 32a, and/or storage system 34a.
With the development of science and technology, the route of transmission of computer program is no longer limited by tangible medium, it can also be directly from net Network downloading, or obtained using other modes.Therefore, the computer-readable medium in the present embodiment not only may include tangible Medium can also include invisible medium.
The computer-readable medium of the present embodiment can be using any combination of one or more computer-readable media. Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer-readable storage medium Matter for example may be-but not limited to-system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or Any above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes: with one Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or Person is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be Any computer-readable medium other than computer readable storage medium, which can send, propagate or Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++, Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.? Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service It is connected for quotient by internet).
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit It divides, only a kind of logical function partition, there may be another division manner in actual implementation.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the present invention The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read- Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various It can store the medium of program code.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.

Claims (16)

1. a kind of information recommendation method of intelligent customer service, which is characterized in that the described method includes:
When detecting that user enters intelligent customer service, the characteristic parameter that the user enters the intelligent customer service is obtained；
Obtain the service condition of the user；
Enter the characteristic parameter of the intelligent customer service and the service condition of the user according to the user, is obtained from knowledge base Corresponding N number of target problem；The N is positive integer；
Recommend N number of target problem to the user.
2. the method according to claim 1, wherein after recommending N number of target problem to the user, institute State method further include:
If the first object problem in N number of problem is selected by the user, it is corresponding to obtain the first object problem Answer:
To the corresponding answer of first object problem described in the user feedback.
3. being specifically included the method according to claim 1, wherein obtaining the service condition of the user:
Obtain the mark of the user；
According to the mark of the user, the service condition of the user is obtained from user information database.
4. the method according to claim 1, wherein being joined according to the feature that the user enters the intelligent customer service Several and the user service condition, corresponding N number of target problem is obtained from knowledge base, is specifically included:
Enter the characteristic parameter of the intelligent customer service and the service condition of the user according to the user, from the knowledge base Obtain corresponding multiple alternative questions；
Alternative question described in the consulting highest top n of the frequency is obtained from the multiple alternative question, as corresponding described N number of Target problem.
5. according to the method described in claim 4, it is characterized in that, the feature for obtaining the user into the intelligent customer service is joined Number, specifically includes:
Obtain the entry position that the user enters the intelligent customer service；
Accordingly, the characteristic parameter of the intelligent customer service and the service condition of the user are entered according to the user, from described Corresponding multiple alternative questions are obtained in knowledge base, are specifically included:
The entry position for entering the intelligent customer service according to the user, gets corresponding multiple first from the knowledge base Node；
According to the service condition of user described in the service condition of the user and the information table pre-established and the knowledge The corresponding relationship between node in library obtains at least one corresponding second node from the multiple first node；
From the second node each in the knowledge base, corresponding the multiple alternative question is obtained.
6. according to the method described in claim 5, it is characterized in that, the user enters the characteristic parameter of the intelligent customer service also Including seeking advice from the time；Accordingly, the characteristic parameter that the user enters the intelligent customer service is obtained, is specifically included:
Obtain entry position and the consulting time of the user into the intelligent customer service；
Accordingly, the user enters the characteristic parameter of the intelligent customer service and the service condition of the user, from the knowledge Corresponding multiple alternative questions are obtained in library, are specifically included:
The entry position for entering the intelligent customer service according to the user, gets corresponding the multiple from the knowledge base First node；
According to the service condition of user described in the service condition of the user and the information table pre-established and the knowledge The corresponding relationship between node in library obtains at least one corresponding described second node from the multiple first node；
According to the corresponding relationship of the consulting peak period in the information table and the node in the knowledge base, each described second is obtained The corresponding consulting peak period of node；
According to the consulting time, the consulting that the consulting time hit is obtained from least one described second node is high At least one third node of peak phase；
From the third node each in the knowledge base, corresponding the multiple alternative question is obtained.
7. according to method described in claim 5 or 6, which is characterized in that enter the intelligent customer service according to the user The service condition of characteristic parameter and the user, before obtaining corresponding N number of target problem in knowledge base, the method is also wrapped It includes:
The hierarchical relationship of the problems in the classification of the product serviced according to the intelligent customer service and every kind of product classification, Create the knowledge base of tree；
According to the history consultation information of the intelligent customer service, excavates all problems of each node in the knowledge base, each described asks Inscribe the consulting frequency of corresponding answer and each described problem；
Each described problem, the corresponding answer and the corresponding consulting frequency are stored in corresponding in the knowledge base On node；
According to the history consultation information of the intelligent customer service, each described problem for excavating each node in the consulting knowledge base is corresponding User service condition and enter the entry position of the intelligent customer service and with the described problem for concentrating consulting characteristic Seek advice from peak period；
The corresponding entry position into the intelligent customer service is mounted on each node in the knowledge base；
According to the service condition of the corresponding user of each described problem of each node in the knowledge base of excavation, the user is obtained Service condition and the knowledge base in the node between corresponding relationship, and be stored in the information table；
According to the consulting peak period with the described problem for concentrating consulting characteristic of excavation, obtaining has the institute for concentrating consulting characteristic The consulting peak period of problem and the corresponding relationship of the node in the knowledge base are stated, and is stored in the information table.
8. a kind of server of intelligent customer service, which is characterized in that the server includes:
Characteristic parameter obtains module, when for detecting that user enters intelligent customer service, obtaining the user and entering the intelligence visitor The characteristic parameter of clothes；
Service condition obtains module, for obtaining the service condition of the user；
Problem obtains module, for entering the characteristic parameter of the intelligent customer service and the business shape of the user according to the user State obtains corresponding N number of target problem from knowledge base；The N is positive integer；
Recommending module, for recommending N number of target problem to the user.
9. server according to claim 8, which is characterized in that the server further include:
Answer obtains module, if the first object problem in N number of problem select by the user, acquisition described the The corresponding answer of one target problem:
The recommending module is also used to the corresponding answer of first object problem described in the user feedback.
10. server according to claim 8, which is characterized in that the service condition obtains module, is specifically used for:
When detecting that user enters intelligent customer service, the mark of the user is obtained；
According to the mark of the user, the service condition of the user is obtained from user information database.
11. server according to claim 8, which is characterized in that described problem obtains module, is specifically used for:
Enter the characteristic parameter of the intelligent customer service and the service condition of the user according to the user, from the knowledge base Obtain corresponding multiple alternative questions；
Alternative question described in the consulting highest top n of the frequency is obtained from the multiple alternative question, as corresponding described N number of Target problem.
12. server according to claim 11, which is characterized in that the characteristic parameter obtains module, specifically for obtaining The user is taken to enter the entry position of the intelligent customer service；
Accordingly, described problem obtains module, is specifically used for:
The entry position for entering the intelligent customer service according to the user, gets corresponding multiple first from the knowledge base Node；
According to the service condition of user described in the service condition of the user and the information table pre-established and the knowledge The corresponding relationship between node in library obtains at least one corresponding second node from the multiple first node；
From the second node each in the knowledge base, corresponding the multiple alternative question is obtained.
13. server according to claim 12, which is characterized in that the characteristic parameter obtains module, specifically for obtaining Take entry position and the consulting time of the user into the intelligent customer service；
Accordingly, described problem obtains module, is specifically used for:
The entry position for entering the intelligent customer service according to the user, gets corresponding the multiple from the knowledge base First node；
According to the service condition of user described in the service condition of the user and the information table pre-established and the knowledge The corresponding relationship between node in library obtains at least one corresponding described second node from the multiple first node；
According to the corresponding relationship of the consulting peak period in the information table and the node in the knowledge base, each described second is obtained The corresponding consulting peak period of node；
According to the consulting time, the consulting that the consulting time hit is obtained from least one described second node is high At least one third node of peak phase；
From the third node each in the knowledge base, corresponding the multiple alternative question is obtained.
14. server according to claim 12 or 13, which is characterized in that the server further include:
Creation module, the problems in the classification of the product for being serviced according to the intelligent customer service and every kind of product class Other hierarchical relationship creates the knowledge base of tree；
Module is excavated, for the history consultation information according to the intelligent customer service, excavates all of each node in the knowledge base The consulting frequency of problem, the corresponding answer of each described problem and each described problem；
Memory module, it is described for each described problem, the corresponding answer and the corresponding consulting frequency to be stored in In knowledge base on corresponding node；
The excavation module is also used to the history consultation information according to the intelligent customer service, excavates and seeks advice from the knowledge base respectively The service condition of the corresponding user of each described problem of node and enters the entry position of the intelligent customer service and have and concentrate Seek advice from the consulting peak period of the described problem of characteristic；
The memory module is also used to mount on each node in the knowledge base corresponding into the intelligent customer service Entry position；
The memory module is also used to the industry of the corresponding user of each described problem of each node in the knowledge base according to excavation Business state obtains the corresponding relationship between the node in the service condition and the knowledge base of the user, and is stored in In the information table；
The memory module is also used to the consulting peak period with the described problem for concentrating consulting characteristic according to excavation, obtains The corresponding relationship of the node in consulting peak period and the knowledge base with the described problem for concentrating consulting characteristic, and deposit Storage is in the information table.
15. a kind of server apparatus, which is characterized in that the equipment includes:
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real The now method as described in any in claim 1-7.
16. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that the program is executed by processor Method of the Shi Shixian as described in any in claim 1-7.
CN201710610706.3A 2017-07-25 2017-07-25 Information recommendation method, server and computer readable medium for intelligent customer service Active CN110019693B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710610706.3A CN110019693B (en) 2017-07-25 2017-07-25 Information recommendation method, server and computer readable medium for intelligent customer service

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710610706.3A CN110019693B (en) 2017-07-25 2017-07-25 Information recommendation method, server and computer readable medium for intelligent customer service

Publications (2)

Publication Number Publication Date
CN110019693A true CN110019693A (en) 2019-07-16
CN110019693B CN110019693B (en) 2021-12-24

Family

ID=67185840

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710610706.3A Active CN110019693B (en) 2017-07-25 2017-07-25 Information recommendation method, server and computer readable medium for intelligent customer service

Country Status (1)

Country Link
CN (1) CN110019693B (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110569346A (en) * 2019-09-10 2019-12-13 北京创鑫旅程网络技术有限公司 automatic service processing method, device, equipment and storage medium
CN110609890A (en) * 2019-09-11 2019-12-24 浙江大搜车软件技术有限公司 Self-service customer service interaction method and device, computer equipment and storage medium
CN110929027A (en) * 2019-09-30 2020-03-27 珠海格力电器股份有限公司 Prompting system, prompting method, computer and waste accommodating device
US20200320405A1 (en) * 2017-11-29 2020-10-08 Iryou Jyouhou Gijyutu Kenkyusho Corporation Knowledge management system
CN112015892A (en) * 2020-07-24 2020-12-01 上海淇玥信息技术有限公司 Resource allocation method and device and electronic equipment
CN113297516A (en) * 2021-04-27 2021-08-24 上海淇玥信息技术有限公司 Customer interaction interface generation method and device and electronic equipment
CN113392324A (en) * 2021-06-17 2021-09-14 北京京东振世信息技术有限公司 Information pushing method, device, equipment and storage medium
CN113570381A (en) * 2021-06-18 2021-10-29 五八有限公司 Information recommendation method, system, electronic device and storage medium
CN114586323A (en) * 2019-10-28 2022-06-03 利维帕尔森有限公司 Dynamic routing of communications to different end nodes

Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040230601A1 (en) * 2002-09-09 2004-11-18 Joao Raymond A. Apparatus and method for facilitating shipping commerce
US20070038532A1 (en) * 2005-08-11 2007-02-15 Caterpillar Inc. Method and system for integrated service delivery
CN101076060A (en) * 2007-03-30 2007-11-21 腾讯科技（深圳）有限公司 Chatting robot system and automatic chatting method
CN101340552A (en) * 2008-08-11 2009-01-07 中国网络通信集团公司 Synthetic service navigation system
CN103516908A (en) * 2013-10-09 2014-01-15 北京奇虎科技有限公司 Method and device assisting replying communication message
CN104022940A (en) * 2014-04-16 2014-09-03 华为技术有限公司 Information processing method, device and system based on instant messaging (IM)
CN104809197A (en) * 2015-04-24 2015-07-29 同程网络科技股份有限公司 On-line question and answer method based on intelligent robot
CN105512153A (en) * 2014-10-20 2016-04-20 中国电信股份有限公司 Method and device for service provision of online customer service system, and system
CN105590225A (en) * 2015-12-22 2016-05-18 成都小多科技有限公司 Sales stage identification method and device based on client problems
CN106326984A (en) * 2016-08-09 2017-01-11 北京京东尚科信息技术有限公司 User intention identification method and device and automatic answering system
CN106468990A (en) * 2015-08-21 2017-03-01 上海触乐信息科技有限公司 The method and apparatus that service entrance is provided
CN106528613A (en) * 2016-05-26 2017-03-22 中科鼎富（北京）科技发展有限公司 Intelligent question-answer (Q&A) method and device
CN106572001A (en) * 2016-10-31 2017-04-19 厦门快商通科技股份有限公司 Conversation method and system for intelligent customer service
CN106648688A (en) * 2016-12-29 2017-05-10 北京奇虎科技有限公司 Information display method and apparatus
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
CN106897334A (en) * 2016-06-24 2017-06-27 阿里巴巴集团控股有限公司 A kind of question pushing method and equipment
CN106934594A (en) * 2017-02-22 2017-07-07 深圳市金证科技股份有限公司 Business handling method and system on a kind of line
CN106209592B (en) * 2016-07-15 2020-02-07 福建星网信通软件有限公司 WeChat customer service system and customer service message interaction method thereof

Patent Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040230601A1 (en) * 2002-09-09 2004-11-18 Joao Raymond A. Apparatus and method for facilitating shipping commerce
US20070038532A1 (en) * 2005-08-11 2007-02-15 Caterpillar Inc. Method and system for integrated service delivery
CN101076060A (en) * 2007-03-30 2007-11-21 腾讯科技（深圳）有限公司 Chatting robot system and automatic chatting method
CN101340552A (en) * 2008-08-11 2009-01-07 中国网络通信集团公司 Synthetic service navigation system
CN103516908A (en) * 2013-10-09 2014-01-15 北京奇虎科技有限公司 Method and device assisting replying communication message
CN104022940A (en) * 2014-04-16 2014-09-03 华为技术有限公司 Information processing method, device and system based on instant messaging (IM)
CN105512153A (en) * 2014-10-20 2016-04-20 中国电信股份有限公司 Method and device for service provision of online customer service system, and system
CN104809197A (en) * 2015-04-24 2015-07-29 同程网络科技股份有限公司 On-line question and answer method based on intelligent robot
CN106468990A (en) * 2015-08-21 2017-03-01 上海触乐信息科技有限公司 The method and apparatus that service entrance is provided
CN105590225A (en) * 2015-12-22 2016-05-18 成都小多科技有限公司 Sales stage identification method and device based on client problems
CN106528613A (en) * 2016-05-26 2017-03-22 中科鼎富（北京）科技发展有限公司 Intelligent question-answer (Q&A) method and device
CN106897334A (en) * 2016-06-24 2017-06-27 阿里巴巴集团控股有限公司 A kind of question pushing method and equipment
CN106209592B (en) * 2016-07-15 2020-02-07 福建星网信通软件有限公司 WeChat customer service system and customer service message interaction method thereof
CN106326984A (en) * 2016-08-09 2017-01-11 北京京东尚科信息技术有限公司 User intention identification method and device and automatic answering system
CN106572001A (en) * 2016-10-31 2017-04-19 厦门快商通科技股份有限公司 Conversation method and system for intelligent customer service
CN106648688A (en) * 2016-12-29 2017-05-10 北京奇虎科技有限公司 Information display method and apparatus
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
CN106934594A (en) * 2017-02-22 2017-07-07 深圳市金证科技股份有限公司 Business handling method and system on a kind of line

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MENG MAGGIE QIU 等: "Systematic Analysis of Public Cloud Service Level Agreements and Related Business Values", 《2013 IEEE INTERNATIONAL CONFERENCE ON SERVICES COMPUTING》 *
邹知宇: "基于公众消息平台的客服***的研究与实现", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 *

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11605005B2 (en) * 2017-11-29 2023-03-14 Iryou Jyouhou Gijyutu Kenkyusho Corporation Knowledge management system
US20200320405A1 (en) * 2017-11-29 2020-10-08 Iryou Jyouhou Gijyutu Kenkyusho Corporation Knowledge management system
CN110569346A (en) * 2019-09-10 2019-12-13 北京创鑫旅程网络技术有限公司 automatic service processing method, device, equipment and storage medium
CN110609890A (en) * 2019-09-11 2019-12-24 浙江大搜车软件技术有限公司 Self-service customer service interaction method and device, computer equipment and storage medium
CN110929027B (en) * 2019-09-30 2022-08-12 珠海格力电器股份有限公司 Prompting system, prompting method, computer and waste accommodating device
CN110929027A (en) * 2019-09-30 2020-03-27 珠海格力电器股份有限公司 Prompting system, prompting method, computer and waste accommodating device
CN114586323A (en) * 2019-10-28 2022-06-03 利维帕尔森有限公司 Dynamic routing of communications to different end nodes
CN114586323B (en) * 2019-10-28 2024-05-17 利维帕尔森有限公司 Dynamic communication routing to different endpoints
CN112015892A (en) * 2020-07-24 2020-12-01 上海淇玥信息技术有限公司 Resource allocation method and device and electronic equipment
CN113297516A (en) * 2021-04-27 2021-08-24 上海淇玥信息技术有限公司 Customer interaction interface generation method and device and electronic equipment
CN113392324A (en) * 2021-06-17 2021-09-14 北京京东振世信息技术有限公司 Information pushing method, device, equipment and storage medium
CN113392324B (en) * 2021-06-17 2023-11-10 北京京东振世信息技术有限公司 Information pushing method, device, equipment and storage medium
CN113570381A (en) * 2021-06-18 2021-10-29 五八有限公司 Information recommendation method, system, electronic device and storage medium

Also Published As

Publication number Publication date
CN110019693B (en) 2021-12-24

Similar Documents

Publication Publication Date Title
CN110019693A (en) Information recommendation method, server and the computer-readable medium of intelligent customer service
Chan et al. Mediating effects on the relationship between perceived service quality and public library app loyalty during the COVID-19 era
Hew et al. Predicting drivers of mobile entertainment adoption: a two-stage SEM-artificial-neural-network analysis
US10635952B2 (en) Cognitive analysis and classification of apparel images
US8452676B1 (en) Method and system for filing a tax form using quick return
KR101742820B1 (en) Digital marketing optimization
Gerhart et al. Social network migration and anonymity expectations: What anonymous social network apps offer
CN104115143B (en) Multiple tabss stack user interface
US11017430B2 (en) Delivering advertisements based on user sentiment and learned behavior
CN105229485A (en) Multifactor location verification
CN108830682A (en) Online house prosperity transaction data processing method, device, terminal and storage medium
CN108984658A (en) A kind of intelligent answer data processing method and device
CN109377253A (en) Advertisement placement method, device, terminal and storage medium
CN109800291A (en) Question response method and device, electronic equipment and storage medium
CN109388548A (en) Method and apparatus for generating information
US20170337601A1 (en) Monetization of interactive network-based information objects
CN107220236A (en) It is a kind of to determine the doubtful naked method and device for borrowing student
US9754289B2 (en) Systems and methods for providing recommendations to residential relocators
CN116757786A (en) Business handling method based on meta universe, financial service platform and electronic equipment
Hai-Jew Online Survey Design and Data Analytics: Emerging Research and Opportunities: Emerging Research and Opportunities
JP7288062B2 (en) Methods and devices for outputting information, electronic devices, storage media, and computer programs
Maturo et al. Analysing research impact via functional data analysis: a powerful tool for scholars, insiders, and research organizations
CN109829593A (en) The credit rating of target object determines method, apparatus, storage medium and electronic device
US20210322877A1 (en) A system and method for providing one or more services using an augmented reality display
US20190266540A1 (en) Method and system for tracking health statistics

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
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20190716

Assignee: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd.

Assignor: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd.

Contract record no.: X2019110000005

Denomination of invention: Information recommendation method of intelligent customer service, server and computer readable medium

License type: Common License

Record date: 20191119

EE01 Entry into force of recordation of patent licensing contract
GR01 Patent grant
GR01 Patent grant