CN110019693B - Information recommendation method, server and computer readable medium for intelligent customer service - Google Patents
Information recommendation method, server and computer readable medium for intelligent customer service Download PDFInfo
- Publication number
- CN110019693B CN110019693B CN201710610706.3A CN201710610706A CN110019693B CN 110019693 B CN110019693 B CN 110019693B CN 201710610706 A CN201710610706 A CN 201710610706A CN 110019693 B CN110019693 B CN 110019693B
- Authority
- CN
- China
- Prior art keywords
- user
- customer service
- consultation
- acquiring
- 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.)
- Active
Links
Images
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 invention provides an information recommendation method, a server and a computer readable medium for intelligent customer service. The method comprises the following steps: when detecting that a user enters intelligent customer service, acquiring characteristic parameters of the user entering the intelligent customer service; acquiring a service state of a user; acquiring corresponding N target problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user; recommending N target questions to the user. Compared with the problem prediction method based on the access behavior track of the user in the prior art, the technical scheme of the invention can more accurately predict the problem that the user wants to consult according to the service state of the user and the characteristic parameters of entering the intelligent customer service by obtaining the N target problems, thereby effectively improving the accuracy of predicting the problem. Moreover, the accuracy of the prediction problem is effectively improved, so that the operation cost of the user can be effectively reduced, and the use experience of the user can be effectively improved.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of computer application, in particular to an intelligent customer service information recommendation method, a server and a computer readable medium.
[ background of the invention ]
In order to provide services to users more conveniently, many websites and Application (App) clients of websites and the like provide services for users with online customer services. The user can consult the problem through the online customer service, and the use is very convenient.
In the prior art, a server side of an online customer service can be monitored by a manual customer service, and after receiving a problem sent by a user through the online customer service, the manual customer service answers the problem in an online mode. However, as the use of the network is popularized, more and more users can perform problem consultation by selecting online customer service, which causes that the working pressure of manual customer service is higher, and the increased online problem consultation cannot be satisfied, and then, an online intelligent customer service gradually appears. When the user enters the intelligent customer service, the intelligent customer service acquires the access behavior track of the user to the website or the application page before the user enters the intelligent customer service, predicts one or more problems possibly encountered by the user in the access process according to the access behavior track of the user, and sends the problems to the user. If the user really wants to consult one of the questions when entering the intelligent customer service, the user can click the question and the intelligent customer service returns the answer to the question to finish the on-line consultation of the user, the on-line consultation process is very intelligent, and the user can use the intelligent customer service very conveniently.
However, in the prior art, the visiting behavior track of the website or the application page before the user enters the intelligent customer service may only be an expression and already deviates from the problem to be consulted, for example, the visiting of the website or the application page before the user enters the intelligent customer service may be that the user wants to try to solve the problem by himself, and if the user problem is predicted according to the visiting behavior track of the user, the user problem deviates from the real problem of the user. Therefore, in the prior art, the problem to be consulted by the user is predicted according to the access behavior track of the user to the website or the application page before the user enters the intelligent customer service, so that the accuracy of predicting the problem is low.
[ summary of the invention ]
The invention provides an information recommendation method, a server and a computer readable medium for intelligent customer service, which are used for improving the accuracy of problem prediction.
The invention provides an information recommendation method for intelligent customer service, which comprises the following steps:
when detecting that a user enters intelligent customer service, acquiring characteristic parameters of the user entering the intelligent customer service;
acquiring the service state of the user;
acquiring N corresponding target problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user; n is a positive integer;
recommending the N target questions to the user.
Further optionally, in the method described above, after recommending the N target questions to the user, the method further includes:
if a first target question of the N questions is selected by the user, acquiring an answer corresponding to the first target question:
and feeding back an answer corresponding to the first target question to the user.
Further optionally, in the method, acquiring the service state of the user specifically includes:
acquiring the identification of the user;
and acquiring the service state of the user from a user information base according to the user identification.
Further optionally, in the method, obtaining the corresponding N target questions from a knowledge base according to the feature parameter of the user entering the intelligent customer service and the service state of the user specifically includes:
acquiring a plurality of corresponding alternative problems from the knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user;
and acquiring the first N candidate problems with the highest consultation frequency from the plurality of candidate problems as the corresponding N target problems.
Further optionally, in the method, obtaining the characteristic parameter of the user entering the intelligent customer service specifically includes:
acquiring the entrance position of the user entering the intelligent customer service;
correspondingly, according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user, obtaining a plurality of corresponding alternative problems from the knowledge base, specifically comprising:
acquiring a plurality of corresponding first nodes from the knowledge base according to the entrance position of the user entering the intelligent customer service;
acquiring at least one corresponding second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user and the nodes in the knowledge base in a pre-established information table;
and acquiring the plurality of corresponding candidate problems from each second node in the knowledge base.
Further optionally, in the method as described above, the characteristic parameter of the user entering the intelligent customer service further includes a consultation time; correspondingly, acquiring the characteristic parameters of the user entering the intelligent customer service specifically comprises the following steps:
acquiring the entrance position of the user entering the intelligent customer service and the consultation time;
correspondingly, the step of enabling the user to enter the characteristic parameters of the intelligent customer service and the service state of the user and acquiring a plurality of corresponding alternative problems from the knowledge base specifically comprises the following steps:
acquiring the corresponding first nodes from the knowledge base according to the entrance position of the user entering the intelligent customer service;
acquiring the corresponding at least one second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user and the nodes in the knowledge base in a pre-established information table;
acquiring the consultation peak periods corresponding to the second nodes according to the corresponding relation between the consultation peak periods in the information table and the nodes in the knowledge base;
acquiring at least one third node of the consultation peak period hit by the consultation time from the at least one second node according to the consultation time;
and acquiring the plurality of corresponding candidate problems from each third node in the knowledge base.
Further optionally, in the method described above, before acquiring, according to the feature parameter of the user entering the intelligent customer service and the service state of the user, the N corresponding target problems from the knowledge base, the method further includes:
creating the knowledge base with a tree structure according to the categories of products served by the intelligent customer service and the hierarchical relation of the problem categories in each product;
mining all the problems of each node in the knowledge base, answers corresponding to the problems and consultation frequency of the problems according to historical consultation information of the intelligent customer service;
storing each question, the corresponding answer and the corresponding consultation frequency on a corresponding node in the knowledge base;
according to the historical consultation information of the intelligent customer service, the business state of a user corresponding to each problem of each node in the knowledge base is mined and consulted, the entrance position of the user entering the intelligent customer service is accessed, and the consultation peak period of the problems with centralized consultation characteristics is obtained;
hanging corresponding entrance positions for entering the intelligent customer service on each node in the knowledge base;
acquiring a corresponding relation between the service state of the user and the nodes in the knowledge base according to the service state of the user corresponding to each problem of each node in the knowledge base, and storing the corresponding relation in the information table;
and acquiring the corresponding relation between the consultation peak period of the problem with the centralized consultation characteristic and the nodes in the knowledge base according to the mined consultation peak period of the problem with the centralized consultation characteristic, and storing the corresponding relation in the information table.
The invention provides a server of intelligent customer service, comprising:
the system comprises a characteristic parameter acquisition module, a service management module and a service management module, wherein the characteristic parameter acquisition module is used for acquiring a characteristic parameter of a user entering the intelligent customer service when detecting that the user enters the intelligent customer service;
a service state obtaining module, configured to obtain a service state of the user;
the problem acquisition module is used for acquiring corresponding N target problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user; n is a positive integer;
and the recommending module is used for recommending the N target problems to the user.
Further optionally, in the server described above, the server further includes:
an answer obtaining module, configured to, if a first target question of the N questions is selected by the user, obtain an answer corresponding to the first target question:
the recommending module is further configured to feed back an answer corresponding to the first target question to the user.
Further optionally, in the server described above, the service status obtaining module is specifically configured to:
acquiring the identification of the user;
and acquiring the service state of the user from a user information base according to the user identification.
Further optionally, in the server described above, the problem obtaining module is specifically configured to:
acquiring a plurality of corresponding alternative problems from the knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user;
and acquiring the first N candidate problems with the highest consultation frequency from the plurality of candidate problems as the corresponding N target problems.
Further optionally, in the server described above, the characteristic parameter obtaining module is specifically configured to obtain an entry position where the user enters the intelligent customer service;
correspondingly, the problem acquisition module is specifically configured to:
acquiring a plurality of corresponding first nodes from the knowledge base according to the entrance position of the user entering the intelligent customer service;
acquiring at least one corresponding second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user and the nodes in the knowledge base in a pre-established information table;
and acquiring the plurality of corresponding candidate problems from each second node in the knowledge base.
Further optionally, in the server described above, the characteristic parameter obtaining module is specifically configured to obtain an entry position where the user enters the intelligent customer service and the consultation time;
correspondingly, the problem acquisition module is specifically configured to:
acquiring the corresponding first nodes from the knowledge base according to the entrance position of the user entering the intelligent customer service;
acquiring the corresponding at least one second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user and the nodes in the knowledge base in a pre-established information table;
acquiring the consultation peak periods corresponding to the second nodes according to the corresponding relation between the consultation peak periods in the information table and the nodes in the knowledge base;
acquiring at least one third node of the consultation peak period hit by the consultation time from the at least one second node according to the consultation time;
and acquiring the plurality of corresponding candidate problems from each third node in the knowledge base.
Further optionally, in the server described above, the server further includes:
the creation module is used for creating the knowledge base with a tree structure according to the categories of the products served by the intelligent customer service and the hierarchical relationship of the problem categories in each product;
the mining module is used for mining all the problems of all the nodes in the knowledge base, answers corresponding to the problems and consultation frequency of the problems according to historical consultation information of the intelligent customer service;
the storage module is used for storing each question, the corresponding answer and the corresponding consultation frequency on the corresponding node in the knowledge base;
the mining module is further used for mining the service state of the user corresponding to each problem of each node in the knowledge base, the entrance position of the user entering the intelligent customer service and the consultation peak period of the problems with centralized consultation characteristics according to the historical consultation information of the intelligent customer service;
the storage module is further used for hooking corresponding entrance positions for entering the intelligent customer service to the nodes in the knowledge base;
the storage module is further configured to obtain a correspondence between the service state of the user and the node in the knowledge base according to the service state of the user corresponding to each problem of each node in the mined knowledge base, and store the correspondence in the information table;
the storage module is further configured to obtain a correspondence between the consultation peak periods of the problems with the centralized consultation characteristics and the nodes in the knowledge base according to the mined consultation peak periods of the problems with the centralized consultation characteristics, and store the correspondence in the information table.
The present invention also provides a server apparatus, the apparatus comprising:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the intelligent customer service information recommendation method as described above.
The present invention also provides a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements the intelligent customer service information recommendation method as described above.
According to the information recommendation method, the server and the computer readable medium for the intelligent customer service, when the situation that the user enters the intelligent customer service is detected, the characteristic parameters of the user entering the intelligent customer service are obtained; acquiring a service state of a user; acquiring corresponding N target problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user; recommending N target questions to the user. Compared with the problem prediction method based on the access behavior track of the user in the prior art, the technical scheme of the invention can more accurately predict the problem that the user wants to consult according to the service state of the user and the characteristic parameters of entering the intelligent customer service by obtaining the N target problems, thereby effectively improving the accuracy of predicting the problem. Moreover, the accuracy of the prediction problem is effectively improved, so that the operation cost of the user can be effectively reduced, and the use experience of the user can be effectively improved.
[ description of the drawings ]
Fig. 1 is a flowchart of a first embodiment of an information recommendation method for intelligent customer service according to the present invention.
Fig. 2 is a block diagram of a first embodiment of a server for intelligent customer service according to the present invention.
Fig. 3 is a block diagram of a second embodiment of the server for intelligent customer service according to the present invention.
Fig. 4 is a block diagram of an embodiment of a server apparatus of the present invention.
Fig. 5 is an exemplary diagram of a server device provided by the present invention.
[ detailed description ] embodiments
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a flowchart of a first embodiment of an information recommendation method for intelligent customer service according to the present invention. As shown in fig. 1, the information recommendation method for intelligent customer service in this embodiment may specifically include the following steps:
100. when detecting that a user enters intelligent customer service, acquiring characteristic parameters of the user entering the intelligent customer service;
the execution main body of the information recommendation method for intelligent customer service in the embodiment is a server for intelligent customer service. The server of the intelligent customer service can be communicated with a website or App client or other platforms of a served network company to provide services for online customer services coming from various entrances of the network company.
In this embodiment, the user has certain characteristics when entering the intelligent customer service, for example, the user may provide an online customer service entrance on a webpage of a website to enter the intelligent customer service, may also enter the intelligent customer service through an online customer service entrance in an APP of the website, or may also enter the intelligent customer service through an online customer service entrance of another service platform provided by the website. For example, if a financial website issues a plurality of financial products and insurance products, the introduction page of each product is linked with the entrance of the intelligent customer service. Similarly, in App, the introduction page of each product is linked with a portal of intelligent customer service. Therefore, optionally, in this embodiment, the feature parameter entering the intelligent customer service may include an entry location of the intelligent customer service, and in general, what kind of problem the user wants to consult will usually enter the intelligent customer service on a page of a product that has a related problem, so that the entry location entering the intelligent customer service can predict the direction of the problem the user wants to consult more accurately. No matter which way the user enters the intelligent customer service, when the server of the intelligent customer service detects that the user enters the intelligent customer service, characteristic parameters, such as an entrance position, of the user entering the intelligent customer service can be obtained.
101. Acquiring a service state of a user;
the service state of the user in this embodiment may be each stage in the service used by the user. For example, the business status of purchasing a service may include an unpurchased status, a post-purchase inactivated status, an activated status, and the like. As another example, the business status of a loan application may include an unapplied status, a pending status after application, an approval through pending payment status, a repayment status, a loan release status, and the like. In a similar manner, for each service, the status of the service may be determined based on the characteristics of the service.
For example, the step 101 may specifically include: acquiring an identifier of a user; and acquiring the service state of the user from the user information base according to the identification of the user.
In this embodiment, the user consulting the intelligent customer service may be a login user, and the identifier of the user may be an account of the user. In the server of the intelligent customer service, a user information base may be stored, in which information of all users served by the website is stored, and may include, for example, an account number of the user, a contact address, a service identifier transacted by the user, and a service status of each service. For example, for a certain loan application website, a user may apply for a loan through an App or a website, and in a user information base stored in a server of an intelligent customer service of the website, information of each user applying for the loan, such as an account number, a name, a contact address, and the like of the user may be recorded, and a service state of the user may be stored, such as an application stage, an approval stage, a repayment stage, and the like. For different services, the service states corresponding to different users are not described in detail herein. In addition, if the user applies for a plurality of services at the same time on a certain website, correspondingly, the service state of each service applied by the user can be acquired from the user information base of the intelligent customer service according to the identification of the user.
When it needs to be described, for the identifier of a certain user, if the user information base does not store the information of the user yet, it indicates that the user has not performed any related service, and the service state at this time may be identified as 0, that is, there is no service progress.
Optionally, in this embodiment, for a user who enters the smart customer service in the guest identity, that is, an unregistered user or a user who does not register an account, the identifier of the service state of the corresponding user may be 0, that is, there is no service progress.
102. Acquiring corresponding N target problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user;
103. recommending N target questions to the user.
In this embodiment, when the corresponding N target problems are obtained from the knowledge base according to the feature parameter of the user entering the intelligent customer service and the service state of the user, the feature parameter of the user entering the intelligent customer service and the service state of the user are two conditions for obtaining the N target problems. That is, the two conditions need to be satisfied simultaneously for the acquired N target problems. When the N problems are obtained, the two conditions can be firstly screened to meet the characteristic parameters of entering the intelligent customer service, and can also be firstly screened to meet the service state of the user. If the characteristic parameter entering the intelligent customer service is the entrance position entering the intelligent customer service, the two conditions are used for preferentially screening alternative problems meeting the entrance position condition entering the intelligent customer service, then the problem meeting the service state condition of the user is screened from the obtained alternative problems, and finally N target problems are obtained.
Optionally, in step 102 "obtaining N corresponding target questions from the knowledge base according to the feature parameters of the user entering the intelligent customer service and the service state of the user" in this embodiment may specifically include: acquiring a plurality of corresponding alternative problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user; and acquiring the first N candidate problems with the highest consultation frequency from the plurality of candidate problems as the corresponding N target problems. That is, if a plurality of candidate questions are directly used as target questions, the number of candidate questions may be large, which may result in less prominent key questions, and in this embodiment, the top N historical consultation frequencies may be obtained from the plurality of candidate questions as target questions.
If the number of candidate questions is less than N or equal to N, all the candidate questions are set as target questions. If the characteristic parameter of the user entering the intelligent customer service is the entrance position of the user entering the intelligent customer service, and the corresponding multiple alternative problems are obtained from the knowledge base according to the characteristic parameter of the user entering the intelligent customer service and the service state of the user, preferably, the corresponding multiple problems are obtained from the knowledge base according to the entrance position of the user entering the intelligent customer service, and then the corresponding multiple alternative problems are obtained from the multiple problems according to the service state of the user. Finally, the first N candidate problems with the highest consultation frequency are obtained from the plurality of candidate problems,
the knowledge base of this embodiment may be created in advance based on all products included in the web site serviced by the smart customer service and various categories of questions under each product. For example, for an educational installment, there may be questions such as "credit application", "credit activation", "loan advice", "payment issue", and "refund advice" that are under the product. Wherein, the problems of how to pay, the amount of paid money, overdue payment, advance payment and the like can also be found below the payment problem. The problems of APP payment, password-free payment, automatic payment and the like exist below the 'how to pay'. Thus, the education staging can be used as a primary father node, and the 'quota application', 'quota activation', 'paying consultation', 'repayment problem' and 'chargeback consultation' are divided into child nodes which are used as father nodes and are used as education staging; furthermore, "how to pay", "amount of payment", "overdue payment" and "advance payment" can also be used as child nodes of the "payment problem"; the APP payment, the password-free payment and the automatic payment can also be used as child nodes of 'how to pay'. According to the parent-child relationship of the nodes of each problem, a corresponding knowledge base of the tree structure can be created. According to the structure of the knowledge base, a similar knowledge base with a tree structure can be created at each website.
Wherein in the lowest nodes of the tree structure of the knowledge base, such as 'how to repay', 'repayment amount', 'overdue repayment', 'advance repayment', 'APP repayment', 'secret-free repayment' and 'automatic repayment', one or more knowledge points can be stored in each lowest node correspondingly, each knowledge point comprises a question and a corresponding answer under the corresponding node, and the attribute information corresponding to each knowledge point can comprise the consultation frequency of the knowledge point. And in the knowledge base, each node can be connected with a plurality of entrance positions for entering the intelligent customer service. Similarly, the problem in the node based on the knowledge base is also in corresponding relation with the service state of the user, so that an information table can be pre-established, the corresponding relation between the service state of the user and the node in the knowledge base is stored, and the target problem can be conveniently acquired according to the service state of the user in the follow-up process. For the problem with centralized consultation characteristics, the consultation peak period can be counted in advance, and the corresponding relation between the consultation peak period of the problem and the corresponding node of the problem in the knowledge base is recorded in the information table, so that the target problem can be conveniently acquired according to whether the consultation time hits the consultation peak period or not in the follow-up process.
In this embodiment, the user in different business states may consult different questions, for example, regarding the network company providing the service, for the user who does not purchase the service, the business state is 0, and the question consulted by the user may be more biased to how to purchase the service, the service enjoyed after purchase, the fee problem during purchase, the payment problem, and the like. For a user who has purchased a service but is in an inactive business state, the consultation will be more biased to the problems of how to activate, activate the notes, and how to deal with various errors in activation. For users who have purchased services and have activated business states, the problem of consultation is more biased towards the problem of use, the problem of subsequent renewal if use is continued and the problem of refund if use is terminated early, etc. That is, for each traffic state, there are a plurality of problems in the node matched thereto and a plurality of knowledge points in the lower nodes of the node in the knowledge base.
Similarly, for each entry location into the intelligent customer service, there are multiple problems in the knowledge base with its matching node and multiple knowledge points in the node subordinate nodes. Therefore, according to the entrance position of the user entering the intelligent customer service and the service state of the user, N target problems which correspond to the entrance position of the user entering the intelligent customer service and the service state of the user are obtained from the knowledge base. Then, the obtained N target questions can be recommended to the user through an interface for the intelligent customer service to communicate with the user. In this embodiment, according to the entry position where the user enters the intelligent customer service and the service state of the user, the number of N in the N corresponding target questions obtained from the knowledge base may be set according to actual requirements, for example, 3, 5, or 10, or other integer numbers may be selected.
Specifically, when the feature parameter of the user entering the intelligent customer service is the entry position of the user entering the intelligent customer service, the step "the feature parameter of the user entering the intelligent customer service and the service state of the user, and obtaining a plurality of corresponding candidate problems from the knowledge base" in the embodiment may specifically include the following steps:
(a1) acquiring a plurality of corresponding first nodes from a knowledge base according to the entrance position of a user entering the intelligent customer service;
(b1) acquiring at least one corresponding second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user in the pre-established information table and the nodes in the knowledge base;
(c1) and acquiring a plurality of corresponding alternative problems from each second node in the knowledge base.
The above steps (a1) - (c1) enable sequential screening of a plurality of conditions in obtaining a plurality of candidate questions. For example, firstly, screening nodes meeting the entry position condition of a user entering the intelligent customer service, and acquiring a plurality of corresponding first nodes from a knowledge base; and then screening at least one second node corresponding to the service state of the user from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user in the pre-established information table and the nodes in the knowledge base. Each first node and each second node may be intermediate nodes in the knowledge base or lowermost nodes. If the second node is the lowest node in the knowledge base, the second node may include a plurality of knowledge points, and a plurality of problems may be obtained from the plurality of knowledge points as candidate problems. If the second node is an intermediate node of the knowledge base, a plurality of corresponding problems can be obtained from the lowest-layer child node corresponding to the second node in the knowledge base as alternative problems.
Still further optionally, the feature parameter of the user entering the intelligent customer service in this embodiment further includes consultation time; the granularity of the consultation time of the embodiment can be set according to the requirement of the product service. For example, for a loan repayment product with a monthly repayment period, the corresponding referral time may be recorded at a day granularity, with the peak of the referral time correspondingly recorded at a day granularity. If 18 per month is a payment date, 13-18 per month can be set as a payment consultation peak period, and for consultation during the period of consultation, N target problems related to payment related to business state of the push user are preferred.
Specifically, when the characteristic parameter of the user entering the intelligent customer service is the entry position of the user entering the intelligent customer service and the consultation time, the step "the characteristic parameter of the user entering the intelligent customer service and the service state of the user, and a plurality of corresponding candidate problems are obtained from the knowledge base" in the embodiment may specifically include the following steps:
(a2) acquiring a plurality of corresponding first nodes from a knowledge base according to the entrance position of a user entering the intelligent customer service;
(b2) acquiring at least one corresponding second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user in the pre-established information table and the nodes in the knowledge base;
(c2) acquiring consultation peak periods corresponding to the second nodes according to the corresponding relation between the consultation peak periods in the information table and the nodes in the knowledge base;
(d2) at least one third node for acquiring a consultation peak period hit by the consultation time from the at least one second node according to the consultation time;
(e2) and acquiring a plurality of preset problems corresponding to the corresponding consultation peak period from each third node in the knowledge base as a plurality of alternative problems.
The steps (a2) - (e2) of the present embodiment are different from the steps (a1) - (c1) described above in that, when a plurality of candidate questions are acquired in the present embodiment, the consultation time of the screening condition is increased on the basis of the entry position of the screening condition user into the smart customer service and the service state of the user. The priority order of the screening conditions is as follows: the method comprises the steps of firstly screening a plurality of first nodes which meet entrance position conditions of a user entering intelligent customer service, then screening a plurality of second nodes which meet business state conditions of the user from the screened first nodes, and then screening at least one third node which meets consultation time conditions from the obtained second nodes. When at least one third node is screened from the plurality of second nodes according to the consultation time, the consultation peak periods of the second nodes can be obtained firstly, then whether the current consultation time hits the consultation peak periods of some second nodes or not is judged, and if yes, the corresponding second node is screened out to be used as the third node. Otherwise, if not, the second node is discarded. It is understood that the knowledge points stored in the third node or the lowest child node downstream of the third node are all questions and answers corresponding to the consultation peak period. For example, for a consultation with a payment date of No. 18 per month and a consultation peak period of No. 13 to 18 per month, the consultation at the consultation peak period at the consultation time can default to be a consultation about the payment related problem, and a knowledge point of the payment related problem can be stored in a node corresponding to the consultation peak period or the lowest node at the downstream, so that when a third node is screened subsequently, if the consultation time hits the consultation peak period, the node can be screened out, and a plurality of payment related problems can be acquired as alternative problems.
For example, for a monthly loan repayment product, multiple candidate questions related to repayment can be obtained in the above manner, and finally, the top N candidate questions with the highest consultation frequency are obtained from the multiple candidate questions as the corresponding N target questions. Similarly, if the number of the plurality of candidate questions related to the repayment is less than N or equal to N, all the plurality of candidate questions related to the repayment may be regarded as corresponding target questions.
In this embodiment, for the consultation outside the repayment peak period, the corresponding N target problems are obtained from the knowledge base according to the entry position where the user enters the intelligent customer service and the service state of the user, and the detailed implementation process is the same as above and is not described herein again.
The above embodiment records the consultation time with day as granularity, and in practical application, for other products, the granularity of the consultation time may be hours according to the characteristics of the period of the product itself, for example, one period per day. For the insurance-type products that are renewed each year, each year is a period, the granularity of consultation time can be months, and the like, which are not described in detail herein.
Further optionally, in this embodiment, after "recommending N target questions to the user" in step 103, the method may further include: if a first target question of the N target questions is selected by the user, acquiring an answer corresponding to the first target question: and feeding back an answer corresponding to the first target question to the user. Specifically, an answer corresponding to the first target question is obtained from the knowledge base and fed back to the user.
Further optionally, before step 102 "obtaining the corresponding N target questions from the knowledge base according to the feature parameters of the user entering the intelligent customer service and the service state of the user", the following steps may be further included:
(a3) creating a knowledge base with a tree structure according to the category of products served by the intelligent customer service and the hierarchical relationship of the problem category in each product;
(b3) mining all the problems of each node in a knowledge base, answers corresponding to the problems and consultation frequency of the problems according to historical consultation information of the intelligent customer service;
(c3) storing each question, the corresponding answer and the corresponding consultation frequency on the corresponding node in the knowledge base;
each question and the corresponding answer can be stored in the corresponding node as a knowledge point, and the consultation frequency is stored in the attribute of the knowledge point as the attribute information of the knowledge point.
(d3) According to historical consultation information of the intelligent customer service, mining the service state of a user corresponding to each problem of each node in a consultation knowledge base, the entrance position of entering the intelligent customer service and the consultation peak time of the problems with centralized consultation characteristics;
(e3) hanging corresponding entrance positions for entering the intelligent customer service on each node in the knowledge base;
(f3) acquiring a corresponding relation between the service state of the user and the nodes in the knowledge base according to the service state of the user corresponding to each problem of each node in the mined knowledge base, and storing the corresponding relation in an information table;
(g3) and acquiring the corresponding relation between the consultation peak periods of the problems with the centralized consultation characteristics and the nodes in the knowledge base according to the mined consultation peak periods of the problems with the centralized consultation characteristics, and storing the corresponding relation in an information table.
The processes of the above steps (a3) - (g3) are processes of creating a knowledge base and establishing an information table according to the knowledge base, so as to obtain corresponding target problems from the knowledge base according to the screening conditions and combining the knowledge base and the information table established according to the knowledge base. The process in which the tree structure of the knowledge base is created can be explained with reference to the above-described related embodiments. When the knowledge points stored in the lowest node in the knowledge base are generated and stored, historical consultation information of the intelligent customer service needs to be collected, for example, the historical consultation information of the embodiment not only includes questions and answers pushed by the intelligent customer service for the user. Meanwhile, the method also comprises the steps that the user does not solve the problem in the problem and the answer pushed by the intelligent customer service, but the problem input by the user is solved by the worker of the intelligent customer service in a manual mode. Namely, in this embodiment, the server of the intelligent customer service can also collect the questions input by the user and the answers of the manual customer service to answer the questions, so as to enrich the question information of the intelligent customer service. Then the intelligent customer service history consultation information is mined to find all the questions of various types in the intelligent customer service and answers corresponding to the questions. The category of the present embodiment may be a category of the smart customer service, for example, a certain website includes 5 products, each product may correspond to a category, and each category has a corresponding problem that may be consulted. Furthermore, each product comprises various subordinate categories, such as pre-sale (which may correspond to the business state of the unpurchased service), activation, payment and the like, and each subordinate category also has a corresponding problem that the product may be consulted; further, for each subordinate category of pre-sale, activation, payment and repayment, further subordinate categories may be included. By analogy, the category of the product served by the intelligent customer service and all the hierarchical categories in each product can be obtained. According to the categories of each hierarchy, a tree-shaped knowledge base structure can be generated. Then, the knowledge points corresponding to each category, i.e., the questions, the corresponding answers, and the attribute information such as the consultation frequency, may be stored in a corresponding node at the lowest layer of the knowledge base. For example, the knowledge points for the educational staging products in the above embodiments are stored in the lowest level node corresponding to the educational staging. The knowledge points corresponding to the category of 'repayment problem' under the education stage are stored in nodes corresponding to the categories of 'how to repay', 'repayment amount', 'overdue repayment' and 'advance repayment'; further, for example, the knowledge point corresponding to the category "how to pay" is stored in the knowledge points corresponding to the categories "APP payment", "password free payment", and "automatic payment". In the above manner, each knowledge point corresponding to each category may be stored in the corresponding lowest node according to the correspondence relationship of the categories of the respective layers in the knowledge base.
In addition, according to the historical consultation information of the intelligent customer service, the service state of the user corresponding to each problem of each node in the consultation knowledge base, the entrance position of entering the intelligent customer service and the consultation peak time of the problems with centralized consultation characteristics can be mined. Then, according to the mined information, the corresponding entry positions entering the intelligent customer service are hooked on the nodes, that is, the nodes and the corresponding entry positions entering the intelligent customer service establish a corresponding relationship, and in this embodiment, one node may correspond to one, two or more entry positions entering the intelligent customer service. And then, according to the mined information, establishing a corresponding relation between the service state of the user and the nodes in the knowledge base. Meanwhile, in the information table, the consultation peak periods of some nodes can be stored, and because some problems in the knowledge points have the characteristic of centralized consultation, in the embodiment, the corresponding relation between the consultation peak periods of the problems with the characteristic of centralized consultation and the corresponding nodes in the knowledge base can be established and stored in the information. That is, some nodes in the information table have corresponding consultation peak periods. The problem in the knowledge point among the nodes having the corresponding consultation peak period has a characteristic of centralized consultation. In the manner described above, a knowledge base and information tables are created. The corresponding target problem can be subsequently obtained from the knowledge base according to the knowledge base and the information table in the manner of the above embodiment.
According to the information recommendation method for the intelligent customer service, when the situation that the user enters the intelligent customer service is detected, the characteristic parameters of the user entering the intelligent customer service are obtained; acquiring a service state of a user; acquiring corresponding N target problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user; recommending N target questions to the user. Compared with the problem prediction method based on the access behavior track of the user in the prior art, the technical scheme of the embodiment can more accurately predict the problem that the user wants to consult according to the service state of the user and the characteristic parameters of entering the intelligent customer service, thereby effectively improving the accuracy of predicting the problem. Moreover, the accuracy of the prediction problem is effectively improved, so that the operation cost of the user can be effectively reduced, and the use experience of the user can be effectively improved.
Fig. 2 is a block diagram of a first embodiment of a server for intelligent customer service according to the present invention. As shown in fig. 2, the server of the intelligent customer service in this embodiment may specifically include: the system comprises a characteristic parameter acquisition module 10, a service state acquisition module 11, a problem acquisition module 12 and a recommendation module 13.
The characteristic parameter obtaining module 10 is configured to obtain a characteristic parameter of a user entering the intelligent customer service when the user is detected to enter the intelligent customer service;
the service state acquiring module 11 is configured to acquire a service state of a user;
the problem acquisition module 12 is configured to acquire corresponding N target problems from the knowledge base according to the feature parameters entering the intelligent customer service acquired by the feature parameter acquisition module 10 and the service state of the user acquired by the service state acquisition module 11; n is a positive integer;
the recommending module 13 is configured to recommend the N target questions acquired by the question acquiring module 12 to the user.
The implementation principle and technical effect of the server for intelligent customer service using the module to implement information recommendation of intelligent customer service are the same as those of the related method embodiments, and reference may be made to the description of the related method embodiments in detail, which is not described herein again.
Fig. 3 is a block diagram of a second embodiment of the server for intelligent customer service according to the present invention. As shown in fig. 3, the server of intelligent customer service in this embodiment further introduces the technical solution of the present invention in more detail on the basis of the technical solution of the embodiment shown in fig. 2.
As shown in fig. 3, the server for intelligent customer service of the present embodiment further includes:
the answer obtaining module 14 is configured to, if a first target question of the N questions is selected by the user, obtain an answer corresponding to the first target question:
the recommending module 13 is further configured to feed back an answer corresponding to the first target question acquired by the answer acquiring module 14 to the user.
Further optionally, in the server of the intelligent customer service in this embodiment, the service state obtaining module 10 is specifically configured to:
acquiring an identifier of a user;
and acquiring the service state of the user from the user information base according to the identification of the user.
Further optionally, in the server of the intelligent customer service in this embodiment, the problem obtaining module 12 is specifically configured to:
acquiring a plurality of corresponding alternative problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service acquired by the characteristic parameter acquisition module 10 and the service state of the user acquired by the service state acquisition module 11;
and acquiring the first N candidate problems with the highest consultation frequency from the plurality of candidate problems as the corresponding N target problems.
Further optionally, in the server of the intelligent customer service in this embodiment, the characteristic parameter obtaining module 10 is specifically configured to obtain an entry position where the user enters the intelligent customer service;
correspondingly, the problem obtaining module 12 is specifically configured to:
acquiring a plurality of corresponding first nodes from a knowledge base according to the entry position of the user entering the intelligent customer service, which is acquired by the characteristic parameter acquisition module 10;
acquiring at least one corresponding second node from the plurality of first nodes according to the service state of the user acquired by the service state acquisition module 11 and the correspondence between the service state of the user in the pre-established information table and the nodes in the knowledge base;
and acquiring a plurality of corresponding alternative problems from each second node in the knowledge base.
Further optionally, in the server of the intelligent customer service in this embodiment, the characteristic parameter obtaining module 11 is specifically configured to obtain an entry position and consultation time of the user entering the intelligent customer service;
correspondingly, the problem obtaining module 12 is specifically configured to:
acquiring a plurality of corresponding first nodes from a knowledge base according to the entry position of the user entering the intelligent customer service, which is acquired by the characteristic parameter acquisition module 10;
acquiring at least one corresponding second node from the plurality of first nodes according to the service state of the user acquired by the service state acquisition module 11 and the correspondence between the service state of the user in the pre-established information table and the nodes in the knowledge base;
acquiring consultation peak periods corresponding to the second nodes according to the corresponding relation between the consultation peak periods in the information table and the nodes in the knowledge base;
according to the consultation time, at least one third node in the consultation peak period hit by the consultation time is obtained from at least one second node;
and acquiring a plurality of corresponding alternative problems from each third node in the knowledge base.
Further optionally, as shown in fig. 3, the server for intelligent customer service in this embodiment further includes:
the creating module 15 is used for creating a knowledge base with a tree structure according to the categories of products served by the intelligent customer service and the hierarchical relationship of the problem categories in each product;
the mining module 16 is used for mining all the problems of each node in the knowledge base created by the creating module 15, answers corresponding to the problems and consultation frequency of the problems according to historical consultation information of the intelligent customer service;
the storage module 17 is used for storing each question, the corresponding answer and the corresponding consultation frequency on the corresponding node in the knowledge base;
the mining module 16 is further configured to mine, according to the historical consultation information of the intelligent customer service, a business state of the user corresponding to each problem of each node in the knowledge base created by the consultation creating module 15, an entry position where the user enters the intelligent customer service, and a consultation peak period of the problems with centralized consultation characteristics;
the storage module 17 is further configured to hook a corresponding entry position for entering the intelligent customer service to each node in the knowledge base;
the storage module 17 is further configured to obtain a correspondence between the service state of the user and the node in the knowledge base according to the service state of the user corresponding to each problem of each node in the mined knowledge base, and store the correspondence in the information table;
the storage module 17 is further configured to obtain a correspondence between the consultation peak periods of the problems with the centralized consultation characteristics and the nodes in the knowledge base according to the mined consultation peak periods of the problems with the centralized consultation characteristics, and store the correspondence in the information table.
Correspondingly, the problem obtaining module 12 is configured to obtain the corresponding N target problems from the knowledge base created by the creating module 15 according to the feature parameters entering the intelligent customer service obtained by the feature parameter obtaining module 10 and the service state of the user obtained by the service state obtaining module 11.
The implementation principle and technical effect of the server for intelligent customer service using the module to implement information recommendation of intelligent customer service are the same as those of the related method embodiments, and reference may be made to the description of the related method embodiments in detail, which is not described herein again.
Fig. 4 is a block diagram of an embodiment of a server apparatus of the present invention. As shown in fig. 4, the server device of the present embodiment includes: one or more processors 30, and a memory 40, the memory 40 being configured to store one or more programs, when the one or more programs stored in the memory 40 are executed by the one or more processors 30, the one or more processors 30 are enabled to implement the information recommendation method for intelligent customer service according to the embodiment shown in fig. 1-3. The embodiment shown in fig. 4 is exemplified by including a plurality of processors 30.
For example, fig. 5 is an exemplary diagram of a server device provided by the present invention. FIG. 5 illustrates a block diagram of an exemplary server device 12a suitable for use in implementing embodiments of the present invention. The server device 12a shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in FIG. 5, server device 12a is in the form of a general purpose computing device. The components of server device 12a may include, but are not limited to: one or more processors 16a, a system memory 28a, and a bus 18a that connects the various system components (including the system memory 28a and the processors 16 a).
Bus 18a represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
The system memory 28a may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30a and/or cache memory 32 a. Server device 12a may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34a may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18a by one or more data media interfaces. System memory 28a may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of the various embodiments of the invention described above in fig. 1-3.
A program/utility 40a having a set (at least one) of program modules 42a may be stored, for example, in system memory 28a, such program modules 42a including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may include an implementation of a network environment. Program modules 42a generally perform the functions and/or methodologies described above in connection with the various embodiments of fig. 1-5 of the present invention.
The processor 16a executes various functional applications and data processing by executing programs stored in the system memory 28a, for example, to implement the information recommendation method for intelligent customer service shown in the above-described embodiment.
The present invention also provides a computer-readable medium on which a computer program is stored, which when executed by a processor implements the information recommendation method for intelligent customer service as shown in the above embodiments.
The computer-readable media of this embodiment may include RAM30a, and/or cache memory 32a, and/or storage system 34a in system memory 28a in the embodiment illustrated in fig. 5 described above.
With the development of technology, the propagation path of computer programs is no longer limited to tangible media, and the computer programs can be directly downloaded from a network or acquired by other methods. Accordingly, the computer-readable medium in the present embodiment may include not only tangible media but also intangible media.
The computer-readable medium of the present embodiments may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (14)
1. An information recommendation method for intelligent customer service is characterized by comprising the following steps:
when detecting that a user enters intelligent customer service, acquiring characteristic parameters of the user entering the intelligent customer service;
acquiring the service state of the user in an information base;
acquiring N corresponding target problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user; n is a positive integer;
recommending the N target questions to the user;
the method for acquiring N corresponding target problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user specifically comprises the following steps:
acquiring a plurality of corresponding alternative problems from the knowledge base according to the entry position and consultation time of the user in the characteristic parameters of the intelligent customer service and the service state of the user;
and acquiring the first N candidate problems with the highest consultation frequency from the plurality of candidate problems as the corresponding N target problems.
2. The method of claim 1, wherein after recommending the N target questions to the user, the method further comprises:
if a first target question of the N questions is selected by the user, acquiring an answer corresponding to the first target question:
and feeding back an answer corresponding to the first target question to the user.
3. The method according to claim 1, wherein the obtaining the service status of the user specifically comprises:
acquiring the identification of the user;
and acquiring the service state of the user from a user information base according to the user identification.
4. The method according to claim 1, wherein the obtaining of the characteristic parameter of the user entering the intelligent customer service specifically comprises:
acquiring the entrance position of the user entering the intelligent customer service;
correspondingly, according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user, obtaining a plurality of corresponding alternative problems from the knowledge base, specifically comprising:
acquiring a plurality of corresponding first nodes from the knowledge base according to the entrance position of the user entering the intelligent customer service;
acquiring at least one corresponding second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user and the nodes in the knowledge base in a pre-established information table;
and acquiring the plurality of corresponding candidate problems from each second node in the knowledge base.
5. The method of claim 4, wherein the characteristic parameters of the user entering the smart customer service further comprise a consultation time; correspondingly, acquiring the characteristic parameters of the user entering the intelligent customer service specifically comprises the following steps:
acquiring the entrance position of the user entering the intelligent customer service and the consultation time;
correspondingly, the step of enabling the user to enter the characteristic parameters of the intelligent customer service and the service state of the user and acquiring a plurality of corresponding alternative problems from the knowledge base specifically comprises the following steps:
acquiring the corresponding first nodes from the knowledge base according to the entrance position of the user entering the intelligent customer service;
acquiring the corresponding at least one second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user and the nodes in the knowledge base in a pre-established information table;
acquiring the consultation peak periods corresponding to the second nodes according to the corresponding relation between the consultation peak periods in the information table and the nodes in the knowledge base;
acquiring at least one third node of the consultation peak period hit by the consultation time from the at least one second node according to the consultation time;
and acquiring the plurality of corresponding candidate problems from each third node in the knowledge base.
6. The method according to claim 4 or 5, wherein before acquiring the corresponding N target questions from the knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user, the method further comprises:
creating the knowledge base with a tree structure according to the categories of products served by the intelligent customer service and the hierarchical relation of the problem categories in each product;
mining all the problems of each node in the knowledge base, answers corresponding to the problems and consultation frequency of the problems according to historical consultation information of the intelligent customer service;
storing each question, the corresponding answer and the corresponding consultation frequency on a corresponding node in the knowledge base;
according to the historical consultation information of the intelligent customer service, the business state of a user corresponding to each problem of each node in the knowledge base is mined and consulted, the entrance position of the user entering the intelligent customer service is accessed, and the consultation peak period of the problems with centralized consultation characteristics is obtained;
hanging corresponding entrance positions for entering the intelligent customer service on each node in the knowledge base;
acquiring a corresponding relation between the service state of the user and the nodes in the knowledge base according to the service state of the user corresponding to each problem of each node in the knowledge base, and storing the corresponding relation in the information table;
and acquiring the corresponding relation between the consultation peak period of the problem with the centralized consultation characteristic and the nodes in the knowledge base according to the mined consultation peak period of the problem with the centralized consultation characteristic, and storing the corresponding relation in the information table.
7. A server of intelligent customer service, the server comprising:
the system comprises a characteristic parameter acquisition module, a service management module and a service management module, wherein the characteristic parameter acquisition module is used for acquiring a characteristic parameter of a user entering the intelligent customer service when detecting that the user enters the intelligent customer service;
a service state obtaining module, configured to obtain a service state of the user in an information base;
the problem acquisition module is used for acquiring corresponding N target problems from a knowledge base according to the characteristic parameters of the user entering the intelligent customer service and the service state of the user; n is a positive integer;
a recommending module for recommending the N target questions to the user;
the problem acquisition module is specifically configured to:
acquiring a plurality of corresponding alternative problems from the knowledge base according to the entry position and consultation time of the user in the characteristic parameters of the intelligent customer service and the service state of the user;
and acquiring the first N candidate problems with the highest consultation frequency from the plurality of candidate problems as the corresponding N target problems.
8. The server of claim 7, further comprising:
an answer obtaining module, configured to, if a first target question of the N questions is selected by the user, obtain an answer corresponding to the first target question:
the recommending module is further configured to feed back an answer corresponding to the first target question to the user.
9. The server according to claim 7, wherein the service status obtaining module is specifically configured to:
when detecting that a user enters intelligent customer service, acquiring an identifier of the user;
and acquiring the service state of the user from a user information base according to the user identification.
10. The server according to claim 7, wherein the characteristic parameter obtaining module is specifically configured to obtain an entry location where the user enters the smart customer service;
correspondingly, the problem acquisition module is specifically configured to:
acquiring a plurality of corresponding first nodes from the knowledge base according to the entrance position of the user entering the intelligent customer service;
acquiring at least one corresponding second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user and the nodes in the knowledge base in a pre-established information table;
and acquiring the plurality of corresponding candidate problems from each second node in the knowledge base.
11. The server according to claim 10, wherein the characteristic parameter obtaining module is specifically configured to obtain an entry location where the user enters the smart customer service and the consultation time;
correspondingly, the problem acquisition module is specifically configured to:
acquiring the corresponding first nodes from the knowledge base according to the entrance position of the user entering the intelligent customer service;
acquiring the corresponding at least one second node from the plurality of first nodes according to the service state of the user and the corresponding relation between the service state of the user and the nodes in the knowledge base in a pre-established information table;
acquiring the consultation peak periods corresponding to the second nodes according to the corresponding relation between the consultation peak periods in the information table and the nodes in the knowledge base;
acquiring at least one third node of the consultation peak period hit by the consultation time from the at least one second node according to the consultation time;
and acquiring the plurality of corresponding candidate problems from each third node in the knowledge base.
12. The server according to claim 10 or 11, wherein the server further comprises:
the creation module is used for creating the knowledge base with a tree structure according to the categories of the products served by the intelligent customer service and the hierarchical relationship of the problem categories in each product;
the mining module is used for mining all the problems of all the nodes in the knowledge base, answers corresponding to the problems and consultation frequency of the problems according to historical consultation information of the intelligent customer service;
the storage module is used for storing each question, the corresponding answer and the corresponding consultation frequency on the corresponding node in the knowledge base;
the mining module is further used for mining the service state of the user corresponding to each problem of each node in the knowledge base, the entrance position of the user entering the intelligent customer service and the consultation peak period of the problems with centralized consultation characteristics according to the historical consultation information of the intelligent customer service;
the storage module is further used for hooking corresponding entrance positions for entering the intelligent customer service to the nodes in the knowledge base;
the storage module is further configured to obtain a correspondence between the service state of the user and the node in the knowledge base according to the service state of the user corresponding to each problem of each node in the mined knowledge base, and store the correspondence in the information table;
the storage module is further configured to obtain a correspondence between the consultation peak periods of the problems with the centralized consultation characteristics and the nodes in the knowledge base according to the mined consultation peak periods of the problems with the centralized consultation characteristics, and store the correspondence in the information table.
13. A server device, characterized in that the device comprises:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
14. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-6.
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 CN110019693A (en) | 2019-07-16 |
CN110019693B true 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) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6814482B2 (en) * | 2017-11-29 | 2021-01-20 | 株式会社医療情報技術研究所 | Knowledge management system |
CN110569346B (en) * | 2019-09-10 | 2022-08-12 | 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 |
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 |
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 |
Family Cites Families (18)
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 |
CN101340552B (en) * | 2008-08-11 | 2010-11-17 | 中国联合网络通信集团有限公司 | Synthetic service navigation system |
CN103516908B (en) * | 2013-10-09 | 2016-08-24 | 北京奇虎科技有限公司 | Auxiliary replys the method and device of 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 |
CN106528613B (en) * | 2016-05-26 | 2018-11-27 | 中科鼎富(北京)科技发展有限公司 | Intelligent answer method and device |
CN106897334B (en) * | 2016-06-24 | 2020-07-14 | 阿里巴巴集团控股有限公司 | 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 |
CN106572001B (en) * | 2016-10-31 | 2019-10-11 | 厦门快商通科技股份有限公司 | A kind of dialogue method and system of intelligent customer service |
CN106648688B (en) * | 2016-12-29 | 2021-02-26 | 北京奇虎科技有限公司 | Information display method and device |
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 |
-
2017
- 2017-07-25 CN CN201710610706.3A patent/CN110019693B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN110019693A (en) | 2019-07-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110019693B (en) | Information recommendation method, server and computer readable medium for intelligent customer service | |
US8024660B1 (en) | Method and apparatus for variable help content and abandonment intervention based on user behavior | |
KR101794221B1 (en) | System and method for providing calculation of online sellers | |
US8626769B1 (en) | Community contributed rules in online accounting systems | |
US20120290486A1 (en) | Automated method and system for interactive compulsory reporting of lease application adjudication decisions, ongoing tenancy histories and debtor collections | |
EP3754582A1 (en) | Systems and methods for recommending merchant discussion groups based on settings in an e-commerce platform | |
US20210350488A1 (en) | Methods and systems for notifying user of change to data sharing settings | |
CA2875435C (en) | System and method for identifying vehicles for a purchaser | |
US20230385834A1 (en) | Product analysis platform to perform a facial recognition analysis to provide information associated with a product to a user | |
CN111612512A (en) | Resource allocation method and device and electronic equipment | |
CN104376452A (en) | System and method for managing payment success rate on basis of international card payment channel | |
US11798006B1 (en) | Automating content and information delivery | |
CN110689425A (en) | Method and device for pricing quota based on income and electronic equipment | |
US20150356575A1 (en) | Methods and systems for predicting online and in-store purchasing | |
CN115049448A (en) | System and method for optimizing performance of online services | |
CN112348658A (en) | Resource allocation method and device and electronic equipment | |
WO2017105794A1 (en) | System and method for test data provisioning | |
CN111179057A (en) | Resource allocation method and device and electronic equipment | |
US20190147454A1 (en) | Real-time event management system for mobile devices | |
CN115994819A (en) | Risk customer identification method, apparatus, device and medium | |
US20220230178A1 (en) | Computer-implemented systems and methods for detecting fraudulent activity | |
US11586636B2 (en) | Methods and systems for generating search results | |
CA3224473A1 (en) | System and method for introduction of a transaction mechanism to an e-commerce website without necessitation of multi party systems integration | |
JP6878343B2 (en) | Best Rate Guarantee Methods, Computers, and Programs | |
US20240202803A1 (en) | System And Method for Modifying a Portion of a User Interface According to An Interaction with A Message |
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 |