CN116701606A - Intelligent customer service management method, system, equipment and medium - Google Patents
Intelligent customer service management method, system, equipment and medium Download PDFInfo
- Publication number
- CN116701606A CN116701606A CN202310854575.9A CN202310854575A CN116701606A CN 116701606 A CN116701606 A CN 116701606A CN 202310854575 A CN202310854575 A CN 202310854575A CN 116701606 A CN116701606 A CN 116701606A
- Authority
- CN
- China
- Prior art keywords
- dialogue
- customer service
- intelligent customer
- user
- answer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims description 11
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 235000012907 honey Nutrition 0.000 description 22
- 238000010586 diagram Methods 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 5
- 238000006731 degradation reaction Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012552 review Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- 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
- G06F16/34—Browsing; Visualisation therefor
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a management method, a system, equipment and a medium for intelligent customer service, belonging to the field of customer service management. The method comprises the following steps: acquiring dialogue question information between an online customer service SDK and a user; analyzing and extracting the identification in the dialogue question message, searching the intelligent customer service corresponding to the identification, and sending the dialogue question message to the searched intelligent customer service; the intelligent customer service generates a corresponding dialogue answer based on the dialogue question message; and sending the dialogue answer to the user. The recognition rate of intelligent customer service to the problem is effectively improved, and therefore the user experience is greatly improved.
Description
Technical Field
The invention relates to the technical field of customer service management, in particular to an intelligent customer service management method, system, equipment and medium.
Background
With the development of economy and society, the travel demands of people are increasing, and taking a car for convenience is the preferred mode of people's travel. However, with the increasing demands of users, the number of online customer service lines for drivers and passengers is also increasing, which is still a small pressure for the customer service staff. Statistics according to related data show that the repetition rate of most incoming line problems is very high, so intelligent customer service processing is generally adopted.
At present, intelligent customer service performs intelligent question and answer by adopting a text matching mode through a knowledge base maintained by the intelligent customer service. However, the method has poor accuracy, low efficiency of solving the problems, unfriendly interaction of the driver and the passenger with the line, and most of the problems can be finally solved by manual customer service, and the problem of high pressure of the current line cannot be solved. In addition, if an activity is newly added, a new port needs to be redeveloped, the development efficiency is low, and the customer service line is possibly increased by times. On the other hand, the maintenance of the knowledge base requires a lot of human capital, and therefore, there is a need to provide a method, a system, a device and a medium for managing intelligent customer service.
Disclosure of Invention
In view of the above drawbacks of the prior art, an object of the present invention is to provide an intelligent customer service method, system, device and storage medium, so as to solve the problem in the prior art that the intelligent customer service cannot accurately identify the question intention of the user, resulting in low accuracy of answers fed back to the user and lower experience of the user.
To achieve the above and other related objects, the present invention provides a method for managing intelligent customer service, comprising the following steps:
acquiring dialogue question information between an online customer service SDK and a user;
analyzing and extracting the identification in the dialogue question message, searching the intelligent customer service corresponding to the identification, and sending the dialogue question message to the searched intelligent customer service;
the intelligent customer service generates a corresponding dialogue answer based on the dialogue question message;
and sending the dialogue answer to the user.
In an embodiment of the present invention, the dialogue question message is stored in a message queue, and before the dialogue question message between the online customer service SDK and the user is obtained, the method further includes: and the message queue carries out flow limiting processing on the dialogue question message based on a preset flow limiting mechanism.
In an embodiment of the present invention, the parsing and extracting the identifier in the dialogue question message, and searching the intelligent customer service corresponding to the identifier, includes:
analyzing the dialogue question message based on a preset analysis principle, and acquiring the SDK version number and service line information in the dialogue question message;
judging whether the SDK version number is larger than or equal to a preset version threshold value;
if the SDK version number is larger than or equal to a preset version threshold value, matching corresponding intelligent customer service based on the service line information;
if the SDK version number is smaller than a preset version threshold value, based on a preset knowledge base, a dialogue answer adapted to the dialogue question message is obtained and sent to a user.
In an embodiment of the present invention, the obtaining, based on a preset knowledge base, a dialogue answer adapted to the dialogue question message and sending the dialogue answer to a user includes:
acquiring the message content in the dialogue question message;
calculating the matching degree of the message content and various preset dialogue answers in a preset knowledge base, and obtaining the dialogue answer with the highest matching degree with the user information content;
and sending the dialogue answer to the user.
In an embodiment of the present invention, the intelligent customer service generates a corresponding dialogue answer based on the dialogue question message, including:
the intelligent customer service judges whether to call a custom interface according to the dialogue question message;
if the custom interface is called, remote data call is carried out on the custom interface, and a dialogue answer returned by the custom interface is obtained;
if the user-defined interface is not called, acquiring a corresponding dialogue answer according to the dialogue question message and a preset knowledge cloud system
In one embodiment of the invention, the remote data call is a Dubbo-based remote data call.
In an embodiment of the present invention, there is also provided a management system for intelligent customer service, the system including:
the dialogue question acquisition module is used for acquiring dialogue question information between the on-line customer service SDK and the user;
the intelligent customer service searching module is used for analyzing and extracting the identifier in the dialogue question message, searching the intelligent customer service corresponding to the identifier and sending the dialogue question message to the searched intelligent customer service;
the dialogue answer generation module is used for generating corresponding dialogue answers based on the dialogue question information by the intelligent customer service;
and the dialogue answer sending module is used for sending the dialogue answer to the user.
In an embodiment of the present invention, there is further provided an intelligent customer service management device, including a processor, where the processor is coupled to a memory, and the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the method of any one of the above is implemented.
In an embodiment of the invention, there is also provided a computer readable storage medium comprising a program which, when run on a computer, performs the method of any of the above.
In summary, in the invention, after the dialogue question message between the online customer service SDK and the user is obtained, the identification in the dialogue question message is extracted by analyzing the dialogue question message, and the intelligent customer service adapting to the identification is searched according to the identification, so that the current dialogue question message is sent to the intelligent customer service. The intelligent customer service searches and generates a proper dialogue answer according to the dialogue question information, and the intelligent customer service engine sends the dialogue answer to the user who gives the question. By configuring the corresponding intelligent customer service for each type of problem in a targeted manner, the recognition rate of the intelligent customer service on the problems is effectively improved, and therefore the user experience is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a system architecture diagram showing a method for managing intelligent customer service according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for managing intelligent customer service according to an embodiment of the invention;
FIG. 3 is a flow chart of a message queue acquiring information according to an embodiment of the invention;
FIG. 4 is a flow chart of the intelligent customer service searching process according to an embodiment of the invention;
FIG. 5 is a flow chart of a degradation process according to an embodiment of the invention;
FIG. 6 is a flow chart illustrating the generation of answers to a dialogue in an embodiment of the invention;
FIG. 7 is a system timing diagram illustrating a method for managing intelligent customer service according to an embodiment of the invention;
FIG. 8 is a diagram of a resource platform architecture in accordance with one embodiment of the present invention;
FIG. 9 is a diagram showing a method for managing intelligent customer service according to an embodiment of the invention;
FIG. 10 is a flow chart of an execution engine according to an embodiment of the invention;
fig. 11 is a schematic structural diagram of a management system for intelligent customer service according to an embodiment of the invention.
Description of element numbers:
100. a management system of intelligent customer service; 110. a dialogue question acquisition module; 120. an intelligent customer service searching module; 130. a dialogue answer generation module; 140. and a dialogue answer transmitting module.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. It is also to be understood that the terminology used in the examples of the invention is for the purpose of describing particular embodiments only, and is not intended to limit the scope of the invention. The test methods in the following examples, in which specific conditions are not noted, are generally conducted under conventional conditions or under conditions recommended by the respective manufacturers.
Please refer to fig. 1 to 11. It should be understood that the structures, proportions, sizes, etc. shown in the drawings are for illustration purposes only and should not be construed as limiting the invention to the extent that it can be practiced, since modifications, changes in the proportions, or adjustments of the sizes, which are otherwise, used in the practice of the invention, are included in the spirit and scope of the invention which is otherwise, without departing from the spirit or scope thereof. Also, the terms such as "upper," "lower," "left," "right," "middle," and "a" and the like recited in the present specification are merely for descriptive purposes and are not intended to limit the scope of the invention, but are intended to provide relative positional changes or modifications without materially altering the technical context in which the invention may be practiced.
Where numerical ranges are provided in the examples, it is understood that unless otherwise stated herein, both endpoints of each numerical range and any number between the two endpoints are significant both in the numerical range. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs and to which this invention belongs, and any method, apparatus, or material of the prior art similar or equivalent to the methods, apparatus, or materials described in the examples of this invention may be used to practice the invention.
The invention provides a management method of intelligent customer service, which innovatively combines the cloud honey AI conversation capability, constructs an adaptive conversation flow aiming at specific keywords, and effectively improves the recognition rate of intelligent customer service on problems by integrating the conversation capability of an intelligent conversation robot. The robot question-answering capability is built by using DUBBO generalization and elasticity, a generalization platform is built according to the Dubbo capability, the existing DUBBO interfaces of all service lines are accessed, the existing service capability is integrated, knowledge base information is filled, and the manual maintenance cost of the knowledge base is reduced. Through integrated Sentinel, flow monitoring is carried out on the robot question and answer monitoring, the quick failure capability is provided, and the stability of intelligent customer service is ensured.
Referring to fig. 1, fig. 1 is a system architecture diagram of a method for managing intelligent customer service according to an embodiment of the invention. The invention relates to a management method of intelligent customer service, and a corresponding system architecture comprises a presentation layer, a gateway layer, a service layer and a data layer. The display layer comprises a driver interface and an Arin cloud honey interface, and multiple input modes such as common problem summarization, voice input, text input and the like can be provided on the driver interface. The cloud and honey interface in the Ari is used as a calling interface, and displays the received dialogue question information, the corresponding dialogue answers, the knowledge base and other information. The gateway layer comprises an intelligent customer service resource platform, a TCP-Server and an instant messaging system IM. And the user inputs a dialogue question on the intelligent customer service resource platform and obtains a corresponding dialogue answer through the cloud honey. Specifically, the cloud honey and the intelligent customer service resource platform are connected through HTTP, and the driver and the Server TCP-Server are connected through long, so that more TCP establishment and closing operations can be omitted, resource waste is reduced, and information transmission time is saved. The cloud Server TCP-Server sends the received dialogue question to the instant messaging system IM, and the instant messaging system IM transmits the dialogue question to the intelligent customer service engine in the form of a message body based on the MQTT protocol. Firstly, judging whether the dialogue question can be processed by the cloud honey or not through a gray level strategy engine, if so, configuring by an intelligent robot route, distributing the corresponding cloud honey intelligent robot as an execution engine, calling Yun Xiao a honey dialogue, and communicating with a user. If the dialogue question cannot be processed by the cloud honey, the degradation process is carried out, the question posed by the user is responded based on the FAQ knowledge base through online customer service, the question is transmitted to an instant messaging system (Instant Messenger, IM) through a Websocket protocol, and the response content is transmitted to the user through the IM. Wherein, the relevant data information of the FAQ knowledge base is stored in the Lucene database. Further, if the user is not satisfied with the answer of the cloud honey or in the gray level policy engine, it is determined that the dialogue question sent by the user needs to be directly processed by a human, the dialogue question can be processed by a human customer service, and the question of the user is responded by means of various pre-built business knowledge bases. The business knowledge base comprises, but is not limited to, a network taxi consultation inquiry, a windward consultation inquiry, a taxi consultation inquiry and the like.
Referring to fig. 1, fig. 2 and fig. 7, fig. 2 is a flow chart of a method for managing intelligent customer service according to an embodiment of the invention, and fig. 7 is a system timing chart of a method for managing intelligent customer service according to an embodiment of the invention. In an embodiment of the present invention, the method for managing intelligent customer service includes the following steps:
s10, acquiring dialogue question information between the online customer service SDK and the user.
The intelligent customer service engine realizes the message communication with the user through the online customer service SDK, the user sends the dialogue question message to the online customer service SDK, and after the online customer service SDK acquires the dialogue question message sent by the user, the dialogue question message is sent to the intelligent customer service engine through a preset information transmission mode. The intelligent customer service engine matches the appropriate intelligent customer service for the user based on the relevant identification in the dialogue question message.
Specifically, referring to fig. 3, in an embodiment of the present invention, before step S10, the method further includes:
s11, the online customer service SDK receives a dialogue question sent by a user, converts the dialogue question into a message body with a preset format and sends the message body to the instant messaging system. After the user initiates an online customer service question, the dialogue question is sent to the online customer service SDK. After receiving the dialogue question sent by the user, the online customer service SDK converts the dialogue question into a message body according to a message body in a preset format, and sends the message body to the instant messaging system through a TCP protocol. The format of the message body is as follows: user identification uid, user type utype, service line bizLine, user message content and extension information extra; wherein the content of the user message is: message content msg, session Id, sending type requestType, user terminal type appType, service line bizLine and user problem; the extension information extra is: operating system SDKOS, version name sdkvmerion, version number sdkvmerion code. It can be understood that the message body format can be elastically scaled on the basis of the above, and those skilled in the art can adaptively add or delete corresponding contents according to actual needs, which is not limited herein. For example, when the user identifier uid is a, the user type appType is b, the version number sdkvmrsioncode is c, the service line bizLine is d, and the session sessionId is e, the message body is interpreted as: and a user performs a session with e as session id on the d service line once on the app with c version number b, and the problem is e. It should be noted that, for convenience of description, the present invention is directed to a driver and passenger platform, a system architecture diagram is drawn, and corresponding users are drivers and passengers, but the method for managing intelligent customer service according to the present invention may also be applicable to other types of service platforms, and is not limited herein.
And S12, the instant messaging system sends the message body to a message queue in real time.
The instant messaging system is a cross-platform customizable P2P instant messaging system, provides one-stop customized solutions for all industries, portals and enterprises, and creates a stable, safe, efficient and extensible instant messaging system. After receiving the message body, the instant messaging system sends the message body to the corresponding message queue in real time. In the invention, considering that the flow is more in the message interaction process, a plurality of producers and consumers are seamlessly supported for improving the throughput, and the message queue is Kafka.
In an embodiment of the present invention, before the instant messaging system sends the message body to the message queue in real time, the method further includes: the instant messaging system persists the message body to an RDS database. In order to facilitate subsequent customer service or users to review chat records at any time, the review speed is improved, so that dialogue information needs to be stored in a cloud RDS database in a lasting manner.
In an embodiment of the present invention, the dialogue question message is stored in a message queue, and before the dialogue question message between the online customer service SDK and the user is obtained, the method further includes: and the message queue carries out flow limiting processing on the dialogue question message based on a preset flow limiting mechanism. The dialogue question information is stored in the information queue in the form of information body, when a plurality of different information bodies are sent to the information queue at the same time, if the flow exceeds the preset quota, the information queue starts a flow limiting mechanism to limit the information body. Specifically, in one embodiment of the present invention, the current limiting mechanism includes interface fusing and interface current limiting. The flow entering the message queue at the same time can be limited by interface fusing and interface current limiting, so that the condition of network breakdown is avoided.
S20, analyzing and extracting the identification in the dialogue question message, searching the intelligent customer service corresponding to the identification, and sending the dialogue question message to the searched intelligent customer service.
The intelligent customer service engine (named csc-cs) monitors a message queue in Kafka in real time based on a pre-subscribed theme, acquires a corresponding message body from the message queue once a consumer corresponding to the theme appears in the message queue, and searches for the corresponding intelligent customer service by analyzing the message body. The intelligent customer service provided by the invention is cloud honey, yun Xiao honey is a session robot facing a developer, and intelligent sessions based on natural language processing, such as websites, APP, entity robots and the like, are supported to be realized on different message ends. The user can configure own specific knowledge base in the cloud honey to realize intelligent question and answer, and also can integrate with a third party API through multiple rounds of dialogue to realize self-service, such as: order inquiry, logistics tracking, self-service goods returning robots and the like.
Referring to fig. 1, fig. 4 and fig. 7, fig. 4 is a schematic flow chart of searching for intelligent customer service according to an embodiment of the invention. Specifically, in an embodiment of the present invention, in step S30, the parsing and extracting the identifier in the dialogue question message, and searching the intelligent customer service corresponding to the identifier, includes:
s21, analyzing the dialogue question message based on a preset analysis principle to acquire the SDK version number and service line information in the dialogue question message;
s22, judging whether the SDK version number is larger than or equal to a preset version threshold value;
s23, if the SDK version number is larger than or equal to a preset version threshold value, matching corresponding intelligent customer service based on the service line information;
and S24, if the SDK version number is smaller than a preset version threshold value, acquiring a dialogue answer adapted to the dialogue question message based on a preset knowledge base, and sending the dialogue answer to a user.
After receiving the message body, the intelligent customer service engine analyzes the message body according to a preset analysis principle to acquire the transmission type request type in the content of the user message and the SDKVERIon in the extension information extra. Considering version alternation, for old versions, the related functions of cloud nectar may not be supported, so that intelligent customer service cloud nectar may not be used, and therefore, whether the current version supports cloud nectar needs to be judged through an SDK version number SDKVErsionCode in a message body. If the SDK version number is smaller than the version threshold value, the current version is not supported by the intelligent customer service cloud nectar, and degradation processing is needed. If the SDK version number is greater than or equal to the version threshold value, the current version is indicated to support the cloud nectar. In order to accurately answer the questions of the user, the intelligent cloud small-honey robot of a corresponding type is matched for different business lines bizLine. Therefore, the intelligent customer service engine can acquire the problem type of the current user through the business line bizLine, so that the intelligent customer service engine is matched with the corresponding cloud small-honey intelligent robot to answer.
Referring to fig. 1, 5 and 7, fig. 5 is a schematic flow chart of a degradation process according to an embodiment of the invention. In an embodiment of the present invention, in step S24, the obtaining, based on a preset knowledge base, a dialogue answer adapted to the dialogue question message, and sending the dialogue answer to the user includes:
s241, acquiring the message content of the dialogue question message body;
s242, calculating the matching degree of the message content and various preset dialogue answers in a preset knowledge base, and obtaining the dialogue answer with the highest matching degree with the user information content;
s244, sending the dialogue answer to the user.
After the online customer service obtains the message content in the message body, the dialogue question content or key word information proposed by the user is input into a pre-constructed FAQ knowledge base, the FAQ knowledge base calculates dialogue answers with the highest matching degree with the dialogue question from various candidate dialogue answers through a key word matching method, the dialogue answers are presented on an output interface of the FAQ knowledge base, and the online customer service answers the dialogue questions proposed by the user according to the dialogue answers. The FAQ refers to the solutions of common problem items and corresponding problems, and some questions and answers frequently asked by the user are stored in the FAQ knowledge base. Through the degradation processing, when the system version number does not meet the use condition of the cloud honey, the user can still be ensured to obtain satisfactory answers, the service quality is improved, and the use experience of the user is effectively improved.
S30, the intelligent customer service generates a corresponding dialogue answer based on the dialogue question message.
Referring to fig. 1, fig. 6 to fig. 8, fig. 6 is a schematic flow chart of generating a dialogue answer according to an embodiment of the invention, and fig. 8 is a diagram of a resource platform framework according to an embodiment of the invention. In an embodiment of the present invention, in step S30, the intelligent customer service generates a corresponding dialogue answer based on the dialogue question message, including:
s31, the intelligent customer service judges whether to call a custom interface according to the dialogue question message;
s32, if the custom interface is called, remote data call is carried out on the custom interface, and a dialogue answer returned by the custom interface is obtained;
and S33, if the user-defined interface is not called, acquiring a corresponding dialogue answer according to the dialogue question message and a preset knowledge cloud system.
When the execution engine is cloud honey, the intelligent robot routing configuration obtains a corresponding cloud honey intelligent robot from a database according to a service line, takes the cloud honey intelligent robot as an intelligent customer service execution engine, and calls a corresponding gateway interface chatApi.chat according to the ID of the cloud honey intelligent robot. In the invention, the gateway is named csc-gateway. After receiving a call request of the cloud smart robot, the gateway csc-gateway requests to call an alicloud chat () interface so as to obtain a corresponding dialogue answer from the alicloud, wherein the call request contains a message body. After receiving the call request, the Arian cloud analyzes the message body, and judges whether the custom function node is configured or not by analyzing the corresponding dialogue flow configuration, if so, the Arian cloud considers that the custom interface API needs to be called, and if not, the custom interface API does not need to be called. Further, when the custom interface API needs to be called, the oricloud will send an HTTP call request to the corresponding custom interface according to URL information configured in the function node, where the custom interface may be adaptively set according to service needs, for example, a custom interface of a Cao operation trip may be set. In the invention, the custom interface is named csc-csop. In order to prevent the situation that the custom interface is crashed due to the surge of the traffic and prevent the situation of overtime transmission when the custom interface has a problem. When the custom interface receives a call request sent by the Arian cloud, the Sentinel component also performs measures such as interface current limiting and fusing by taking the flow as an access point and performing current limiting treatment on the data. After the user-defined interface receives the HTTP request sent by the Arian, the user-defined interface considers that the service needs to be called remotely through the modes of signature verification, authentication and the like, and obtains the corresponding generalized configuration in the cloud database according to the URL. In the present invention, the generalized configuration includes: interface class full path name interfaceName, interface method name apiName, interface method parameter configuration apipeamamConfig. In one embodiment of the invention, the remote data call is a Dubbo-based remote data call. Specifically, a corresponding generalization proxy object is obtained in a Dubbo preset generalization proxy factory, and when remote call is executed, call request data is dynamically generated according to generalization configuration by the generalization proxy object, wherein the call request data comprises, but is not limited to, a parameter type list, a parameter list and the like, and a call request is sent to a custom interface through a Dubbo network communication layer. After receiving the call request, the custom interface obtains the corresponding dialogue answer from the corresponding service platform according to the call request data, and sends the dialogue answer to the user through the instant messaging system IM. In one embodiment of the present invention, the instant messaging system persists the answer to the session in the RDS database for subsequent review by the user. In addition, if the user-defined interface API is not required to be called, the dialogue answer can be directly sent to the user by the cloud widget according to dialogue flow configuration in the message body. In this way, the alicloud can call the remote service without knowing the specific implementation class, and the corresponding service end only needs to expose the custom interface and does not need to expose the implementation class. This may increase the flexibility and scalability of the system. On the basis of intellectualization, the invention innovatively uses Dubbo generalization, builds a generalization platform according to Dubbo capability, can flexibly configure a middle business interface to acquire required data, and compared with the prior art, the method and the device need to newly access an interface to be redeveloped, and only need to configure an interface basic data interface when the interface is newly accessed.
And S40, sending the dialogue answer to the user.
After the intelligent customer service engine acquires the dialogue answers sent by the intelligent customer service, the dialogue answers are fed back to the message queue according to the receiving sequence. The instant messaging system IM monitors information in a message queue based on a pre-subscribed theme, receives a dialogue answer from the message queue when the information in the message queue is matched with the current theme, and feeds the dialogue answer back to the intelligent customer service SDK. The intelligent customer service SDK sends the received dialogue answers to the users who put out the questions, so that the users acquire the dialogue answers which are matched with the questions.
Referring to fig. 8 to 10, a user sends IM chat information to an online customer service, the information is sent to a customer service platform through an instant messaging system IM, and the user identity and the data of the proposed problem can be judged by reading the sending type requestType, service line bizLine, user identifier uid and the like in the chat information. And judging the type of the questions proposed by the user, such as the common question and answer type questions, or the dialogue initiated by the user in the form of order cards such as links, pictures and the like according to the data through the message policy route. And through tangential flow processing, the flow flowing into the execution engine is ensured to be stable. And then selecting a proper response mode for the user according to the judgment result, such as a response by a manual client or a response by using an intelligent customer service cloud and honey robot. When intelligent customer service response is selected, the cloud honey robot can accurately recognize answers required to be obtained by a user through intention recognition, and can conduct multi-round conversations with the user through an intelligent question-answer mode, and can also use a question-answer mode to push the answers to the user so as to finish the current conversations. When the dialogue is conducted, the intelligent customer service answers are more accurate through dialogue flow configuration of scene intention, and the use experience of a user is improved. After receiving the dialogue answer sent by the intelligent customer service, the user can evaluate the dialogue answer in a mode of praying or stepping on, and the evaluation result is returned to the intelligent customer service platform in a mode of adding a transparent field. When the user is not satisfied with the dialogue answer given by the intelligent customer service, the manual customer service processing can be selected, so that a satisfied answer is obtained.
The above method is divided into steps, which are only for clarity of description, and may be combined into one step or split into multiple steps when implemented, so long as they contain the same logic relationship, and they are all within the protection scope of the present invention; it is within the scope of the invention to add insignificant modifications to the algorithm or flow or introduce insignificant designs, but not to alter the core design of its algorithm and flow.
Referring to fig. 11, fig. 11 is a schematic structural diagram of a management system for intelligent customer service according to an embodiment of the invention. The intelligent customer service management system 100 includes a dialogue question acquisition module 110, an intelligent customer service search module 120, a dialogue answer generation module 130, and a dialogue answer transmission module 140. The dialogue question obtaining module 110 is configured to obtain a dialogue question message between the online customer service SDK and the user. The intelligent customer service searching module 120 is configured to parse and extract the identifier in the dialogue question message, search the intelligent customer service corresponding to the identifier, and send the dialogue question message to the searched intelligent customer service. The dialogue answer generating module 130 is configured to generate a corresponding dialogue answer based on the dialogue question message by the intelligent customer service. The dialogue answer sending module 140 is configured to send the dialogue answer to the user.
It should be noted that, in order to highlight the innovative part of the present invention, no module that is not very close to solving the technical problem presented by the present invention is introduced in the present embodiment, but it does not indicate that other modules are not present in the present embodiment.
In addition, it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein. In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional units.
The embodiment also provides an intelligent customer service management device, which comprises a processor and a memory, wherein the processor is coupled with the memory, the memory stores program instructions, and the task management method is realized when the program instructions stored in the memory are executed by the processor. The processor may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components; the Memory may comprise random access Memory (Random Access Memory, RAM) and may also include Non-Volatile Memory (Non-Volatile Memory), such as at least one disk Memory. The memory may be an internal memory of the random access memory (Random Access Memory, RAM) type, and the processor, memory may be integrated into one or more separate circuits or hardware, such as: an application specific integrated circuit (Application Specific Integrated Circuit, ASIC). It should be noted that the computer program in the above-mentioned memory may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a separate product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present invention.
The present embodiment also proposes a computer-readable storage medium storing computer instructions for causing a computer to execute the above-described intelligent customer service management method. The storage medium may be an electronic medium, a magnetic medium, an optical medium, an electromagnetic medium, an infrared medium, or a semiconductor system or propagation medium. The storage medium may also include semiconductor or solid state memory, magnetic tape, removable computer diskette, random Access Memory (RAM), read-only memory (ROM), rigid magnetic disk and optical disk. Optical discs may include compact disc-read only memory (CD-ROM), compact disc-read/write (CD-RW), and DVD.
In summary, in the invention, the conventional question-answering mode is abandoned, and only the self-maintained knowledge base is used as the basis of the incoming line question-answering, so that the provided answer cannot satisfy the user due to low question recognition rate. According to the intelligent conversation robot, the cloud honey AI conversation capability is innovatively combined, an adaptive conversation flow is constructed aiming at specific keywords, and the conversation capability of the intelligent conversation robot is integrated, so that the recognition rate of intelligent customer service on the problems is effectively improved, and the manual answer cost is reduced. In addition, the intelligent question answering mode enables the cloud honey intelligent robot to answer questions presented by clients quickly and accurately, waiting time of users is greatly reduced, and user experience is improved. Further, the invention constructs the question-answering capability of the robot by using the DUBBO generalization and elasticity, constructs a generalization platform according to the Dubbo capability, accesses each service line to have the existing DUBBO interface, and realizes the elasticity configuration of the middle service interface in a form corresponding to a self-defined function so as to acquire the required data. Compared with the traditional method, the method and the system for realizing the new access of the interface have the advantages that the interface needs to be redeveloped after the new access, the existing business capability is integrated, knowledge base information is filled, the knowledge base maintenance efficiency is improved, and the manual maintenance cost of the knowledge base is reduced. Only the basic data interface of the interface needs to be configured when the interface is newly accessed, so that the development efficiency is greatly improved. In addition, the invention provides the quick failure capability for the flow monitoring of the robot question and answer monitoring by integrating the Sentinel, and provides a guarantee for the stability of intelligent customer service. Therefore, the invention effectively overcomes some practical problems in the prior art, thereby having high utilization value and use significance.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims, which are within the ordinary skill of the art, be within the spirit and scope of the present disclosure.
Claims (9)
1. The intelligent customer service management method is characterized by comprising the following steps of:
acquiring dialogue question information between an online customer service SDK and a user;
analyzing and extracting the identification in the dialogue question message, searching the intelligent customer service corresponding to the identification, and sending the dialogue question message to the searched intelligent customer service;
the intelligent customer service generates a corresponding dialogue answer based on the dialogue question message;
and sending the dialogue answer to the user.
2. The method for managing intelligent customer service according to claim 1, wherein the parsing and extracting the identifier in the dialogue question message, searching the intelligent customer service corresponding to the identifier, comprises:
analyzing the dialogue question message based on a preset analysis principle, and acquiring the SDK version number and service line information in the dialogue question message;
judging whether the SDK version number is larger than or equal to a preset version threshold value;
if the SDK version number is larger than or equal to a preset version threshold value, matching corresponding intelligent customer service based on the service line information;
if the SDK version number is smaller than a preset version threshold value, based on a preset knowledge base, a dialogue answer adapted to the dialogue question message is obtained and sent to a user.
3. The intelligent customer service management method according to claim 2, wherein the acquiring, based on a preset knowledge base, a dialogue answer adapted to the dialogue question message and sending the dialogue answer to a user includes:
acquiring the message content in the dialogue question message;
calculating the matching degree of the message content and various preset dialogue answers in a preset knowledge base, and obtaining the dialogue answer with the highest matching degree with the user information content;
and sending the dialogue answer to the user.
4. The intelligent customer service management method according to claim 1, wherein the dialogue question message is stored in a message queue, and further comprising, before the step of acquiring the dialogue question message between the online customer service SDK and the user: and the message queue carries out flow limiting processing on the dialogue question message based on a preset flow limiting mechanism.
5. The method for managing intelligent customer service according to claim 1, wherein the intelligent customer service generates a corresponding dialogue answer based on the dialogue question message, comprising:
the intelligent customer service judges whether to call a custom interface according to the dialogue question message;
if the custom interface is called, remote data call is carried out on the custom interface, and a dialogue answer returned by the custom interface is obtained;
and if the user-defined interface is not called, acquiring a corresponding dialogue answer according to the dialogue question message and a preset knowledge cloud system.
6. The intelligent customer service management method according to claim 5, wherein the remote data call is a Dubbo-based remote data call.
7. A system for intelligent customer service management, the system comprising:
the dialogue question acquisition module is used for acquiring dialogue question information between the on-line customer service SDK and the user;
the intelligent customer service searching module is used for analyzing and extracting the identifier in the dialogue question message, searching the intelligent customer service corresponding to the identifier and sending the dialogue question message to the searched intelligent customer service; the dialogue answer generation module is used for generating corresponding dialogue answers based on the dialogue question information by the intelligent customer service;
and the dialogue answer sending module is used for sending the dialogue answer to the user.
8. An intelligent customer service management device, which is characterized in that: comprising a processor coupled to a memory, the memory storing program instructions that, when executed by the processor, implement the method of any one of claims 1 to 6.
9. A computer-readable storage medium, characterized by: comprising a program which, when run on a computer, performs the method according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310854575.9A CN116701606A (en) | 2023-07-12 | 2023-07-12 | Intelligent customer service management method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310854575.9A CN116701606A (en) | 2023-07-12 | 2023-07-12 | Intelligent customer service management method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116701606A true CN116701606A (en) | 2023-09-05 |
Family
ID=87835889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310854575.9A Pending CN116701606A (en) | 2023-07-12 | 2023-07-12 | Intelligent customer service management method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116701606A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391515A (en) * | 2023-10-24 | 2024-01-12 | 科讯嘉联信息技术有限公司 | Service quality management method and system based on general large language model |
-
2023
- 2023-07-12 CN CN202310854575.9A patent/CN116701606A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391515A (en) * | 2023-10-24 | 2024-01-12 | 科讯嘉联信息技术有限公司 | Service quality management method and system based on general large language model |
| CN117391515B (en) * | 2023-10-24 | 2024-06-07 | 科讯嘉联信息技术有限公司 | Service quality management method and system based on general large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11540340B2 (en) | System and method for analyzing messages and initiating communication sessions | |
| JP7135177B2 (en) | Dynamic communication routing based on consistency weighting and routing rules | |
| US11716261B2 (en) | Systems and methods for external system integration | |
| US11558503B2 (en) | Dynamic message processing and aggregation of data in messaging | |
| US20190327191A1 (en) | Bot response generation with dynamically-changing website or native application | |
| AU2020229706B2 (en) | Intent-driven contact center | |
| US11620452B2 (en) | Dynamic text message processing implementing endpoint communication channel selection | |
| US20180033053A1 (en) | Method and system for facilitating communications according to interaction protocols | |
| CN113572677A (en) | System and method for automatic reply based on adaptive emotion | |
| CN114223188A (en) | System and method for managing interactive invitations | |
| CN116701606A (en) | Intelligent customer service management method, system, equipment and medium | |
| EP2929502A1 (en) | Cross-channel conversations with context aware transition between channels | |
| CN107924507B (en) | Dynamic communication routing based on consistency weighting and routing rules |
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 |