CN114996402A - Intelligent customer service information processing method and device - Google Patents
Intelligent customer service information processing method and device Download PDFInfo
- Publication number
- CN114996402A CN114996402A CN202210615175.8A CN202210615175A CN114996402A CN 114996402 A CN114996402 A CN 114996402A CN 202210615175 A CN202210615175 A CN 202210615175A CN 114996402 A CN114996402 A CN 114996402A
- Authority
- CN
- China
- Prior art keywords
- information
- starting
- service
- trigger action
- behavior data
- 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
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an intelligent customer service information processing method and device, relates to the technical field of intelligent customer service, and can be used in the financial field or other technical fields. The method comprises the following steps: responding to a starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action; determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information; and calling a service knowledge graph to retrieve according to the service consultation information and the key information to obtain service consultation reply information. The device performs the above method. The method and the device provided by the embodiment of the invention can improve the intelligence of intelligent customer service.
Description
Technical Field
The invention relates to the technical field of intelligent customer service, in particular to an intelligent customer service information processing method and device.
Background
The rise and the explosion of the app with the payment function, such as the payment treasure and the WeChat, of the Internet finance generate huge impact on the traditional financial service industries, such as banks and the like. The intelligent customer service is an innovative product launched by combining with emerging technologies such as artificial intelligence, but the intelligent customer service performance provided by the current bank is low in customer acceptance, difficult to give a response desired by a customer, and finally still has to help the artificial customer service. Through analysis, the main reasons for generating the intelligence insufficient for the intelligent customer service at present are: the analysis of the user's behavior is not accurate enough; no accurate response can be given to the client consultation.
Disclosure of Invention
To solve the problems in the prior art, embodiments of the present invention provide an intelligent customer service information processing method and apparatus, which can at least partially solve the problems in the prior art.
In one aspect, the present invention provides an intelligent customer service information processing method, including:
responding to a starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action;
determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph;
initiating a voice query to the start triggering action executing party according to the query information type, responding to a response result of the start triggering action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information;
and calling a service knowledge graph for retrieval according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information.
The acquiring behavior data of the starting triggering action executing party before starting the triggering action includes:
acquiring behavior data of a trigger action starting executing party in an adjacent preset time period before a trigger action starting moment;
or acquiring the behavior data of the starting triggering action executing party within the adjacent preset behavior times before the moment of starting the triggering action.
If abnormal information is determined to occur in the process of processing the behavior data, recording the abnormal information; correspondingly, the determining the type of the query information provided to the start triggering action executing party according to the key information further includes:
an exception query information type for the exception information.
The method comprises the following steps that a main page of each module, a switching event of each function of the page and a click event mounting and embedding point codes of the page function are pre-loaded; correspondingly, the acquiring behavior data of the starting trigger action executor before the starting trigger action includes:
and calling the embedded point code to acquire behavior data of a starting trigger action executing party before starting the trigger action.
In one aspect, the present invention provides an intelligent customer service information processing apparatus, including:
the acquisition unit is used for responding to the starting triggering action of the intelligent customer service and acquiring behavior data of a starting triggering action executor before the starting triggering action;
the determining unit is used for determining key information corresponding to the behavior data and determining the type of inquiry information provided for the starting triggering action executing party according to the key information; the key information is service information contained in a service knowledge graph;
the analysis unit is used for initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information;
and the broadcasting unit is used for calling the service knowledge graph to search according to the service consultation information and the key information to obtain service consultation response information and broadcasting the service consultation response information.
Wherein the obtaining unit is specifically configured to:
acquiring behavior data of a trigger action starting executing party in an adjacent preset time period before a trigger action starting moment;
or acquiring the behavior data of the starting triggering action executing party within the adjacent preset behavior times before the moment of starting the triggering action.
If abnormal information is determined to occur in the process of processing the behavior data, recording the abnormal information; correspondingly, the determining unit further includes:
an exception query information type for the exception information.
The method comprises the following steps that a main page of each module, a switching event of each function of the page and a click event mounting and embedding point codes of the page function are pre-loaded; correspondingly, the obtaining unit is specifically configured to:
and calling the embedded point code to acquire behavior data of a starting trigger action executing party before starting the trigger action.
In another aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the following method when executing the computer program:
responding to a starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action;
determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph;
initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information;
and calling a service knowledge graph for retrieval according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information.
An embodiment of the present invention provides a computer-readable storage medium, including:
the computer-readable storage medium stores a computer program which, when executed by a processor, implements a method comprising:
responding to a starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action;
determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph;
initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information;
and calling a service knowledge graph to search according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the following method:
responding to a starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action;
determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph;
initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information;
and calling a service knowledge graph to search according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information.
The intelligent customer service information processing method and device provided by the embodiment of the invention respond to the starting triggering action of the intelligent customer service and acquire the behavior data of a starting triggering action executor before the starting triggering action; determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph; initiating a voice query to the start triggering action executing party according to the query information type, responding to a response result of the start triggering action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information; and calling a service knowledge graph to retrieve according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information, so that the accuracy of inquiring the service knowledge can be improved, and the intelligence of intelligent customer service is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a schematic flow chart of an intelligent customer service information processing method according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of an intelligent customer service information processing method according to another embodiment of the present invention.
Fig. 3 is a flowchart illustrating an intelligent customer service information processing method according to another embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an intelligent customer service information processing apparatus according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
Fig. 1 is a schematic flow chart of an intelligent customer service information processing method according to an embodiment of the present invention, and as shown in fig. 1, the intelligent customer service information processing method according to the embodiment of the present invention includes:
step S1: and responding to the starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action.
Step S2: determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph.
Step S3: and initiating a voice inquiry to the starting trigger action executing party according to the type of the inquiry information, responding to a response result of the starting trigger action executing party aiming at the voice inquiry, and analyzing the response result to obtain service inquiry information.
Step S4: and calling a service knowledge graph for retrieval according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information.
In step S1, the device acquires behavior data of the start trigger executor before the start trigger in response to the start trigger of the smart customer service. The apparatus may be a computer device or the like, e.g. a server, performing the method. According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations. The starting triggering action executor can be a client, and the starting triggering action can be a clicking action triggered by the client and started by the intelligent customer service.
The behavior data prior to initiating the trigger action may include a click operation on a web page, an entry of a content item, and so on.
The acquiring of the behavior data of the starting trigger action executor before the starting trigger action includes:
acquiring behavior data of a trigger action starting executing party in an adjacent preset time period before a trigger action starting moment; the preset time period can be set independently according to actual conditions, and can be selected to be 5 minutes. For example, the time when the trigger action is started is 10 o 'clock, the behavior data in the adjacent preset time period is the behavior data between 9 o' clock 55 o 'clock and 10 o' clock.
Or acquiring the behavior data of the starting triggering action executing party within the adjacent preset behavior times before the moment of starting the triggering action. The preset action times can be set independently according to actual conditions and can be selected as 5 times. For example, when the trigger operation starting time is 10 o 'clock, the behavior data in the adjacent preset behavior frequency is the behavior data of the previous 5 times of behaviors counted from 10 o' clock.
Embedding point codes in a main page of each module, switching events of each function of the page and clicking events of the page function in advance; correspondingly, the acquiring behavior data of the starting triggering action executing party before the starting triggering action includes:
and calling the embedded point code to acquire behavior data of a starting trigger action executing party before starting the trigger action.
Namely: 1. and mounting the embedded point codes on the main page of each module, the switching event of each function of the page and the clicking event of the page function.
2. And representing the clicking behavior of the client by using a buried point code, and transmitting the clicking behavior to a data acquisition server through a plug-in so as to obtain behavior data of the client before clicking intelligent customer service.
In the above step S2, the apparatus determines the key information corresponding to the behavior data, and determines the type of inquiry information provided to the start triggering action executor according to the key information; the key information is service information contained in a service knowledge graph. For example, if the behavior data of the user is a webpage on which a fund income ranking list is clicked, the key information is fund service information, and the inquiry information types may include fund product recommendation, fund purchase common questions and answers thereof.
The business knowledge graph can be obtained by the following method:
3. acquiring information texts of all business modules of a bank, extracting knowledge of business information to obtain a plurality of entities, attributes of the entities and relations among the entities, and obtaining a bank business knowledge map of each business module based on the entities, the attributes of the entities and the relations among the entities.
If the abnormal information is determined to appear in the process of processing the behavior data, recording the abnormal information; correspondingly, the determining the type of the query information provided to the start triggering action executing party according to the key information further includes:
an exception query information type for the exception information.
For example, if a webpage display error occurs in the webpage punching process of the client, the webpage display error is recorded, and the query information type further comprises webpage display abnormality.
In the step S3, the apparatus initiates a voice query to the start trigger action executor according to the query information type, responds to a response result of the start trigger action executor to the voice query, and parses the response result to obtain service query information. Referring to the example above, a customer may be initiated "do you want to know about a fund product? "and" do you encounter a problem with web page display anomalies? "
Referring to the example above, if the customer is directed to "do you want to know about the fund product? "does the response result not, but is for" do you encounter a problem with web page display anomalies? If the response result is yes, the business consultation information aiming at the webpage display abnormal problem can be analyzed.
In the step S4, the apparatus calls the service knowledge map to perform retrieval according to the service consultation information and the key information, so as to obtain service consultation response information, and broadcasts the service consultation response information. And calling the service knowledge graph to search according to the fund service information and the service consultation information of the webpage display abnormal problem to obtain service consultation reply information, and specifically, the method can comprise an operation step of solving the fund webpage access abnormity and broadcasting the operation step.
With reference to the above description:
4. the behavior data is used for predicting the business field which the client wants to consult and inquiring the client when the client just enters the intelligent customer service. In a subsequent intelligent question-answering link, keyword extraction is carried out on questions asked by a client, retrieval is carried out in a knowledge graph of a service field with the closest similarity, a candidate answer set is obtained, and answers of the questions consulted by the client are determined based on the candidate answer set.
The method steps are illustrated in figure 2.
As shown in fig. 3, the method of the embodiment of the present invention may be implemented based on modularization, which specifically includes:
the user behavior data acquisition module 1:
and (3) laying a buried point code (a js code) on pages of all customers in the bank, collecting clicking and jumping behaviors of the customers, and sending the behaviors to a data collection server. And laying the bottom according to the data of each module, so that the behaviors of which business module field each walk belongs to can be collected. If the situation that the backstage throws errors in the processing process occurs, the errors are collected together and uploaded to the data collection server.
The bank business module knowledge acquisition and processing module 2:
generally, the acquired knowledge of each business module is stored in a text form, and the knowledge text of each business module needs to be extracted to obtain a plurality of entities, the attributes of each entity and the relationship among the entities.
The bank business module knowledge modeling module 3:
and obtaining a knowledge graph comprising information of the banking field based on the extracted entities, the attributes of the entities and the relationship among the entities. Storing the knowledge graph in a Neo4j graph database; and representing the entities of the business knowledge by using nodes in the Neo4j graph database, and representing the relation between the business knowledge by using edges in the Neo4j graph database.
Question answering service field prediction module 4:
after entering the intelligent customer service, the client actively inquires whether the client consults related information in the field or not according to the business field of which the behavior data appears for the last 5 times; and the client is also inquired when the interface abnormality occurs in 5 times, and the client can enter a subsequent intelligent question-answering link after clicking.
Intelligent question-answering module 5:
based on the questions stated by the customer, and the selections made by the customer. And searching in the service knowledge graph to obtain answer triples (entities, attributes and relations) of the question candidates, and determining answers corresponding to the questions consulted by the client.
The intelligent customer service information processing method provided by the embodiment of the invention responds to the starting triggering action of the intelligent customer service, and obtains the behavior data of a starting triggering action executor before the starting triggering action; determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph; initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information; and calling a service knowledge graph to retrieve according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information, so that the accuracy of service knowledge inquiry can be improved, and the intelligence of intelligent customer service is improved.
Further, the acquiring behavior data of the starting triggering action executing party before the starting triggering action includes:
acquiring behavior data of a trigger action starting executing party in an adjacent preset time period before a trigger action starting moment; reference is made to the above description and no further description is made.
Or acquiring the behavior data of the starting triggering action executing party within the adjacent preset behavior times before the moment of starting the triggering action. Reference is made to the above description and no further description is made.
Further, if abnormal information is determined to occur in the process of processing the behavior data, recording the abnormal information; correspondingly, the determining the type of the query information provided to the start triggering action executing party according to the key information further includes:
an exception query information type for the exception information. Reference is made to the above description and no further description is made.
Furthermore, embedding point codes in a main page of each module, switching events of each function of the page and clicking events of the functions of the page in advance; correspondingly, the acquiring behavior data of the starting triggering action executing party before the starting triggering action includes:
and calling the embedded point code to acquire behavior data of a starting trigger action executing party before starting the trigger action. Reference is made to the above description and no further description is made.
It should be noted that the intelligent customer service information processing method provided by the embodiment of the present invention may be used in the financial field, and may also be used in any technical field other than the financial field.
Fig. 4 is a schematic structural diagram of an intelligent customer service information processing apparatus according to an embodiment of the present invention, and as shown in fig. 4, the intelligent customer service information processing apparatus according to the embodiment of the present invention includes an obtaining unit 401, a determining unit 402, an analyzing unit 403, and a broadcasting unit 404, where:
the acquiring unit 401 is configured to respond to a start trigger action of the intelligent customer service, and acquire behavior data of a start trigger action executor before the start trigger action; the determining unit 402 is configured to determine key information corresponding to the behavior data, and determine a type of query information provided to the start triggering action executor according to the key information; the key information is service information contained in a service knowledge graph; the analyzing unit 403 is configured to initiate a voice query to the start trigger action executor according to the query information type, respond to a response result of the start trigger action executor to the voice query, and analyze the response result to obtain service consultation information; the broadcasting unit 404 is configured to call a service knowledge graph to perform retrieval according to the service consultation information and the key information, obtain service consultation response information, and broadcast the service consultation response information.
Specifically, the obtaining unit 401 in the device is configured to obtain, in response to a start trigger action of the intelligent customer service, behavior data of a start trigger action executor before the start trigger action; the determining unit 402 is configured to determine key information corresponding to the behavior data, and determine, according to the key information, a type of query information provided to the start triggering action executor; the key information is service information contained in a service knowledge graph; the analyzing unit 403 is configured to initiate a voice query to the start trigger action executor according to the query information type, respond to a response result of the start trigger action executor to the voice query, and analyze the response result to obtain service consultation information; the broadcasting unit 404 is configured to call a service knowledge graph to perform retrieval according to the service consultation information and the key information, obtain service consultation response information, and broadcast the service consultation response information.
The intelligent customer service information processing device provided by the embodiment of the invention responds to the starting triggering action of the intelligent customer service and acquires the behavior data of a starting triggering action executor before the starting triggering action; determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph; initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information; and calling a service knowledge graph to retrieve according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information, so that the accuracy of inquiring the service knowledge can be improved, and the intelligence of intelligent customer service is improved.
Further, the obtaining unit 401 is specifically configured to:
acquiring behavior data of a trigger action starting executing party in an adjacent preset time period before a trigger action starting moment;
or acquiring the behavior data of the starting triggering action executing party within the adjacent preset behavior times before the moment of starting the triggering action.
Further, if abnormal information is determined to occur in the process of processing the behavior data, recording the abnormal information; correspondingly, the determining unit 402 further includes:
an exception query information type for the exception information.
Further, embedding point codes in a main page of each module, switching events of each function of the page and clicking events of the functions of the page in advance; correspondingly, the obtaining unit 401 is specifically configured to:
and calling the buried point code to acquire behavior data of a starting trigger action executor before starting the trigger action.
The embodiment of the intelligent customer service information processing apparatus provided in the embodiment of the present invention may be specifically configured to execute the processing flows of the above method embodiments, and the functions of the embodiment are not described herein again, and reference may be made to the detailed description of the method embodiments.
Fig. 5 is a schematic structural diagram of a computer device provided in an embodiment of the present invention, and as shown in fig. 5, the computer device includes: a memory 501, a processor 502 and a computer program stored on the memory 501 and executable on the processor 502, the processor 502 implementing the following method when executing the computer program:
responding to a starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action;
determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph;
initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information;
and calling a service knowledge graph for retrieval according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information.
The present embodiment discloses a computer program product comprising a computer program which, when executed by a processor, implements the method of:
responding to a starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action;
determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph;
initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information;
and calling a service knowledge graph for retrieval according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information.
The present embodiments provide a computer-readable storage medium storing a computer program which, when executed by a processor, implements a method of:
responding to a starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action;
determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph;
initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information;
and calling a service knowledge graph for retrieval according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information.
Compared with the technical scheme in the prior art, the embodiment of the invention responds to the starting triggering action of the intelligent customer service and acquires the behavior data of the starting triggering action executor before the starting triggering action; determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph; initiating a voice query to the start triggering action executing party according to the query information type, responding to a response result of the start triggering action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information; and calling a service knowledge graph to retrieve according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information, so that the accuracy of service knowledge inquiry can be improved, and the intelligence of intelligent customer service is improved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description herein, reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and should not be used to limit the scope of the present 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 (11)
1. An intelligent customer service information processing method is characterized by comprising the following steps:
responding to a starting trigger action of the intelligent customer service, and acquiring behavior data of a starting trigger action executor before the starting trigger action;
determining key information corresponding to the behavior data, and determining the type of inquiry information provided for the starting triggering action executor according to the key information; the key information is service information contained in a service knowledge graph;
initiating a voice query to the starting trigger action executing party according to the query information type, responding to a response result of the starting trigger action executing party aiming at the voice query, and analyzing the response result to obtain service consultation information;
and calling a service knowledge graph for retrieval according to the service consultation information and the key information to obtain service consultation reply information, and broadcasting the service consultation reply information.
2. The intelligent customer service information processing method according to claim 1, wherein the acquiring of the behavior data of the starting triggering action executing party before the starting triggering action comprises:
acquiring behavior data of a trigger action starting executing party in an adjacent preset time period before a trigger action starting moment;
or acquiring the behavior data of the starting triggering action executing party within the adjacent preset behavior times before the moment of starting the triggering action.
3. The intelligent customer service information processing method according to claim 1, wherein if it is determined that abnormal information occurs in the course of processing the behavior data, the abnormal information is recorded; correspondingly, the determining the type of the query information provided to the start triggering action executing party according to the key information further includes:
an exception query information type for the exception information.
4. The intelligent customer service information processing method according to claim 1, wherein a point code is embedded in a home page of each module, a switching event of each function of a page, and a click event mounting of a page function in advance; correspondingly, the acquiring behavior data of the starting triggering action executing party before the starting triggering action includes:
and calling the embedded point code to acquire behavior data of a starting trigger action executing party before starting the trigger action.
5. An intelligent customer service information processing apparatus, comprising:
the acquisition unit is used for responding to the starting triggering action of the intelligent customer service and acquiring behavior data of a starting triggering action executor before the starting triggering action;
the determining unit is used for determining key information corresponding to the behavior data and determining the type of inquiry information provided for the starting triggering action executing party according to the key information; the key information is service information contained in a service knowledge graph;
the analysis unit is used for initiating a voice inquiry to the starting trigger action executing party according to the inquiry information type, responding to a response result of the starting trigger action executing party aiming at the voice inquiry, and analyzing the response result to obtain service consultation information;
and the broadcasting unit is used for calling the service knowledge graph to search according to the service consultation information and the key information to obtain service consultation response information and broadcasting the service consultation response information.
6. The intelligent customer service information processing apparatus according to claim 5, wherein the obtaining unit is specifically configured to:
acquiring behavior data of a trigger action starting executing party in an adjacent preset time period before a trigger action starting moment;
or acquiring the behavior data of the starting trigger action executing party within the adjacent preset behavior times before the moment of starting the trigger action.
7. The intelligent customer service information processing device according to claim 5, wherein if it is determined that abnormal information occurs in the course of processing the behavior data, the abnormal information is recorded; correspondingly, the determining unit further comprises:
an exception query information type for the exception information.
8. The intelligent customer service information processing device according to claim 5, wherein a point code is embedded in advance in a main page of each module, a switching event of each function of a page, and a click event mounting of a page function; correspondingly, the obtaining unit is specifically configured to:
and calling the embedded point code to acquire behavior data of a starting trigger action executing party before starting the trigger action.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 4.
11. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210615175.8A CN114996402A (en) | 2022-05-31 | 2022-05-31 | Intelligent customer service information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210615175.8A CN114996402A (en) | 2022-05-31 | 2022-05-31 | Intelligent customer service information processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114996402A true CN114996402A (en) | 2022-09-02 |
Family
ID=83030539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210615175.8A Pending CN114996402A (en) | 2022-05-31 | 2022-05-31 | Intelligent customer service information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114996402A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114387A (en) * | 2023-10-25 | 2023-11-24 | 联通在线信息科技有限公司 | Interactive customer service model building method and device, electronic equipment and storage medium |
-
2022
- 2022-05-31 CN CN202210615175.8A patent/CN114996402A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114387A (en) * | 2023-10-25 | 2023-11-24 | 联通在线信息科技有限公司 | Interactive customer service model building method and device, electronic equipment and storage medium |
| CN117114387B (en) * | 2023-10-25 | 2024-02-27 | 联通在线信息科技有限公司 | Interactive customer service model building method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6542881B1 (en) | System and method for revealing necessary and sufficient conditions for database analysis | |
| CN111078513B (en) | Log processing method, device, equipment, storage medium and log alarm system | |
| CN111506719A (en) | Associated question recommending method, device and equipment and readable storage medium | |
| US11023551B2 (en) | Document processing based on proxy logs | |
| JP6779405B1 (en) | Infringement information extraction systems, methods and programs | |
| CN112269816A (en) | Government affair appointment event correlation retrieval method | |
| CN114996402A (en) | Intelligent customer service information processing method and device | |
| CN116578499B (en) | Intelligent analysis and test method and system for public component function change influence | |
| CN113988195A (en) | Private domain traffic clue mining method and device, vehicle and readable medium | |
| US20080103882A1 (en) | Method for cost-sensitive autonomous information retrieval and extraction | |
| CN113259872A (en) | Product processing method and system for unmanned network | |
| CN117290481A (en) | Question and answer method and device based on deep learning, storage medium and electronic equipment | |
| CN112882890A (en) | Log collection method and device | |
| CN117033744A (en) | Data query method and device, storage medium and electronic equipment | |
| CN117056619A (en) | Method and device for determining user behavior characteristics | |
| CN117131083A (en) | Method and device for predicting statement execution time range, processor and electronic equipment | |
| CN116452212A (en) | Intelligent customer service commodity knowledge base information management method and system | |
| US20220109615A1 (en) | Integration navigator and intelligent monitoring for living systems | |
| CN114491102A (en) | Database monitoring method and system based on big data | |
| CN118035387B (en) | Data selecting and outputting method and device based on large language model | |
| JP6730229B2 (en) | Inquiry support device and inquiry support method | |
| CN117076449A (en) | Report retrieval method, device, terminal equipment and storage medium | |
| CN114036370A (en) | Target information generation method and device | |
| CN118779420A (en) | Method, device, equipment and storage medium for constructing question-answer knowledge base | |
| CN118093930A (en) | Audio resource retrieval method, device, equipment and storage medium |
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 |