CN114996402A - Intelligent customer service information processing method and device - Google Patents

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

A kind of intelligent customer service information processing method and device

technical field

The invention relates to the technical field of intelligent customer service, in particular to a method and device for processing intelligent customer service information.

Background technique

The rise and vigorous development of Internet finance, such as Alipay, WeChat and other apps with payment functions, have had a huge impact on traditional banking and other financial service industries. Among them, intelligent customer service is an innovative product launched by combining artificial intelligence and other emerging technologies. However, the current performance of intelligent customer service provided by banks is low in customer acceptance, and it is difficult to give the answer customers want. In the end, it is necessary to resort to manual customer service. Through analysis, the main reasons why intelligent customer service is not intelligent enough at present are: the analysis of users' behavior is not accurate enough; the inability to give accurate answers to customer inquiries.

SUMMARY OF THE INVENTION

In view of the problems in the prior art, the embodiments of the present invention provide a method and device for processing intelligent customer service information, which can at least partially solve the problems in the prior art.

In one aspect, the present invention provides a method for processing intelligent customer service information, including:

In response to the start trigger action of the intelligent customer service, obtain the behavior data of the executor of the start trigger action before the trigger action is started;

Determine the key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information included in the business knowledge graph;

Initiating a voice query to the start-trigger action executor according to the query information type, and in response to a response result made by the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information;

According to the business consultation information and the key information, the business knowledge graph is invoked for retrieval, the business consultation reply information is obtained, and the business consultation reply information is broadcast.

Wherein, the acquiring behavior data of the executor of the triggering action before initiating the triggering action includes:

Acquiring the behavior data of the executor of the start-triggered action in the adjacent preset period before the moment of initiating the triggering action;

Or, acquire behavior data for the adjacent preset behavior times before the start trigger action executor starts the trigger action time.

Wherein, if it is determined that abnormal information occurs in the process of processing the behavior data, the abnormal information is recorded; correspondingly, the determining of the type of inquiry information provided to the execution party of the activation trigger action according to the key information further includes:

The type of information is inquired about the abnormality of the abnormal information.

Wherein, the embedded code is pre-mounted on the main page of each module, the switching event of each function of the page, and the click event of the page function; correspondingly, the acquiring behavior data of the executor of the activation trigger action before activation of the trigger action includes:

Call the buried code to obtain behavior data of the executor of the trigger action before starting the trigger action.

In one aspect, the present invention provides an intelligent customer service information processing device, comprising:

The acquiring unit is used to respond to the start trigger action of the intelligent customer service, and obtain the behavior data of the executor of the start trigger action before the trigger action is started;

a determining unit, configured to determine key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information contained in the business knowledge graph information;

A parsing unit, configured to initiate a voice query to the start-trigger action executor according to the query information type, respond to a response result made by the start-trigger action executor to the voice query, and parse the response result to obtain service consultation information ;

The broadcasting unit is configured to call the business knowledge graph for retrieval according to the business consultation information and the key information, obtain business consultation reply information, and broadcast the business consultation reply information.

Wherein, the obtaining unit is specifically used for:

Acquiring the behavior data of the executor of the start-triggered action in the adjacent preset period before the moment of initiating the triggering action;

Or, acquire behavior data for the adjacent preset behavior times before the start trigger action executor starts the trigger action time.

Wherein, if it is determined that abnormal information occurs in the process of processing the behavior data, the abnormal information is recorded; correspondingly, the determining unit further includes:

The type of information is inquired about the abnormality of the abnormal information.

Among them, the embedded code is pre-mounted on the main page of each module, the switching event of each function of the page, and the click event of the page function; correspondingly, the acquisition unit is specifically used for:

Call the buried code to obtain behavior data of the executor of the trigger action 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 on the memory and running on the processor, where the processor implements the following method when executing the computer program:

In response to the start trigger action of the intelligent customer service, obtain the behavior data of the executor of the start trigger action before the trigger action is started;

Determine the key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information included in the business knowledge graph;

Initiating a voice query to the start-trigger action executor according to the query information type, and in response to a response result made by the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information;

According to the business consultation information and the key information, the business knowledge graph is invoked for retrieval, the business consultation reply information is obtained, and the business consultation reply information is broadcast.

An embodiment of the present invention provides a computer-readable storage medium, including:

The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the following methods are implemented:

In response to the start trigger action of the intelligent customer service, obtain the behavior data of the executor of the start trigger action before the trigger action is started;

Determine the key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information included in the business knowledge graph;

Initiating a voice query to the start-trigger action executor according to the query information type, and in response to a response result made by the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information;

According to the business consultation information and the key information, the business knowledge graph is invoked for retrieval, the business consultation reply information is obtained, and the business consultation reply information is broadcast.

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 following method is implemented:

In response to the start trigger action of the intelligent customer service, obtain the behavior data of the executor of the start trigger action before the trigger action is started;

Determine the key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information included in the business knowledge graph;

Initiating a voice query to the start-trigger action executor according to the query information type, and in response to a response result made by the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information;

According to the business consultation information and the key information, the business knowledge graph is invoked for retrieval, the business consultation reply information is obtained, and the business consultation reply information is broadcast.

The intelligent customer service information processing method and device provided by the embodiments of the present invention, in response to the start trigger action of the smart customer service, obtain the behavior data of the executor of the start trigger action before the trigger action is started; determine the key information corresponding to the behavior data, according to The key information determines the type of query information provided to the start-trigger action executor; the key information is business information included in the business knowledge graph; according to the query information type, a voice is sent to the start-trigger action executor query, in response to the response result made by the start trigger action executor to the voice query, parse the response result to obtain business consultation information; according to the business consultation information and the key information, call the business knowledge graph for retrieval, and obtain The business consultation reply information and the broadcast of the business consultation reply information can improve the accuracy of the business knowledge inquiry and improve the intelligence of the intelligent customer service.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts. In the attached image:

FIG. 1 is a schematic flowchart of a method for processing intelligent customer service information according to an embodiment of the present invention.

FIG. 2 is a schematic flowchart of a method for processing intelligent customer service information provided by another embodiment of the present invention.

FIG. 3 is a schematic flowchart of a method for processing intelligent customer service information provided by another embodiment of the present invention.

FIG. 4 is a schematic structural diagram of a smart customer service information processing apparatus according to an embodiment of the present invention.

FIG. 5 is a schematic diagram of a physical structure of a computer device according to an embodiment of the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention more clearly understood, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but not to limit the present invention. It should be noted that, the embodiments in the present application and the features in the embodiments may be arbitrarily combined with each other if there is no conflict.

FIG. 1 is a schematic flowchart of a method for processing intelligent customer service information provided by an embodiment of the present invention. As shown in FIG. 1 , the method for processing intelligent customer service information provided by an embodiment of the present invention includes:

Step S1: In response to the start-trigger action of the intelligent customer service, the behavior data of the executor of the start-trigger action before the start-trigger action is acquired.

Step S2: Determine the key information corresponding to the behavior data, and determine the type of query information provided to the start trigger action executor according to the key information; the key information is the business information included in the business knowledge graph.

Step S3: Initiating a voice query to the start-trigger action executor according to the query information type, and in response to a response result of the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information.

Step S4: According to the business consultation information and the key information, the business knowledge graph is invoked for retrieval to obtain business consultation reply information, and the business consultation reply information is broadcast.

In the above step S1, the device responds to the activation trigger action of the intelligent customer service, and obtains the behavior data of the executor of the activation trigger action before the activation of the trigger action. The apparatus may be a computer device or the like that executes the method, such as a server. The acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. The executor of the start trigger action may be a customer, and the start trigger action may be a click action initiated by the customer-triggered click smart customer service.

The behavior data before the trigger action is initiated may include click operations on web pages, input content items, and the like.

The acquiring behavior data of the executor of the start trigger action before the start of the trigger action includes:

Obtain the behavior data of the executor of the start-trigger action in the adjacent preset time period before the moment when the trigger action is started; the preset time period can be set independently according to the actual situation, and can be selected as 5 minutes. For example, when the trigger action time is 10:00, the behavior data in the adjacent preset time period is the behavior data between 9:55 and 10:00.

Or, acquire behavior data for the adjacent preset behavior times before the start trigger action executor starts the trigger action time. The preset number of actions can be set independently according to the actual situation, and it can be selected as 5 times. For example, when the trigger action time is 10 o'clock, the behavior data in the adjacent preset behavior times is the behavior data of the previous 5 behaviors from 10 o'clock.

The embedded code is pre-mounted on the main page of each module, the switching event of each function of the page, and the click event of the page function; correspondingly, the acquisition of the behavior data of the executor of the activation trigger action before the activation of the trigger action includes:

Call the buried code to obtain behavior data of the executor of the trigger action before starting the trigger action.

That is: 1. Mount the main page of each module, the switching event of each function of the page, and the click event of the page function to the embedded code.

2. Use the embedded code to represent the customer's click behavior, and transmit it to the data collection server through the plug-in, so as to obtain the customer's behavior data before clicking on the intelligent customer service.

In the above step S2, the device determines the key information corresponding to the behavior data, and determines the type of inquiry information provided to the initiator of the trigger action according to the key information; the key information is included in the business knowledge graph business information. For example, if the user's behavior data is clicking on the webpage of the fund income ranking list, the key information is fund business information, and the type of inquiry information may include fund product recommendation, fund purchase FAQs and their answers.

The business knowledge graph can be obtained in the following ways:

3. Obtain the information text of each business module of the bank, perform knowledge extraction on business information, and obtain multiple entities, the attributes of each entity, and the relationship between the entities, based on multiple entities, the attributes of each entity, and the relationship between each entity The relationship between each business module and the banking business knowledge map is obtained.

If it is determined that abnormal information occurs in the process of processing the behavior data, the abnormal information is recorded; correspondingly, determining the type of inquiry information provided to the execution party of the activation trigger action according to the key information further includes:

The type of information is inquired about the abnormality of the abnormal information.

For example, when a customer has a webpage display error during the check-in process, the webpage display error will be recorded, and the type of information inquired includes abnormal webpage display.

In the above step S3, the device initiates a voice query to the start-trigger action executor according to the query information type, responds to the response result made by the start-trigger action executor to the voice query, and parses the response result to obtain the service Consulting Information. Referring to the above example, you can ask the customer "Do you want to know about fund products?" and "Have you encountered the problem of abnormal display of the webpage?"

Referring to the above example, if the customer responds to "Do you want to know about fund products?" with a result of no, but responds to "Have you encountered a problem that the webpage is displayed abnormally?" The result of the response is yes, it can be parsed to obtain The web page displays business consulting information for unusual problems.

In the above step S4, the device invokes the business knowledge graph for retrieval according to the business consultation information and the key information, obtains business consultation reply information, and broadcasts the business consultation reply information. According to the fund business information and the business consultation information of abnormal problems displayed on the webpage, the business knowledge graph is called for retrieval, and the business consultation reply information is obtained, which may specifically include the operation steps to solve the abnormal access of the fund webpage, and broadcast the operation steps.

Refer to the instructions above:

4. Behavioral data is used to predict the business areas that the customer wants to consult when the customer first enters the intelligent customer service, and ask the customer. In the follow-up intelligent question-and-answer session, keywords are extracted from the questions asked by customers, and are retrieved in the knowledge graph of the business field with the closest similarity to obtain a candidate answer set, based on which the answer to the customer's inquiring question is determined.

The description of the method steps is shown in Figure 2.

As shown in FIG. 3 , the method of the embodiment of the present invention can be implemented based on modularization, which specifically includes:

User behavior data collection module 1:

All customer-facing pages of the bank are covered with embedded code (a piece of js code), and the click and jump behavior of customers will be collected and sent to the data collection server. According to the data of each module, you can collect the behavior of which business module field each behavior is. If there is an error thrown in the background during processing, it will also be collected and uploaded to the data collection server.

Banking business module knowledge collection and processing module 2:

Generally, the acquired knowledge of each business module is stored in the form of text. It is necessary to extract the knowledge text of each business module to obtain multiple entities, the attributes of each entity, and the relationship between each entity.

Banking Business Module Knowledge Modeling Module 3:

Based on the extracted entities, attributes of entities, and relationships between entities, a knowledge graph including banking business domain information is obtained. The knowledge graph is stored in the Neo4j graph database; the nodes in the Neo4j graph database represent the entities of the business knowledge, and the edges in the Neo4j graph database represent the relationships between the business knowledge.

Q&A business domain prediction module 4:

After the customer enters the intelligent customer service, according to the business field that the behavior data has appeared in the last 5 times, the customer will take the initiative to ask the customer whether to consult relevant information in this field; if the interface is abnormal in the past 5 times, the customer will also be asked together. After the customer can click, enter the following Smart question and answer session.

Smart Q&A Module 5:

Based on the problems stated by the customer and the choices made by the customer. Retrieve in the business knowledge graph, get the answer triples (entity, attribute, relationship) of the candidate question, and determine the answer corresponding to the question asked by the customer.

The intelligent customer service information processing method provided by the embodiment of the present invention, in response to the start trigger action of the intelligent customer service, obtains the behavior data of the executor of the start trigger action before the trigger action is started; determines the key information corresponding to the behavior data, according to the The key information determines the type of query information provided to the start-trigger action executor; the key information is business information included in the business knowledge graph; according to the query information type, a voice query is initiated to the start-trigger action executor, In response to the response result made by the start-trigger action executor to the voice inquiry, analyze the response result to obtain business consultation information; according to the business consultation information and the key information, call the business knowledge graph for retrieval, and obtain the business consultation Replying to the information and broadcasting the business consultation reply information can improve the accuracy of the business knowledge inquiry and improve the intelligence of the intelligent customer service.

Further, the acquiring behavior data of the executor of the triggering action before initiating the triggering action includes:

The behavior data of the executor of the start-trigger action within a preset time period adjacent to the moment when the start-trigger action is started is obtained; the above description can be referred to, and details are not repeated here.

Or, acquire behavior data for the adjacent preset behavior times before the start trigger action executor starts the trigger action time. The above description may be referred to, and details are not repeated here.

Further, if it is determined that abnormal information occurs in the process of processing the behavior data, the abnormal information is recorded; correspondingly, the determination of the type of inquiry information provided to the start trigger action executor according to the key information further includes: :

The type of information is inquired about the abnormality of the abnormal information. The above description may be referred to, and details are not repeated here.

Further, the embedded code is pre-mounted on the main page of each module, the switching event of each function of the page, and the click event of the page function; correspondingly, the acquisition of the behavior data of the executor of the triggering action before the triggering action is started, including :

Call the buried code to obtain behavior data of the executor of the trigger action before starting the trigger action. The above description may be referred to, and details are not repeated here.

It should be noted that the intelligent customer service information processing method provided by the embodiment of the present invention can be used in the financial field, and can also be used in any technical field except the financial field, and the embodiment of the present invention does not limit the application field of the intelligent customer service information processing method .

FIG. 4 is a schematic structural diagram of a smart customer service information processing apparatus provided by an embodiment of the present invention. As shown in FIG. 4 , the smart customer service information processing apparatus provided by an embodiment of the present invention includes an acquisition unit 401, a determination unit 402, an analysis unit 403 and a The broadcasting unit 404, wherein:

The obtaining unit 401 is used to respond to the start trigger action of the intelligent customer service, and obtain the behavior data of the executor of the start trigger action before starting the trigger action; the determining unit 402 is used to determine the key information corresponding to the behavior data, according to the key information Determine the type of query information provided to the start-trigger action executor; the key information is the business information included in the business knowledge graph; the parsing unit 403 is configured to initiate a request to the start-trigger action executor according to the query information type Voice query, in response to the response result made by the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information; the broadcasting unit 404 is configured to call the service according to the service consultation information and the key information The knowledge graph is retrieved to obtain business consultation reply information, and the business consultation reply information is broadcast.

Specifically, the obtaining unit 401 in the device is used to respond to the start trigger action of the intelligent customer service, and obtain the behavior data of the executor of the start trigger action before the trigger action is started; the determination unit 402 is used to determine the key information corresponding to the behavior data , according to the key information to determine the type of query information provided to the start trigger action executor; the key information is the business information contained in the business knowledge graph; the parsing unit 403 is configured to send the query information type to the The start trigger action executor initiates a voice query, and in response to the response result made by the start trigger action executor to the voice query, parses the response result to obtain service consultation information; the broadcasting unit 404 is configured to obtain service consultation information according to the service consultation information and all The key information is described, the business knowledge graph is called for retrieval, the business consultation reply information is obtained, and the business consultation reply information is broadcast.

The smart customer service information processing device provided by the embodiment of the present invention responds to the start trigger action of the smart customer service, obtains the behavior data of the executor of the start trigger action before the trigger action is started; determines the key information corresponding to the behavior data, according to the The key information determines the type of query information provided to the start-trigger action executor; the key information is business information included in the business knowledge graph; according to the query information type, a voice query is initiated to the start-trigger action executor, In response to the response result made by the start-trigger action executor to the voice inquiry, analyze the response result to obtain business consultation information; according to the business consultation information and the key information, call the business knowledge graph for retrieval, and obtain the business consultation Replying to the information and broadcasting the business consultation reply information can improve the accuracy of the business knowledge inquiry and improve the intelligence of the intelligent customer service.

Further, the obtaining unit 401 is specifically used for:

Acquiring the behavior data of the executor of the start-triggered action in the adjacent preset period before the moment of initiating the triggering action;

Or, acquire behavior data for the adjacent preset behavior times before the start trigger action executor starts the trigger action time.

Further, if it is determined that abnormal information occurs in the process of processing the behavior data, the abnormal information is recorded; correspondingly, the determining unit 402 further includes:

The type of information is inquired about the abnormality of the abnormal information.

Further, the embedded code is mounted on the main page of each module, the switching event of each function of the page, and the click event of the page function in advance; correspondingly, the obtaining unit 401 is specifically used for:

Call the buried code to obtain behavior data of the executor of the trigger action before starting the trigger action.

The embodiments of the smart customer service information processing apparatus provided by the embodiments of the present invention may be specifically used to execute the processing procedures of the above method embodiments, and the functions thereof will not be repeated here, and reference may be made to the detailed descriptions of the above method embodiments.

FIG. 5 is a schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention. As shown in FIG. 5 , the computer device includes: a memory 501 , a processor 502 , and a computer program stored in the memory 501 and running on the processor 502 , the processor 502 implements the following methods when executing the computer program:

In response to the start trigger action of the intelligent customer service, obtain the behavior data of the executor of the start trigger action before the trigger action is started;

Determine the key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information included in the business knowledge graph;

Initiating a voice query to the start-trigger action executor according to the query information type, and in response to a response result made by the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information;

According to the business consultation information and the key information, the business knowledge graph is invoked for retrieval, the business consultation reply information is obtained, and the business consultation reply information is broadcast.

This embodiment discloses a computer program product, the computer program product includes a computer program, and the computer program implements the following method when executed by a processor:

In response to the start trigger action of the intelligent customer service, obtain the behavior data of the executor of the start trigger action before the trigger action is started;

Determine the key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information included in the business knowledge graph;

Initiating a voice query to the start-trigger action executor according to the query information type, and in response to a response result made by the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information;

According to the business consultation information and the key information, the business knowledge graph is invoked for retrieval, the business consultation reply information is obtained, and the business consultation reply information is broadcast.

This embodiment provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method is implemented:

In response to the start trigger action of the intelligent customer service, obtain the behavior data of the executor of the start trigger action before the trigger action is started;

Determine the key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information included in the business knowledge graph;

Initiating a voice query to the start-trigger action executor according to the query information type, and in response to a response result made by the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information;

According to the business consultation information and the key information, the business knowledge graph is invoked for retrieval, the business consultation reply information is obtained, and the business consultation reply information is broadcast.

Compared with the technical solutions in the prior art, the embodiment of the present invention acquires the behavior data of the executor of the initiation trigger action before initiating the trigger action in response to the initiation trigger action of the intelligent customer service; determines the key information corresponding to the action data, Determine the type of query information provided to the start-trigger action executor according to the key information; the key information is the business information included in the business knowledge graph; initiate a trigger to the start-trigger action executor according to the query information type Voice query, in response to the response result made by the start-trigger action executor to the voice query, parse the response result to obtain business consultation information; according to the business consultation information and the key information, call the business knowledge graph for retrieval, Obtaining business consultation reply information and broadcasting the business consultation reply information can improve the accuracy of business knowledge inquiry and improve the intelligence of intelligent customer service.

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, etc.) 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 in 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 the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

In the description of this specification, reference to the terms "one embodiment", "one specific embodiment", "some embodiments", "for example", "example", "specific example", or "some examples", etc. Indicates 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 present invention. In this specification, schematic representations of the above terms 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 specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above-mentioned specific embodiments are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (11)

1. an intelligent customer service information processing method, is characterized in that, comprises: In response to the start trigger action of the intelligent customer service, obtain the behavior data of the executor of the start trigger action before the trigger action is started; Determine the key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information included in the business knowledge graph; Initiating a voice query to the start-trigger action executor according to the query information type, and in response to a response result made by the start-trigger action executor to the voice query, parsing the response result to obtain service consultation information; According to the business consultation information and the key information, the business knowledge graph is invoked for retrieval, the business consultation reply information is obtained, and the business consultation reply information is broadcast. 2 . The method for processing intelligent customer service information according to claim 1 , wherein the acquiring behavior data of an executor of a triggering action before initiating the triggering action comprises: 2 . Acquiring the behavior data of the executor of the start-triggered action in the adjacent preset period before the moment of initiating the triggering action; Or, acquire behavior data for the adjacent preset behavior times before the start trigger action executor starts the trigger action time. 3. The intelligent customer service information processing method according to claim 1, characterized in that, if it is determined that abnormal information occurs in the process of processing the behavior data, the abnormal information is recorded; correspondingly, according to the key information Determining the type of query information provided to the start-triggering action executor further includes: The type of information is inquired about the abnormality of the abnormal information. 4. The intelligent customer service information processing method according to claim 1, wherein the embedded code is mounted in advance on the main page of each module, the switching event of each function of the page, and the click event of the page function; Get the behavior data of the executor before the trigger action is started, including: Call the buried code to obtain behavior data of the executor of the trigger action before starting the trigger action. 5. An intelligent customer service information processing device, characterized in that, comprising: The acquiring unit is used to respond to the start trigger action of the intelligent customer service, and obtain the behavior data of the executor of the start trigger action before the trigger action is started; a determining unit, configured to determine key information corresponding to the behavior data, and determine the type of inquiry information provided to the start trigger action executor according to the key information; the key information is the business information contained in the business knowledge graph information; A parsing unit, configured to initiate a voice query to the start-trigger action executor according to the query information type, respond to a response result made by the start-trigger action executor to the voice query, and parse the response result to obtain service consultation information ; The broadcasting unit is configured to call the business knowledge graph for retrieval according to the business consultation information and the key information, obtain business consultation reply information, and broadcast the business consultation reply information. 6. The intelligent customer service information processing device according to claim 5, wherein the acquisition unit is specifically used for: Acquiring the behavior data of the executor of the start-triggered action in the adjacent preset period before the moment of initiating the triggering action; Or, acquire behavior data for the adjacent preset behavior times before the start trigger action executor starts the trigger action time. 7. The intelligent customer service information processing device according to claim 5, wherein if it is determined that abnormal information occurs in the process of processing the behavior data, the abnormal information is recorded; correspondingly, the determining unit further comprises: The type of information is inquired about the abnormality of the abnormal information. 8 . The intelligent customer service information processing device according to claim 5 , wherein the embedded code is previously mounted on the main page of each module, the switching event of each function of the page, and the click event of the page function; correspondingly, the described The acquisition unit is specifically used for: Call the buried code to obtain behavior data of the executor of the trigger action before starting the trigger action. 9. A computer device comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements any of claims 1 to 4 when the processor executes the computer program the method. 10. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method of any one of claims 1 to 4 is implemented. 11. A computer program product, characterized in that the computer program product comprises a computer program, which implements the method of any one of claims 1 to 4 when the computer program is executed by a processor.

Images