CN113553409A - Intelligent dialogue method and device combining RPA and AI and electronic equipment - Google Patents

Intelligent dialogue method and device combining RPA and AI and electronic equipment Download PDF

Info

Publication number
CN113553409A
CN113553409A CN202110727765.5A CN202110727765A CN113553409A CN 113553409 A CN113553409 A CN 113553409A CN 202110727765 A CN202110727765 A CN 202110727765A CN 113553409 A CN113553409 A CN 113553409A
Authority
CN
China
Prior art keywords
dialogue
target
rpa system
service
conversation
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
Application number
CN202110727765.5A
Other languages
Chinese (zh)
Inventor
徐春峰
汪冠春
胡一川
褚瑞
李玮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Laiye Network Technology Co Ltd
Laiye Technology Beijing Co Ltd
Original Assignee
Beijing Laiye Network Technology Co Ltd
Laiye Technology Beijing Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Laiye Network Technology Co Ltd, Laiye Technology Beijing Co Ltd filed Critical Beijing Laiye Network Technology Co Ltd
Priority to CN202110727765.5A priority Critical patent/CN113553409A/en
Publication of CN113553409A publication Critical patent/CN113553409A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G06F40/35—Discourse or dialogue representation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Machine Translation (AREA)

Abstract

The utility model provides an intelligent dialogue method, a device and an electronic device which combine RPA and AI, relating to the technical field of artificial intelligence, and obtaining dialogue sentences of service objects from a target service channel through an RPA system; the RPA system analyzes the dialogue type of the dialogue sentence based on the natural language processing NLP to determine the target dialogue type of the dialogue sentence; the RPA system calls a dialogue service matched with the type of the target object, and the dialogue service acquires a reply dialogue based on dialogue statements; the RPA system feeds back the reply dialogue to the terminal equipment of the service object through the target service channel opening. The method has the advantages that a new consultation service channel is provided, compared with manual customer service, the method is high in efficiency and low in cost, timeliness of answering the problem can be guaranteed, and accordingly service quality is improved.

Description

Intelligent dialogue method and device combining RPA and AI and electronic equipment
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to an intelligent dialogue method and apparatus combining an RPA and an AI, and an electronic device.
Background
Robot Process Automation (RPA) is a Process task that simulates human operations on a computer by specific "robot software" and executes automatically according to rules.
Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence.
At present, when many companies or government offices face consultation, telephone consultation or message consultation is adopted, and the problem is mainly solved through manual reply, and when the traffic is large, the conditions of high pressure of workers, irregular reply technique, untimely problem solution and the like easily occur by adopting manual reply, so that the service experience degree of a user is poor.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
To this end, it is an object of the present application to propose an intelligent dialog method combining RPA and AI.
A second object of the present application is to propose an intelligent dialog device combining RPA and AI.
A third object of the present application is to provide an electronic device.
A fourth object of the present application is to propose a non-transitory computer readable storage medium.
A fifth object of the present application is to propose a computer program product.
In order to achieve the above object, an embodiment of the first aspect of the present application provides an intelligent dialogue method combining RPA and AI, including: the RPA system acquires the dialogue sentences of the service objects from the target service channel; the RPA system carries out dialogue type analysis on the dialogue sentences based on Natural Language Processing (NLP) so as to determine the target dialogue types of the dialogue sentences; the RPA system calls a dialogue service matched with the target dialogue type, and the dialogue service acquires a reply dialogue based on the dialogue statement; and the RPA system feeds the reply dialog back to the terminal equipment of the service object through the target service channel opening.
The method has the advantages that a new consultation service channel is provided, compared with manual customer service, the method is high in efficiency and low in cost, timeliness of answering the problem can be guaranteed, and accordingly service quality is improved.
According to an embodiment of the present application, before the RPA system obtains the dialog statement of the service object from the target service channel, the RPA system further includes: the RPA system excavates source corpora, obtains semantic features of the source corpora based on NLP, and constructs a corpus for each conversation type based on the semantic features.
According to an embodiment of the present application, the constructing a corpus for each dialog type based on the semantic features includes: the RPA system generates a generalization corpus of the source corpus based on the semantic features; and the RPA system acquires a problem set of each conversation type aiming at each conversation type, determines a target corpus matched with the problem set from the source corpus and the generalization corpus, and constructs a corpus of the conversation types based on the target corpus.
According to an embodiment of the present application, before the RPA system obtains the dialog statement of the service object from the target service channel, the RPA system further includes: and the RPA system acquires the target operation of a service object from the target service channel, acquires at least one basic problem matched with the target operation, and feeds the basic problem back to the terminal equipment through the target service channel for display.
According to an embodiment of the application, the obtaining, by the conversation service, a reply conversation based on the conversation statement includes: the RPA system matches the dialogue statement with a question set corresponding to the dialogue service by the dialogue service to acquire a target question matched with the dialogue statement; and the RPA system acquires the linguistic data associated with the target problem and generates the reply dialog based on the linguistic data.
According to an embodiment of the present application, the intelligent dialogue method combining RPA and AI further includes: the RPA system carries out statistics on historical conversation related data of the target service channel; and the RPA system draws a conversation trend graph and/or a conversation report based on the historical conversation related data.
According to an embodiment of the present application, the intelligent dialogue method combining RPA and AI further includes: and the RPA system feeds the conversation sentences which cannot be processed back to the target service platform for processing.
According to an embodiment of the present application, before the RPA system obtains the dialog statement of the service object from the target service channel, the RPA system further includes: and the RPA system sends a channel authorization request to a server, wherein the channel authorization request at least comprises the identification of the target service channel.
In order to achieve the above object, a second embodiment of the present application provides an intelligent dialogue device combining RPA and AI, including: a dialogue statement acquisition module, which is used for the RPA system to acquire dialogue statements of service objects from a target service channel; the conversation type analysis module is used for carrying out conversation type analysis on the conversation sentences by the RPA system based on natural language processing NLP so as to determine the target conversation types of the conversation sentences; a reply dialogue obtaining module, configured to invoke, by the RPA system, a dialogue service matched with the target dialogue type, and obtain, by the dialogue service, a reply dialogue based on the dialogue statement; and the reply dialogue feedback module is used for the RPA system to feed the reply dialogue back to the terminal equipment of the service object through the target service channel opening.
According to an embodiment of the application, the dialogue statement acquisition module further includes: and the corpus construction module is used for mining the source corpus by the RPA system, acquiring semantic features of the source corpus based on NLP, and constructing a corpus for each dialog type based on the semantic features.
According to an embodiment of the present application, the corpus construction module is further configured to: the RPA system generates a generalization corpus of the source corpus based on the semantic features; and the RPA system acquires a problem set of each conversation type aiming at each conversation type, determines a target corpus matched with the problem set from the source corpus and the generalization corpus, and constructs a corpus of the conversation types based on the target corpus.
According to an embodiment of the application, the dialogue statement acquisition module further includes: and the RPA system acquires the target operation of a service object from the target service channel, acquires at least one basic problem matched with the target operation, and feeds the basic problem back to the terminal equipment through the target service channel for display.
According to an embodiment of the application, the reply dialog obtaining module is further configured to: the RPA system matches the dialogue statement with a question set corresponding to the dialogue service by the dialogue service to acquire a target question matched with the dialogue statement; and the RPA system acquires the linguistic data associated with the target problem and generates the reply dialog based on the linguistic data.
According to an embodiment of the present application, the intelligent dialogue device combining RPA and AI is further configured to: the RPA system carries out statistics on historical conversation related data of the target service channel; and the RPA system draws a conversation trend graph and/or a conversation report based on the historical conversation related data.
According to an embodiment of the present application, the intelligent dialogue device combining RPA and AI is further configured to: and the RPA system feeds the conversation sentences which cannot be processed back to the target service platform for processing.
According to an embodiment of the application, the dialogue statement acquisition module further includes: and the RPA system sends a channel authorization request to a server, wherein the channel authorization request at least comprises the identification of the target service channel.
To achieve the above object, a third aspect of the present application provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to implement the intelligent dialog method with RPA and AI as described in embodiments of the first aspect of the present application.
To achieve the above object, a fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions for implementing the intelligent dialogue method with RPA and AI according to the first aspect of the present application.
To achieve the above object, a fifth aspect of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program is used to implement the intelligent dialogue method combining RPA and AI according to the first aspect of the present application.
Drawings
FIG. 1 is a schematic diagram of an intelligent dialog method incorporating RPA and AI according to one embodiment of the present application;
FIG. 2 is a block diagram of an intelligent dialog method incorporating RPA and AI according to one embodiment of the present application;
FIG. 3 is a diagram illustrating steps prior to obtaining a dialog statement for a service object from a target service channel, according to an embodiment of the present application;
fig. 4 is a schematic diagram illustrating a terminal device listing a frequently asked question list for prompt according to an embodiment of the present application;
FIG. 5 is a diagram of a dialog service obtaining a reply dialog based on a dialog statement, according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a user inputting a query question according to one embodiment of the present application;
FIG. 7 is a schematic diagram of a drawing a conversation trend graph and/or a conversation report according to one embodiment of the present application;
FIG. 8 is a general flow diagram of a method for intelligent dialog with RPA and AI in accordance with an embodiment of the present application;
FIG. 9 is a schematic diagram of an intelligent dialog device incorporating RPA and AI according to another embodiment of the present application;
fig. 10 is a schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The following describes an intelligent dialogue method, an intelligent dialogue device, and an electronic device in combination with an RPA and an AI according to an embodiment of the present application with reference to the drawings.
Fig. 1 is a flowchart of an intelligent dialogue method combining RPA and AI according to an embodiment of the present application, as shown in fig. 1, the method includes the following steps:
s101, the RPA system acquires the dialogue sentences of the service objects from the target service channel.
And taking the service channel used by the service object for consulting the information as a target service channel, and acquiring the conversation sentence of the service object from the target service channel by the RPA system. The dialogue statement is a statement corresponding to a problem to be consulted by the service object. The RPA system is an automation technology which is derived based on a plurality of system bottom technologies and front-end technologies and simulates human and computer interaction, and is mainly used in the fields of fixed flow, clear logic, large workload and repetition.
Taking the application of the method in the embodiment of the application to the social security customer service field as an example, optionally, the service channels may include service channels such as public numbers, APPs, applets, official networks and the like. Alternatively, the service object may be a user participating in security at all levels of a city, a district/county, a village, and the like. Optionally, the service content includes, but is not limited to, social security card transaction, pension policy, birth allowance, work wound registration, and other business policies and transaction guides. For example, the dialog statement may be: "how do the social security card is lost".
And S102, the RPA system analyzes the conversation type of the spoken sentence based on the natural language processing NLP to determine the target conversation type of the spoken sentence.
The RPA system performs a dialogue type analysis on a dialogue sentence displayed on a target service channel based on Natural Language Processing (NLP) to determine a target dialogue type of the dialogue sentence. Alternatively, as shown in FIG. 2, the target conversation types may include question-answering conversations, task conversations, and chat conversations. The NLP is a sub-field of artificial intelligence, and refers to a technology for performing interactive communication with a machine by using a natural language used for human communication, and a computer can read and understand the natural language through artificial processing of the natural language.
And S103, the RPA system calls a dialogue service matched with the target dialogue type, and the dialogue service acquires a reply dialogue based on the dialogue statement.
In order to solve the problem of the service object in time, the RPA system needs to quickly invoke a dialog service matching the target dialog type. For example, if the target dialog type is a question-answer dialog, the RPA system invokes a dialog service matching the question-answer dialog, and the dialog service obtains a question of a service object based on a dialog sentence and replies to the question to generate a reply dialog.
And S104, the RPA system feeds the reply dialog back to the terminal equipment of the service object through the target service channel opening.
After determining a reply to the problem of the service object, the RPA system feeds back a reply dialog to the terminal device of the service object through the target service channel opening. Alternatively, the terminal device may be a mobile phone, a tablet, a computer, or the like. Continuing to take the example that the method of the embodiment of the application is applied to the social security customer service field as an example, if the target service channel of the service object is the public number on the mobile phone, the RPA system feeds back the reply conversation to the public number reply interface of the mobile phone corresponding to the service object.
The embodiment of the application provides an intelligent dialogue method combining RPA and AI, which is characterized in that dialogue sentences of a service object are obtained from a target service channel through an RPA system; the RPA system analyzes the dialogue type of the dialogue sentence based on the natural language processing NLP to determine the target dialogue type of the dialogue sentence; the RPA system calls a dialogue service matched with the type of the target object, and the dialogue service acquires a reply dialogue based on dialogue statements; the RPA system feeds back the reply dialogue to the terminal equipment of the service object through the target service channel opening. The method has the advantages that a new consultation service channel is provided, compared with manual customer service, the method is high in efficiency and low in cost, timeliness of answering the problem can be guaranteed, and accordingly service quality is improved.
Fig. 3 is a flowchart of an intelligent dialogue method combining RPA and AI according to an embodiment of the present application, where as shown in fig. 3, before the RPA system obtains a dialogue statement of a service object from a target service channel, the method further includes the following steps:
s301, the RPA system excavates the source corpus and obtains semantic features of the source corpus based on NLP.
In order to enable the robot to fully understand and solve the problem of the service object, the RPA system needs to mine the source corpus and obtain the semantic features of the source corpus based on the NLP. Continuing to take the example that the method of the embodiment of the application is applied to the social security customer service field as an example, the RPA system can perform source corpus mining on the problems related to the social security service, create a customer service knowledge base according to the mined source corpus, and acquire semantic features of the mined source corpus based on NLP.
S302, the RPA system generates a generalization corpus of the source corpus based on the semantic features.
In order to enable the robot to fully understand and solve the problem of the service object, the RPA system achieves certain generalization by expanding similar problems with similar semantics based on the semantic features of the source corpus and generates a generalized corpus corresponding to the source corpus. When generating the generalization corpus corresponding to the source corpus, the RPA system can optimize the robot through corpus mining, model training, part-of-speech tagging and the like. Continuing with the example of applying the method of the embodiment of the present application to the social security customer service field, for example, if the source corpus is "location", the source corpus may be generalized into corpora such as "location", "coordinates", and "geographic information".
S303, the RPA system acquires a problem set of each dialogue type according to each dialogue type, determines a target language material matched with the problem set from the source language material and the generalization language material, and constructs a language material base of the dialogue type based on the target language material.
The RPA system respectively acquires problem sets corresponding to the manual service conversation type and the robot service conversation type aiming at each conversation type, determines target corpora matched with the problem sets from the mined source corpora and the generated generalized corpora, and constructs a corpus of the conversation types based on the target corpora.
S304, the RPA system acquires the target operation of the service object from the target service channel, acquires at least one basic problem matched with the target operation, and feeds the basic problem back to the terminal equipment through the target service channel for display.
Continuing to take the application of the method of the embodiment of the application to the social security customer service field as an example, as shown in fig. 4, if a participating security enterprise or a user pays attention to and clicks the social security official public number, the public number automatically carries out customer service care, obtains at least one basic problem matched with the target operation, and lists a common problem list on the terminal device for prompting.
Before the RPA system obtains the target operation of the service object from the target service channel, the RPA system needs to send a channel authorization request to the server in advance, wherein the channel authorization request at least comprises the identification of the target service channel.
In the embodiment of the application, the RPA system acquires the problem set of each conversation type aiming at each conversation type, and determines the target linguistic data matched with the problem set from the source linguistic data and the generalization linguistic data, so that the problem of user consultation can be fully understood, the related problems are fed back to the terminal equipment through the target service channel to be displayed, the user can select the closest problem needing consultation from the terminal equipment, the random service experience is achieved, and the service experience of the user is improved.
Fig. 5 is a flowchart of an intelligent dialogue method combining RPA and AI according to an embodiment of the present application, and as shown in fig. 5, a dialogue service obtains a reply dialogue based on a dialogue statement, including the following steps:
s501, the RPA system matches the dialogue statement with the question set corresponding to the dialogue service by the dialogue service, and obtains the target question matched with the dialogue statement.
Continuing to take the application of the method of the embodiment of the application to the social security customer service field as an example, as shown in fig. 6, the participating enterprise or the user may input a question to be consulted, or click a question to be consulted in the question list, and the RPA system matches the question of the user to the closest knowledge point in the customer service knowledge base as a target question for matching the conversation statement.
As one way to implement, the RPA system may employ keyword rule-based question answering, i.e., a question containing a keyword input by a user is taken as a target question for matching of a conversational sentence.
As another realizable way, the RPA system may adopt questions and answers based on semantic similarity matching, that is, the questions matched with semantic similarity are not necessarily required to contain the keywords input by the user, but are all used as the target questions matched with the dialog sentences according to semantics.
S502, the RPA system obtains the linguistic data related to the target problem and generates a reply dialog based on the linguistic data.
As an implementation method, continuing to take the application of the method of the embodiment of the present application to the social security service field as an example, if the participant wants to know the location of the social security, he may input "location of the social security in city a", "where the social security in city a" and "geographic information of the social security in city a", and these questions correspond to the same determined answer, that is, when the participant inputs the above target questions, these questions are different expressions of the same question, and the RPA system obtains the associated corpus of the target question in the service knowledge base and outputs the corpus to generate the reply dialog. Continuing to take the application of the method of the embodiment of the present application in the social security customer service field as an example, for example, if the RPA system of the question asked by the insurer includes the answer of the corresponding question, the RPA system can call the answer preset in the system and related to the question of the service object as the answer to the question of the service object.
As another realizable method, a dialog statement that cannot be processed by the RPA system, that is, a customer service knowledge base of the RPA system does not have a solution to the question of the participant, the question is fed back to the target service platform and is processed by a manual customer service. When the manual customer service is used for processing, the manual customer service timely solves the problem of the service object and determines the reply conversation. Optionally, a robot may be used to assist the manual customer service when the manual customer service is processed. Continuing to take the application of the method of the embodiment of the application in the social security customer service field as an example, for example, if there is no corresponding answer in the question RPA system of the questions asked by the insurer, the question can be manually answered and replied.
In the embodiment of the application, after the RPA system acquires the target problem, the corpus associated with the target problem is acquired, and the reply dialogue is generated based on the corpus, so that the RPA system is more accurate and quicker compared with the traditional customer service, and is high in efficiency and low in cost.
Fig. 7 is a flowchart of an intelligent dialogue method combining RPA and AI according to an embodiment of the present application, and as shown in fig. 7, based on the above embodiment, the method further includes the following steps:
s701, the RPA system counts the historical dialogue related data of the target service channel.
In order to assist social security workers in analyzing the customer service quality of the RPA system, the RPA system can count the historical conversation related data of the target service channel in units of days or hours. Optionally, the historical dialogue related data may include the number of sessions of the robot service, knowledge point usage ranking, user satisfaction, attributes of the user, number of messages received by the robot, number of recalls of knowledge points, recall rate and number of recalls, and the like.
And S702, drawing a conversation trend graph and/or a conversation report by the RPA system based on the historical conversation related data.
And drawing a conversation trend graph or a conversation report according to the historical conversation related data counted by the RPA system. In the embodiment of the application, the RPA system draws the conversation trend graph and/or the conversation report based on the historical conversation related data, and can assist workers in analyzing the customer service quality of the intelligent conversation robot, so that the intelligent conversation robot is optimized and improved.
Fig. 8 is a general flowchart of an intelligent dialogue method combining RPA and AI according to an embodiment of the present application, as shown in fig. 8, the method includes the following steps:
s801, the RPA system excavates the source corpus and obtains semantic features of the source corpus based on NLP.
S802, the RPA system generates a generalization corpus of the source corpus based on the semantic features.
And S803, the RPA system acquires the problem set of each conversation type according to each conversation type, determines the target language material matched with the problem set from the source language material and the generalization language material, and constructs a language material base of the conversation type based on the target language material.
S804, the RPA system acquires the target operation of the service object from the target service channel, acquires at least one basic problem matched with the target operation, and feeds the basic problem back to the terminal equipment through the target service channel for display.
Regarding steps S801 to S804, the above embodiments have been specifically described, and are not described herein again.
S805, the RPA system acquires the dialogue sentences of the service objects from the target service channel.
S806, the RPA system performs a dialogue type analysis on the spoken sentence based on the natural language processing NLP to determine a target dialogue type of the spoken sentence.
S807, the RPA system calls a dialogue service matching the target object type.
And S808, the RPA system matches the dialogue statements and the problem set corresponding to the dialogue service by the dialogue service to acquire the target problem matched with the dialogue statements.
And S809, the RPA system acquires the linguistic data related to the target question and generates a reply dialog based on the linguistic data.
And S810, the RPA system feeds the reply dialog back to the terminal equipment of the service object through the target service channel opening.
Regarding steps S805 to S810, the above embodiments have been specifically described, and are not described herein again.
S811, the RPA system counts the historical dialogue related data of the target service channel.
And S812, the RPA system draws a conversation trend graph and/or a conversation report based on the historical conversation related data.
Regarding steps S811 to S812, the above embodiments have been specifically described, and are not described again.
The embodiment of the application provides an intelligent dialogue method combining RPA and AI, which is characterized in that dialogue sentences of a service object are obtained from a target service channel through an RPA system; the RPA system analyzes the dialogue type of the dialogue sentence based on the natural language processing NLP to determine the target dialogue type of the dialogue sentence; the RPA system calls a dialogue service matched with the type of the target object, and the dialogue service acquires a reply dialogue based on dialogue statements; the RPA system feeds back the reply dialogue to the terminal equipment of the service object through the target service channel opening. The method has the advantages that a new consultation service channel is provided, compared with manual customer service, the method is high in efficiency and low in cost, timeliness of answering the problem can be guaranteed, and accordingly service quality is improved.
Fig. 9 is a schematic diagram of an intelligent dialogue device combining RPA and AI according to an embodiment of the present application, and as shown in fig. 9, the device 900 includes: a dialogue sentence acquisition module 91, a dialogue type analysis module 92, a reply dialogue acquisition module 93 and a reply dialogue feedback module 94, wherein:
a dialogue statement acquisition module 91, configured to acquire a dialogue statement of a service object from a target service channel by an RPA system;
a dialogue type analysis module 92, configured to perform dialogue type analysis on the utterance by the RPA system based on the natural language processing NLP, so as to determine a target dialogue type of the dialogue;
a reply dialogue obtaining module 93, configured to invoke, by the RPA system, a dialogue service matched with the target dialogue type, and obtain, by the dialogue service, a reply dialogue based on the dialogue statement;
and a reply dialog feedback module 94, configured to feed back, by the RPA system, a reply dialog to the terminal device of the service object through the target service tunnel junction.
Further, before the dialog statement obtaining module 91, the method further includes: and a corpus construction module 95, configured to mine the source corpus by the RPA system, acquire semantic features of the source corpus based on the NLP, and construct a corpus for each dialog type based on the semantic features.
Further, the corpus construction module 95 is further configured to: the RPA system generates a generalization corpus of the source corpus based on semantic features; the RPA system acquires a problem set of each conversation type according to each conversation type, determines a target language material matched with the problem set from a source language material and a generalization language material, and constructs a language material base of the conversation type based on the target language material.
Further, before the dialog statement obtaining module 91, the method further includes: the RPA system acquires the target operation of the service object from the target service channel, acquires at least one basic problem matched with the target operation, and feeds the basic problem back to the terminal equipment through the target service channel for display.
Further, the reply dialog obtaining module 93 is further configured to: the RPA system matches the dialogue statement with a problem set corresponding to the dialogue service by the dialogue service to acquire a target problem matched with the dialogue statement; the RPA system obtains the linguistic data associated with the target problem and generates a reply dialogue based on the linguistic data.
Further, the intelligent dialog device 900 in conjunction with RPA and AI is further configured to: the RPA system counts the historical dialogue related data of the target service channel; the RPA system draws a conversation trend graph and/or a conversation report based on historical conversation related data.
Further, the intelligent dialog device 900 in conjunction with RPA and AI is further configured to: and the RPA system feeds back the conversation sentences which cannot be processed to the target service platform for processing.
Further, before the dialog statement obtaining module 91, the method further includes: the RPA system sends a channel authorization request to the server, wherein the channel authorization request at least comprises an identification of a target service channel.
In order to implement the foregoing embodiments, an embodiment of the present application further provides an electronic device 1000, as shown in fig. 10, where the electronic device 1000 includes: a processor 1001 and a memory 1002 communicatively coupled to the processor, the memory 1002 storing instructions executable by the at least one processor 1001 for implementing a method for intelligent dialogue in conjunction with RPA and AI as embodied in the first aspect of the present application.
To achieve the above embodiments, the present application also proposes a non-transitory computer readable storage medium storing computer instructions for causing a computer to implement the intelligent dialogue method combining RPA and AI as embodied in the first aspect of the present application.
To implement the foregoing embodiments, the present application further provides a computer program product, which includes a computer program and a computer program, where the computer program, when executed by a processor, implements the intelligent dialogue method combining RPA and AI according to the embodiment of the first aspect of the present application.
In the description of the present application, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the present application and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the present application.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific 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 application. In this specification, the schematic representations of the terms used above are not necessarily intended to 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. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (19)

1. An intelligent dialog method combining RPA and AI, performed by an RPA system, the method comprising:
the RPA system acquires a dialogue statement of a service object from a target service channel;
the RPA system carries out dialogue type analysis on the dialogue sentences based on Natural Language Processing (NLP) so as to determine the target dialogue types of the dialogue sentences;
the RPA system calls a dialogue service matched with the target dialogue type, and the dialogue service acquires a reply dialogue based on the dialogue statement;
and the RPA system feeds the reply dialog back to the terminal equipment of the service object through the target service channel opening.
2. The method of claim 1, wherein before the RPA system obtains the conversational sentence of the service object from the target service channel, the RPA system further comprises:
the RPA system excavates source corpora, obtains semantic features of the source corpora based on NLP, and constructs a corpus for each conversation type based on the semantic features.
3. The method of claim 2, wherein the constructing a corpus for each of the dialog types based on the semantic features comprises:
the RPA system generates a generalization corpus of the source corpus based on the semantic features;
and the RPA system acquires a problem set of each conversation type aiming at each conversation type, determines a target corpus matched with the problem set from the source corpus and the generalization corpus, and constructs a corpus of the conversation types based on the target corpus.
4. The method according to any of claims 1-3, wherein before the RPA system obtains the conversational sentence of the service object from the target service channel, the RPA system further comprises:
and the RPA system acquires the target operation of a service object from the target service channel, acquires at least one basic problem matched with the target operation, and feeds the basic problem back to the terminal equipment through the target service channel for display.
5. The method of any one of claims 1-3, wherein obtaining, by the conversation service, a reply conversation based on the conversation statement comprises:
the RPA system matches the dialogue statement with a question set corresponding to the dialogue service by the dialogue service to acquire a target question matched with the dialogue statement;
and the RPA system acquires the linguistic data associated with the target problem and generates the reply dialog based on the linguistic data.
6. The method according to any one of claims 1-3, further comprising:
the RPA system carries out statistics on historical conversation related data of the target service channel;
and the RPA system draws a conversation trend graph and/or a conversation report based on the historical conversation related data.
7. The method according to any one of claims 1-3, further comprising:
and the RPA system feeds the conversation sentences which cannot be processed back to the target service platform for processing.
8. The method of claim 1, wherein before the RPA system obtains the conversational sentence of the service object from the target service channel, the RPA system further comprises:
and the RPA system sends a channel authorization request to a server, wherein the channel authorization request at least comprises the identification of the target service channel.
9. An intelligent dialog device that combines RPA and AI, comprising:
a dialogue statement acquisition module, which is used for the RPA system to acquire dialogue statements of service objects from a target service channel;
the conversation type analysis module is used for carrying out conversation type analysis on the conversation sentences by the RPA system based on natural language processing NLP so as to determine the target conversation types of the conversation sentences;
a reply dialogue obtaining module, configured to invoke, by the RPA system, a dialogue service matched with the target dialogue type, and obtain, by the dialogue service, a reply dialogue based on the dialogue statement;
and the reply dialogue feedback module is used for the RPA system to feed the reply dialogue back to the terminal equipment of the service object through the target service channel opening.
10. The apparatus of claim 9, wherein the dialog statement capture module is preceded by:
and the corpus construction module is used for mining the source corpus by the RPA system, acquiring semantic features of the source corpus based on NLP, and constructing a corpus for each dialog type based on the semantic features.
11. The apparatus of claim 10, wherein the corpus construction module is further configured to:
the RPA system generates a generalization corpus of the source corpus based on the semantic features;
and the RPA system acquires a problem set of each conversation type aiming at each conversation type, determines a target corpus matched with the problem set from the source corpus and the generalization corpus, and constructs a corpus of the conversation types based on the target corpus.
12. The apparatus according to any one of claims 9-11, wherein the dialogue sentence acquisition module is preceded by:
and the RPA system acquires the target operation of a service object from the target service channel, acquires at least one basic problem matched with the target operation, and feeds the basic problem back to the terminal equipment through the target service channel for display.
13. The apparatus according to any one of claims 9-11, wherein the reply dialog acquisition module is further configured to:
the RPA system matches the dialogue statement with a question set corresponding to the dialogue service by the dialogue service to acquire a target question matched with the dialogue statement;
and the RPA system acquires the linguistic data associated with the target problem and generates the reply dialog based on the linguistic data.
14. The apparatus of any of claims 9-11, wherein the apparatus is further configured to:
the RPA system carries out statistics on historical conversation related data of the target service channel;
and the RPA system draws a conversation trend graph and/or a conversation report based on the historical conversation related data.
15. The apparatus of any of claims 9-11, wherein the apparatus is further configured to:
and the RPA system feeds the conversation sentences which cannot be processed back to the target service platform for processing.
16. The apparatus of claim 9, wherein the dialog statement capture module is preceded by:
and the RPA system sends a channel authorization request to a server, wherein the channel authorization request at least comprises the identification of the target service channel.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any of claims 1-8.
19. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-8.
CN202110727765.5A 2021-06-29 2021-06-29 Intelligent dialogue method and device combining RPA and AI and electronic equipment Pending CN113553409A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110727765.5A CN113553409A (en) 2021-06-29 2021-06-29 Intelligent dialogue method and device combining RPA and AI and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110727765.5A CN113553409A (en) 2021-06-29 2021-06-29 Intelligent dialogue method and device combining RPA and AI and electronic equipment

Publications (1)

Publication Number Publication Date
CN113553409A true CN113553409A (en) 2021-10-26

Family

ID=78102535

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110727765.5A Pending CN113553409A (en) 2021-06-29 2021-06-29 Intelligent dialogue method and device combining RPA and AI and electronic equipment

Country Status (1)

Country Link
CN (1) CN113553409A (en)

Similar Documents

Publication Publication Date Title
US11128680B2 (en) AI mediated conference monitoring and document generation
US11997055B2 (en) Chat management system
CN107112016B (en) Multi-modal state cycling
CN102388377B (en) System and method for editing a conversation in a hosted conversation system
CN112838978B (en) System and method for real-time short message robot supporting man-machine cooperation
DE102012109629A1 (en) Mobile multi-mode customer care system
JP2020095764A (en) Information inputting method, information inputting device, and information inputting system
CN108519998B (en) Problem guiding method and device based on knowledge graph
US20120303614A1 (en) Automating responses to information queries
US11216787B1 (en) Meeting creation based on NLP analysis of contextual information associated with the meeting
US9811594B2 (en) Automatic explanation of presented abbreviations
CN116595148B (en) Method and system for realizing dialogue flow by using large language model
CN111585874A (en) Method and system for automatically controlling service group
CN112383667A (en) Call data processing method, device, equipment and storage medium
KR20190058257A (en) Chatbot trainer platform and method of operating the same
CN111611365A (en) Flow control method, device, equipment and storage medium of dialog system
CN114005440A (en) Question-answering method, system, electronic equipment and storage medium based on voice interaction
CN109478206A (en) Multilingual communication system and multilingual communication providing method
Jelphs Communication: soft skill, hard impact?
KR20190036604A (en) Hybrid chat providing method using predefined conversation flow and hybrid chat service server
CN114757155B (en) Conference document generation method and device
US11012382B2 (en) State display information transmission system using chatbot
CN113553409A (en) Intelligent dialogue method and device combining RPA and AI and electronic equipment
CN106202222A (en) The determination method and device of focus incident
CN113138702B (en) Information processing method, device, electronic 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