CN111897942A - Dialogue robot problem processing method, device and equipment combining RPA and AI - Google Patents
Dialogue robot problem processing method, device and equipment combining RPA and AI Download PDFInfo
- Publication number
- CN111897942A CN111897942A CN202010819708.5A CN202010819708A CN111897942A CN 111897942 A CN111897942 A CN 111897942A CN 202010819708 A CN202010819708 A CN 202010819708A CN 111897942 A CN111897942 A CN 111897942A
- Authority
- CN
- China
- Prior art keywords
- information
- processed
- user
- knowledge point
- identifier
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 61
- 238000000034 method Methods 0.000 claims abstract description 53
- 238000012217 deletion Methods 0.000 claims description 24
- 230000037430 deletion Effects 0.000 claims description 24
- 241000590419 Polygonia interrogationis Species 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 description 27
- 230000002452 interceptive effect Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
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
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a dialogue robot problem processing method, a device and equipment combining RPA and AI, wherein the method comprises the following steps: outputting page information of a problem processing scene, and receiving a control instruction input by a user; and executing corresponding operation on the problem to be processed included in the page information according to the control instruction. According to the method and the device, the relevant operation of the knowledge point to-be-processed problem or the intention to-be-processed problem can be completed through the problem processing scene page, the page does not need to be switched, the operation is simplified, the execution efficiency of the electronic equipment can be improved, and the updating efficiency of the dialogue knowledge base is improved.
Description
Cross Reference to Related Applications
The present application claims priority of chinese patent application No. 202010615253.5, entitled "AI-based dialog robot problem review method, apparatus and device", filed on 30/6/2020 by beijing lai network technologies co ltd and beijing benying network technologies co ltd.
Technical Field
The embodiment of the application relates to the field of artificial intelligence, in particular to a method, a device and equipment for processing problems of a conversation robot by combining RPA and AI.
Background
Robot Process Automation (RPA) simulates the operation of a human on a computer through specific robot software and automatically executes Process tasks according to rules. Artificial Intelligence (AI) is a new technology science that studies and develops theories, methods, techniques and application systems for simulating, extending and expanding human intelligence. Research in the field of artificial intelligence includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others. The conversation robot refers to a robot capable of performing conversation interaction with a user or completing corresponding tasks according to user instructions. With the development of science and technology, the functions of the conversation robot are gradually enriched, conversation with a user can be carried out, and corresponding tasks can be executed according to instructions of the user. The dialogue robot can answer the questions of the user or execute corresponding tasks according to the instructions of the user without leaving the knowledge base stored in the dialogue robot. The more comprehensive the content of the knowledge base is, the stronger the ability of the conversation robot to respond to the user questions or execute corresponding tasks is, and the better the performance of the conversation robot is.
In order to ensure the performance of the interactive robot, the knowledge base of the interactive robot is usually updated according to the problem or the instruction that the interactive robot cannot recognize, so that the interactive robot can recognize the problem or the instruction to be processed.
In the related art, the knowledge base needs to be updated according to different pages corresponding to different problems to be processed, so as to update the knowledge base of the conversation robot. That is to say, in the updating process, the processing of the problem to be processed can be completed only by continuously switching the pages, the operation is complex, and the updating efficiency of the knowledge base is low.
Disclosure of Invention
The application provides a dialogue robot problem processing method, device and equipment combining RPA and AI, which can simplify the problem processing process to be processed so as to improve the knowledge base updating efficiency.
In a first aspect, the present application provides a method for processing a dialog robot problem in combination with an RPA and an AI, applied to an electronic device, the method including:
outputting page information of the problem processing scene;
receiving a control instruction input by a user;
and executing corresponding operation on the problem to be processed included in the page information according to the control instruction.
Optionally, the page information includes at least N pieces of information to be selected corresponding to the problem to be processed;
the executing, according to the control instruction, corresponding operations on the to-be-processed problem included in the page information includes:
and establishing an incidence relation between the problem to be processed and target information in the at least N pieces of information to be selected according to the control instruction.
Optionally, the executing, according to the control instruction, a corresponding operation on the to-be-processed problem included in the page information includes:
outputting page information of the added information according to the control instruction;
receiving information to be added input by a user, wherein the information to be added comprises knowledge points or intentions;
and establishing an association relation between the problem to be processed and the information to be added.
Optionally, the method further includes:
receiving selection information input by a user;
and determining the problem to be processed according to the selection information.
Optionally, the method further includes:
receiving deletion information input by a user, wherein the deletion information comprises an identifier of a to-be-deleted problem to be processed;
and deleting the to-be-deleted problems to be processed according to the deletion information. Optionally, the method further includes:
receiving updating information input by a user and an identifier of a problem to be processed needing updating;
and updating the to-be-processed problem to be updated according to the updating information.
Optionally, the outputting the page information of the problem processing scenario includes:
determining an identification of the problem to be processed;
acquiring an identifier of information to be selected from a knowledge point and an ideogram according to the identifier of the problem to be processed and the identifier of the problem to be processed, wherein at least N identifiers of the information to be selected corresponding to the identifier of the problem to be processed are stored in the knowledge point and the ideogram;
respectively acquiring data corresponding to the identifier of each information to be selected;
and outputting page information of the problem processing scene according to the problem to be processed and the data.
Optionally, the information to be selected includes knowledge points or intentions; wherein, the data corresponding to the knowledge point to be selected comprises: the name of the knowledge point, at least one piece of similar question information corresponding to the knowledge point and an answer corresponding to the knowledge point; the data corresponding to the intention to be selected includes: the name of the intent, at least one trigger to which the intent corresponds, and a word slot to which the intent corresponds.
Optionally, the obtaining, according to the to-be-processed problem and the identifier of the to-be-processed problem, the identifier of the to-be-selected information from the knowledge point and the intention chart includes:
inquiring an information base according to the problem to be processed to obtain at least N identifiers of information to be selected, wherein the identifiers are matched with the problem to be processed;
setting the incidence relation between the identification of the problem to be processed and the identification of the at least N pieces of information to be selected so as to form the knowledge point and the intention list;
and the knowledge point and intention table stores preparation question marks corresponding to the marks of the questions to be processed and the marks of the at least N knowledge points and/or intentions to be selected corresponding to the preparation question marks.
Optionally, before the establishing an association relationship between the to-be-processed question and the target information in the at least N pieces of information to be selected according to the control instruction, the method includes:
receiving selection information input by a user;
and determining the target information from the at least N pieces of information to be selected according to the selection information.
In a second aspect, the present application provides a conversation robot problem processing apparatus combining RPA and AI, comprising:
and the output module is used for outputting the page information of the problem processing scene.
And the receiving module is used for receiving a control instruction input by a user.
And the processing module is used for executing corresponding operation on the problem to be processed included in the page information according to the control instruction.
Optionally, the page information includes at least N pieces of information to be selected corresponding to the problem to be processed; the processing module is specifically configured to establish an association relationship between the problem to be processed and target information in the at least N pieces of information to be selected according to the control instruction.
Optionally, the processing module is specifically configured to output page information of the added information according to the control instruction; receiving information to be added input by a user, wherein the information to be added comprises knowledge points or intentions; and establishing an incidence relation between the problem to be processed and the information to be added.
Optionally, the receiving module is further configured to receive selection information input by a user.
The processing module is further used for determining the problem to be processed according to the selection information.
Optionally, the receiving module is further configured to receive deletion information input by the user, where the deletion information includes an identifier of a to-be-processed problem that needs to be deleted.
The processing module is also used for deleting the to-be-processed problems needing to be deleted according to the deletion information.
Optionally, the receiving module is further configured to receive update information input by a user and an identifier of a to-be-processed problem that needs to be updated.
The processing module is further configured to update the to-be-processed problem to be updated according to the update information.
Optionally, the output module is specifically configured to determine an identifier of a problem to be processed; acquiring the identifier of the information to be selected from the knowledge point and the meaning graph according to the identifier of the problem to be processed and the identifier of the problem to be processed, wherein at least N identifiers of the information to be selected corresponding to the identifier of the problem to be processed are stored in the knowledge point and the meaning graph; respectively acquiring data corresponding to the identifier of each information to be selected; and outputting page information of the problem processing scene according to the problems to be processed and the data.
Optionally, the information to be selected includes knowledge points or intentions; wherein, the data corresponding to the knowledge point to be selected comprises: the name of the knowledge point, at least one piece of similar question information corresponding to the knowledge point and an answer corresponding to the knowledge point; the data corresponding to the intention to be selected includes: the name of the intent, at least one trigger to which the intent corresponds, and a word slot to which the intent corresponds.
Optionally, the output module is specifically configured to query an information base according to the problem to be processed, and obtain at least N identifiers of information to be selected, which are matched with the problem to be processed; and setting the incidence relation between the identification of the problem to be processed and the identification of at least N pieces of information to be selected so as to form a knowledge point and an intention list.
Optionally, the receiving module is further configured to receive selection information input by a user.
The processing module is further configured to determine target information from at least N pieces of information to be selected according to the selection information.
In a third aspect, the present application provides an electronic device, comprising: 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 enable the at least one processor to perform the method of dialogue robot problem handling in combination with RPA and AI as the first aspect or the alternatives of the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon computer-executable instructions for implementing a method for conversational robot problem handling in combination with RPA and AI as described in the first aspect or an alternative form of the first aspect when executed by a processor.
According to the method, the device and the equipment for processing the problems of the conversation robot combining the RPA and the AI, page information of a problem processing scene is output; receiving a control instruction input by a user; according to the control instruction, corresponding operation is executed on the to-be-processed question included in the page information, the knowledge base of the conversation robot can be updated, and therefore when the conversation robot receives the to-be-processed question, the conversation robot can respond to the question and make an accurate answer or execute a correct action. And because the related operation of the problem to be processed can be completed through one problem processing scene page, the page does not need to be switched, the execution efficiency of the electronic equipment can be improved, and the updating efficiency of the dialogue knowledge base is further improved.
Furthermore, the problems to be processed can be determined according to the selection information by receiving the selection information input by the user, so that the user can select different problems to be processed according to the requirement of the user to process the problems.
Furthermore, the deletion information input by the user can be received, the identification of the to-be-deleted problem to be processed is included in the deletion information, and the to-be-deleted problem to be processed is deleted according to the deletion information, so that the problem to be processed, which is to be deleted, is prevented from being repeatedly processed for many times, the data volume of the electronic equipment can be reduced, and the operation efficiency is improved.
Furthermore, the problem to be processed which needs to be updated can be updated according to the update information by receiving the update information input by the user and the identification of the problem to be processed which needs to be updated, so that the problem to be processed is supplemented and perfected, the readability of the problem to be processed is improved, and the accuracy of the electronic equipment for processing the problem to be processed is improved.
Drawings
FIG. 1 is a schematic flow chart of a dialogue robot problem processing method combining RPA and AI according to the present application;
FIG. 2 is another schematic flow chart of the dialogue robot problem processing method combining RPA and AI provided by the present application;
FIG. 3 is a schematic view of an interactive interface of an electronic device provided herein;
FIG. 4 is a schematic view of another interactive interface of the electronic device provided herein;
FIG. 5 is a schematic view of yet another interface of an electronic device provided herein;
FIG. 6 is a schematic diagram of yet another interface of an electronic device provided herein;
FIG. 7 is a schematic view of yet another interface of an electronic device provided herein;
FIG. 8 is a schematic diagram of a structure of a dialogue robot problem processing device combining RPA and AI provided by the present application;
fig. 9 is a schematic structural diagram of an electronic device provided in the present application.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
In the following, terms referred to in the embodiments of the present application are explained:
problems to be treated: a question that the robot fails to answer correctly or a task that fails to respond correctly.
Knowledge points are as follows: a collection of similar questions and answers to replies about a question.
Intention is: the user asks the robot for the task to be completed. For example, the computer is turned off.
Similar problems: different expression for a certain problem.
A trigger: an "intention flow" consisting of multiple rounds of interaction.
Word groove: are variables that need to be satisfied in order to accomplish a particular task.
With the development of science and technology, the functions of the conversation robot are gradually enriched, conversation with a user can be carried out, and corresponding tasks can be executed according to instructions of the user. The dialogue robot can answer the questions of the user or execute corresponding tasks according to the instructions of the user without leaving the knowledge base stored in the dialogue robot. The more comprehensive the content of the knowledge base is, the stronger the ability of the conversation robot to respond to the user questions or execute corresponding tasks is, and the better the performance of the conversation robot is.
In order to ensure the performance of the conversation robot, the knowledge base of the conversation robot is updated according to the questions or instructions that the conversation robot cannot identify, also called to-be-processed questions, so that the conversation robot can identify the to-be-processed questions, wherein the knowledge base indicates the association relationship between the to-be-processed questions and a certain knowledge point or a certain intention. In general, a problem that the interactive robot cannot recognize is referred to as a knowledge point problem, and an instruction that the interactive robot cannot recognize is referred to as an intention problem. In the prior art, when a knowledge base is updated, a to-be-processed problem of a knowledge point or an intention to-be-processed problem is processed through a page corresponding to the to-be-processed problem of the knowledge point or a page corresponding to the intention to-be-processed problem, and the knowledge base of a conversation robot is updated.
However, when the to-be-processed problem includes both the to-be-processed problem related to the knowledge point and the to-be-processed problem related to the intention, the user needs to switch pages continuously to process the to-be-processed problem of the knowledge point and the to-be-processed problem of the intention through different pages, the operation is complex, and the updating efficiency of the knowledge base is low.
If the processing of the problem to be processed of the knowledge point and the problem to be processed of the intention can be completed through one page, the knowledge base updating efficiency can be improved. Based on the problem processing method, the problem processing method of the conversation robot combining the RPA and the AI is provided, and page information of a problem processing scene is output; and receiving a control instruction input by a user, and executing corresponding operation on the to-be-processed problem included in the page information according to the control instruction, so that the to-be-processed problem of the knowledge point and the to-be-processed problem of the intention are processed through one page.
The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of a method for processing a dialog robot problem in association with RPA and AI according to the present application, which is applied to an electronic device, and the method shown in fig. 1 includes:
and S101, outputting page information of the problem processing scene.
The electronic equipment outputs page information of a question processing scene through an interactive interface of the electronic equipment, wherein the page information can comprise one or more questions to be processed and related information thereof, such as knowledge points or intentions related to the questions to be processed, answers related to the questions to be processed, similar questions or word slots related to the questions to be processed, and the like.
And S102, receiving a control instruction input by a user.
The electronic device can receive the control instruction input by the user through the interactive interface, and can also receive the control instruction input by the user through the voice device and the like.
S103, according to the control instruction, corresponding operation is executed on the problem to be processed included in the page information.
Specifically, according to the control instruction, the corresponding operation performed on the to-be-processed question included in the page information may be that, when the control instruction indicates that a certain to-be-processed question is added to a certain knowledge point or intention, the electronic device performs an operation of adding the to-be-processed question to the knowledge point or intention; when the control instruction indicates the new knowledge point or the intention, the electronic equipment executes the new knowledge point or the intention and carries out operation of adding the new knowledge point or the intention to the problem to be processed.
According to the conversation robot problem processing method combining the RPA and the AI, page information of a problem processing scene is output; receiving a control instruction input by a user; according to the control instruction, corresponding operation is executed on the to-be-processed problem included in the page information, the knowledge base of the conversation robot can be updated, and then when the to-be-processed problem is received by the conversation robot, the conversation robot can respond to the problem and make an accurate answer or execute a correct action.
When a plurality of problems to be processed exist, in order to meet different requirements of users, the problems to be processed can be screened according to selection instructions input by the users. Based on this, on the basis of the above embodiments, the present application provides another dialogue robot problem processing method combining RPA and AI, and fig. 2 is another schematic flow chart of the dialogue robot problem processing method combining RPA and AI provided by the present application, as shown in fig. 2, the method includes:
s201, receiving selection information input by a user.
The electronic device can receive the selection information input by the user through the interactive interface of the electronic device, and can also receive the selection information input by the user through the voice device. The selection information may be adding time corresponding to the problem to be processed, or a confidence level of the problem to be processed, where the confidence level of the problem to be processed may be determined by a semantic similarity algorithm.
The following is a schematic diagram illustrating how the electronic device receives the selection information input by the user through the interactive interface. Fig. 3 is a schematic view of an interactive interface of the electronic device provided in the present application, and as shown in fig. 3, a user may select different adding times in a selection box corresponding to the adding times, and click a "filtering" control, so as to filter out to-be-processed problems meeting the time requirements from a to-be-processed problem library, where a plurality of to-be-processed problems are stored in the to-be-processed problem library. The user can also select different confidence intervals in the selection frame corresponding to the confidence, and click the 'screening' control, so as to screen the to-be-processed problem meeting the confidence requirement from the to-be-processed problem library; certainly, the user can also select the adding time and the confidence coefficient at the same time, then click the 'screening' control, and screen out the to-be-processed problems meeting the time requirement and the confidence coefficient requirement from the to-be-processed problem library.
In order to simplify the user operation, the user can also display the problems to be processed according to the sequence of adding time by clicking the reverse sequence of adding time or the forward sequence of adding time corresponding to the adding time; the to-be-processed questions can also be displayed according to the sequence of the confidence values by clicking the 'confidence reverse order' or 'confidence forward order' corresponding to the confidence.
S202, determining the problem to be processed according to the selection information.
Further, in order to improve readability of the problem to be processed, optionally, an update operation may be performed on the problem to be processed, specifically, update information input by a user and an identifier of the problem to be processed, which needs to be updated, may be received, and the problem to be processed, which needs to be updated, is updated according to the update information.
By the method, the to-be-processed problems which are incompletely and indistinct in expression can be supplemented and perfected, the readability of the to-be-processed problems is improved, and meanwhile, the accuracy and the efficiency of the electronic equipment for identifying the to-be-processed problems are improved.
And S203, outputting page information of the problem processing scene.
The electronic device can output page information of the problem processing scene through an interactive interface of the electronic device. Specifically, the method can comprise the following steps: determining an identifier of a problem to be processed; acquiring the identifier of the information to be selected from the knowledge point and the meaning graph according to the identifier of the problem to be processed and the identifier of the problem to be processed, wherein at least N identifiers of the information to be selected corresponding to the identifier of the problem to be processed are stored in the knowledge point and the meaning graph; respectively acquiring data corresponding to the identifier of each information to be selected; and outputting page information of the problem processing scene according to the problems to be processed and the data.
The above steps are explained below by way of an example. Table 1 shows a knowledge point and intention table provided by the present application, and as shown in table 1, it is assumed that the identifier of the problem to be processed is id-001, and the knowledge point and intention table stores identifiers of 3 pieces of information to be selected, which are rec _ id-021, rec _ id-123, and rec _ id-041, corresponding to the identifier id-001 of the problem to be processed. And then acquiring the identifier of the information to be selected from the knowledge point and the idea chart according to the problem to be processed and the identifier of the problem to be processed, querying a database according to the identifier of the information to be selected to acquire data corresponding to the identifier of each information to be selected, and outputting page information of a problem processing scene according to the problem to be processed and the data.
Table 1 points of knowledge and intention table 01
Optionally, the information to be selected comprises knowledge points or intentions. Wherein, the data corresponding to the knowledge point to be selected comprises: the name of the knowledge point, at least one piece of similar question information corresponding to the knowledge point and an answer corresponding to the knowledge point. The data corresponding to the intention to be selected includes: the name of the intent, at least one trigger to which the intent corresponds, and a word slot to which the intent corresponds.
Based on the above optional manner, as shown in table 2, it is assumed that the identifier of the problem to be processed is id-001, and the knowledge point and the intention table store the identifiers of 3 pieces of information to be selected, which are rec _ id-021, rec _ id-123 and rec _ id-041, corresponding to the identifier id-001 of the problem to be processed; the type of the information to be selected is a knowledge point or an intention, and it is assumed that "1" identifies the knowledge point and "0" represents the intention. Firstly, acquiring an identifier of information to be selected from a knowledge point and an intention chart according to the problem to be processed and the identifier of the problem to be processed, then querying a corresponding database according to the identifier of the information to be selected and the type of the information to be selected to acquire data corresponding to the identifier of each information to be selected, for example, querying the database corresponding to the knowledge point according to the identifier 'rec _ id-021' of the information to be selected and the type '1' of the information to be selected to acquire data corresponding to the knowledge point; and inquiring a database corresponding to the intention according to the identifier rec _ id-123 of the information to be selected and the type 0 of the information to be selected, and acquiring data corresponding to the intention. And finally, outputting page information of the problem processing scene according to the problems to be processed and the data.
Table 2 points of knowledge and intention table 02
Optionally, on the basis of the above specific implementation, a process of determining knowledge points and ideograms may also be included. Specifically, one possible implementation of determining knowledge points and intent tables is: inquiring an information base according to the problem to be processed to obtain at least N identifiers of information to be selected, which are matched with the problem to be processed; and setting the incidence relation between the identification of the problem to be processed and the identification of at least N pieces of information to be selected so as to form a knowledge point and an intention list. Wherein, the information base comprises a plurality of knowledge points or intentions.
The page information of the problem processing scenario is described below with a schematic diagram. Fig. 4 is a schematic diagram of another interactive interface of the electronic device provided in the present application, and as shown in fig. 4, the page information of the problem processing scenario may include "today is not cold" of the problem to be processed; three knowledge points corresponding to the problem to be processed are named as 'date inquiry', 'weather inquiry' and 'temperature inquiry' respectively; and similar question information and answers corresponding to any knowledge point, specifically, the similar question information corresponding to the knowledge point "date inquiry" includes "number of the year", "number of the day" and "what date", and the corresponding answer is "6 months and 1 days in 2020"; the similar question information corresponding to the knowledge point weather inquiry comprises weather which is today, rain which is today and sunny day, and the corresponding answer is sunny day; the similar question information corresponding to the knowledge point of "temperature query" includes "hot not hot", "temperature is high not high today" and "how many degrees today", and the corresponding answer is "20 ℃. It should be noted that one knowledge point often corresponds to a lot of similar problem information, one intention often corresponds to a plurality of triggers, and fig. 4 is only illustrated due to limited space and is not exhaustive of similar problems corresponding to the knowledge point.
By outputting the page information of the problem processing scene, the user can intuitively judge whether the knowledge points or intentions in the page information of the problem to be processed and the output problem processing scene are matched, and the judgment is simple and intuitive.
And S204, receiving a control instruction input by a user.
S203 is similar to S102, and the detailed description may refer to S102, which is not repeated herein.
And S205, executing corresponding operation on the to-be-processed problem included in the page information according to the control instruction.
Specifically, when the page information includes at least N pieces of information to be selected corresponding to the to-be-processed problem, according to the control instruction, an implementation manner of performing one of corresponding operations on the to-be-processed problem included in the page information is as follows: and establishing an incidence relation between the problem to be processed and target information in the at least N pieces of information to be selected according to the control instruction.
With continued reference to fig. 4, the user may click the control "add to the knowledge point" corresponding to any knowledge point, and output a control instruction, so that the problem to be processed "no cold today" is associated with the knowledge point, for example, the user clicks the control "add to the knowledge point" corresponding to the knowledge point "temperature query", so that the problem to be processed "no cold today" is associated with the knowledge point "temperature query", and when the dialog robot is asked again "no cold today", the dialog robot will make a corresponding answer according to the knowledge point "temperature query".
Optionally, before the association relationship is established between the problem to be processed and the target information in the at least N pieces of information to be selected according to the control instruction, the method may further include: receiving selection information input by a user; and determining target information from at least N pieces of information to be selected according to the selection information.
The above alternative is illustrated by a schematic diagram. Fig. 5 is a schematic view of another interactive interface of the electronic device provided in the present application, and as shown in fig. 5, a user may input selection information by checking any information to be selected, so that the electronic device determines, according to the selection information, the information to be selected checked by the user as target information from at least N pieces of information to be selected; the user can also confirm and input the control instruction by clicking the control, so that the electronic equipment establishes the association relationship between the problem to be processed and the target information according to the control instruction.
Optionally, when there is no information to be selected that can establish an association relationship with the problem to be processed in at least N pieces of information to be selected included in the page information, a new knowledge point or intention may be created, and an association relationship may be established between the problem to be processed and the newly created knowledge point or intention. Specifically, another possible implementation manner for executing corresponding operations on the to-be-processed problem included in the page information according to the control instruction is to output the page information to which information is added according to the control instruction; receiving information to be added input by a user, wherein the information to be added comprises knowledge points or intentions; and establishing an incidence relation between the problem to be processed and the information to be added. By the method, new information can be added conveniently, and an association relation is established between the problem to be processed and the newly added information.
Fig. 6 is a schematic diagram of another interaction interface of the electronic device provided by the present application, as shown in fig. 6, when the to-be-selected information and the to-be-processed problem included in the page information cannot establish an association relationship, the user may click the control "newly-built knowledge point" or "newly-built intention", and newly-built knowledge point or intention, as shown in fig. 6, after the user clicks the control "newly-built knowledge point" on the first page 601, the page jumps to the second page 602, the user may input information, such as the name, answer, similar problem information, and the like of the knowledge point, on the second page, and then click the control "confirm", and complete information addition, that is, the knowledge point is newly built, and an association relationship is established between the to-be-processed problem and the newly-added information.
Optionally, after an association relationship is established between the to-be-processed question and the target information in the at least N pieces of to-be-selected information according to the control instruction, or an association relationship is established between the to-be-processed question and the to-be-added information, the to-be-processed question may be deleted from the to-be-processed question library. Therefore, optionally, the method may further include:
s206, receiving the deleting information input by the user, wherein the deleting information comprises the identification of the to-be-deleted problem to be processed.
The electronic device can receive a deletion instruction input by a user through an interactive interface of the electronic device.
And S207, deleting the to-be-processed problem needing to be deleted according to the deletion information.
With reference to fig. 4, the user may input the identifier of the to-be-processed problem corresponding to the deletion control by clicking the control "delete", and the electronic device deletes the to-be-processed problem corresponding to the identifier of the to-be-processed problem when receiving the deletion instruction.
Optionally, the user may delete the to-be-processed problems in batch by means of checking and the like. Fig. 7 is a schematic diagram of another interactive interface of the electronic device provided by the present application, as shown in fig. 7, a user may click a control on a third interface 701 to "delete a problem to be processed", and jump to a fourth interface 702, then the user may click one or more problems to be processed on the fourth interface, click a control "determine", input deletion information, and the electronic device receives the deletion instruction, and then deletes the problem to be processed corresponding to the identifier of the problem to be processed.
By the method, the problems to be processed which are associated with the knowledge points or the intentions can be deleted from the problem library to be processed, so that the same problem to be processed is prevented from being repeatedly processed; and secondly, the data volume of the electronic equipment can be reduced, the operation speed of the electronic equipment is improved, and the storage capacity of the electronic equipment is guaranteed.
According to the dialogue robot problem processing method combining the RPA and the AI, the problem to be processed is determined by receiving the selection information input by the user and according to the selection information, different problems to be processed can be selected from the problem library to be processed according to different requirements for processing, and the requirements of different users can be met; furthermore, the method comprises the steps of outputting page information of a question processing scene, receiving a control instruction input by a user, executing corresponding operation on a to-be-processed question included in the page information according to the control instruction, establishing an association relation between the to-be-processed question and a knowledge point or intention, updating a phone robot knowledge base through one page, and enabling the conversation robot to respond to the question and make an accurate answer or execute a correct action when receiving the to-be-processed question; the method comprises the steps that deletion information input by a user is received, wherein the deletion information comprises an identifier of a problem to be deleted and to be processed; according to the deletion information, the to-be-deleted problem to be deleted is deleted, so that the same to-be-deleted problem is prevented from being repeatedly operated, the data volume of the electronic equipment is reduced, and the storage capacity of the electronic equipment is guaranteed.
Fig. 8 is a schematic structural diagram of a dialogue robot problem processing apparatus combining RPA and AI according to the present application, and as shown in fig. 8, the apparatus includes:
and the output module 81 is used for outputting the page information of the problem processing scene.
And the receiving module 82 is used for receiving a control instruction input by a user.
And the processing module 83 is configured to execute a corresponding operation on the to-be-processed problem included in the page information according to the control instruction.
Optionally, the page information includes at least N pieces of information to be selected corresponding to the problem to be processed; the processing module 83 is specifically configured to establish an association relationship between the problem to be processed and the target information in the at least N pieces of information to be selected according to the control instruction.
Optionally, the processing module 83 is specifically configured to output page information of the added information according to the control instruction; receiving information to be added input by a user, wherein the information to be added comprises knowledge points or intentions; and establishing an incidence relation between the problem to be processed and the information to be added.
Optionally, the receiving module 82 is further configured to receive selection information input by the user.
The processing module is further used for determining the problem to be processed according to the selection information.
Optionally, the receiving module 82 is further configured to receive deletion information input by the user, where the deletion information includes an identifier of a to-be-processed question that needs to be deleted.
The processing module 83 is further configured to delete the to-be-processed problem that needs to be deleted according to the deletion information.
Optionally, the receiving module 82 is further configured to receive update information input by the user and an identifier of a to-be-processed problem that needs to be updated.
The processing module 83 is further configured to update the to-be-processed problem that needs to be updated according to the update information.
Optionally, the output module 81 is specifically configured to determine an identifier of a problem to be processed; acquiring the identifier of the information to be selected from the knowledge point and the intention chart according to the problem to be processed and the identifier of the problem to be processed; respectively acquiring data corresponding to the identifier of each information to be selected; and outputting page information of the problem processing scene according to the problems to be processed and the data.
Optionally, the information to be selected includes knowledge points or intentions; wherein, the data corresponding to the knowledge point to be selected comprises: the name of the knowledge point, at least one piece of similar question information corresponding to the knowledge point and an answer corresponding to the knowledge point; the data corresponding to the intention to be selected includes: the name of the intent, at least one trigger to which the intent corresponds, and a word slot to which the intent corresponds.
Optionally, the output module 81 is specifically configured to query an information base according to the problem to be processed, and obtain at least N identifiers of the information to be selected, which are matched with the problem to be processed; and setting the incidence relation between the identification of the problem to be processed and the identification of at least N pieces of information to be selected so as to form a knowledge point and an intention list.
Optionally, the receiving module 82 is further configured to receive selection information input by the user.
The processing module 83 is further configured to determine target information from at least N pieces of information to be selected according to the selection information.
The apparatus for processing questions of a dialogue robot combining RPA and AI may execute the method for processing questions of a dialogue robot combining RPA and AI, and the contents and effects thereof may refer to the embodiment of the method, which is not described herein again.
Fig. 9 is a schematic structural diagram of an electronic device provided in the present application, and as shown in fig. 9, the electronic device of this embodiment includes: a processor 91, a memory 92; the processor 91 is communicatively connected to the memory 92. The memory 92 is used to store computer programs. The processor 91 is adapted to call a computer program stored in the memory 92 to implement the method in the above-described method embodiment.
Optionally, the electronic device further comprises: a transceiver 93 for enabling communication with other devices.
The electronic device can execute the above method for processing the problem of the dialogue robot by combining the RPA and the AI, and the contents and effects thereof can be referred to the embodiment of the method, which is not described again.
The application also provides a computer readable storage medium, wherein computer execution instructions are stored in the computer readable storage medium, and when being executed by a processor, the computer execution instructions are used for realizing the conversation robot problem processing method combining the RPA and the AI.
The content and effect of the method for processing the problem of the dialogue robot combining the RPA and the AI can be referred to in the embodiment of the method, and details thereof are not repeated.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims. It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (13)
1. A conversation robot problem processing method combining RPA and AI, which is applied to an electronic device, the method comprising:
outputting page information of the problem processing scene;
receiving a control instruction input by a user;
and executing corresponding operation on the to-be-processed problem included in the page information according to the control instruction.
2. The method according to claim 1, wherein the page information includes at least N information to be selected corresponding to the question to be processed;
the executing, according to the control instruction, corresponding operations on the to-be-processed problem included in the page information includes:
and establishing an incidence relation between the problem to be processed and target information in the at least N pieces of information to be selected according to the control instruction.
3. The method according to claim 1, wherein the performing, according to the control instruction, a corresponding operation on the to-be-processed question included in the page information includes:
outputting page information of the added information according to the control instruction;
receiving information to be added input by a user, wherein the information to be added comprises knowledge points or intentions;
and establishing an association relation between the problem to be processed and the information to be added.
4. The method of claim 1, further comprising:
receiving selection information input by a user;
and determining the problem to be processed according to the selection information.
5. The method of claim 1, further comprising:
receiving deletion information input by a user, wherein the deletion information comprises an identifier of a to-be-deleted problem to be processed;
and deleting the to-be-deleted problems to be processed according to the deletion information.
6. The method of claim 1, further comprising:
receiving updating information input by a user and an identifier of a problem to be processed needing updating;
and updating the to-be-processed problem to be updated according to the updating information.
7. The method of claim 1, wherein outputting page information of a problem processing scenario comprises:
determining an identification of the problem to be processed;
acquiring an identifier of information to be selected from a knowledge point and an ideogram according to the identifier of the problem to be processed and the identifier of the problem to be processed, wherein at least N identifiers of the information to be selected corresponding to the identifier of the problem to be processed are stored in the knowledge point and the ideogram;
respectively acquiring data corresponding to the identifier of each information to be selected;
and outputting page information of the problem processing scene according to the problem to be processed and the data.
8. The method of claim 7, wherein the information to be selected comprises knowledge points or intents;
wherein, the data corresponding to the knowledge point to be selected comprises: the name of a knowledge point, at least one piece of similar question information corresponding to the knowledge point and an answer corresponding to the knowledge point;
the data corresponding to the intention to be selected comprises: the name of an intent, at least one trigger corresponding to the intent, and a word slot corresponding to the intent.
9. The method according to claim 7, wherein the obtaining an identifier of information to be selected from a knowledge point and an intention graph according to the question to be processed and the identifier of the question to be processed comprises:
inquiring an information base according to the problem to be processed to obtain at least N identifiers of information to be selected, wherein the identifiers are matched with the problem to be processed;
setting the incidence relation between the identification of the problem to be processed and the identification of the at least N pieces of information to be selected so as to form the knowledge point and the intention list;
and the knowledge point and intention table stores preparation question marks corresponding to the marks of the questions to be processed and the marks of the at least N knowledge points and/or intentions to be selected corresponding to the preparation question marks.
10. The method according to claim 2, wherein before establishing the association relationship between the to-be-processed question and the target information in the at least N pieces of information to be selected according to the control instruction, the method comprises:
receiving selection information input by a user;
and determining the target information from the at least N pieces of information to be selected according to the selection information.
11. A conversation robot problem processing apparatus combining RPA and AI, comprising:
the output module is used for outputting page information of the problem processing scene;
the receiving module is used for receiving a control instruction input by a user;
and the processing module is used for executing corresponding operation on the problem to be processed included in the page information according to the control instruction.
12. An electronic device, comprising:
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 enable the at least one processor to perform the RPA and AI-integrated dialogue robot problem processing method of any one of claims 1 to 10.
13. A computer-readable storage medium having stored thereon computer-executable instructions for implementing the RPA and AI-coupled dialogue robot problem processing method of any one of claims 1 to 10 when executed by a processor.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020106152535 | 2020-06-30 | ||
| CN202010615253 | 2020-06-30 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111897942A true CN111897942A (en) | 2020-11-06 |
| CN111897942B CN111897942B (en) | 2024-07-23 |
Family
ID=73229476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010819708.5A Active CN111897942B (en) | 2020-06-30 | 2020-08-14 | Dialogue robot problem processing method, device and equipment combining RPA and AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111897942B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197167A (en) * | 2017-12-18 | 2018-06-22 | 深圳前海微众银行股份有限公司 | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing |
| US20190197181A1 (en) * | 2017-12-21 | 2019-06-27 | Shanghai Xiaoi Robot Technology Co., Ltd. | Questioning and answering method, method for generating questioning and answering system, and method for modifying questioning and answering system |
| CN111309889A (en) * | 2020-02-27 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Method and device for text processing |
-
2020
- 2020-08-14 CN CN202010819708.5A patent/CN111897942B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197167A (en) * | 2017-12-18 | 2018-06-22 | 深圳前海微众银行股份有限公司 | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing |
| US20190197181A1 (en) * | 2017-12-21 | 2019-06-27 | Shanghai Xiaoi Robot Technology Co., Ltd. | Questioning and answering method, method for generating questioning and answering system, and method for modifying questioning and answering system |
| CN111309889A (en) * | 2020-02-27 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Method and device for text processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111897942B (en) | 2024-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107958059B (en) | Intelligent question answering method, device, terminal and computer readable storage medium | |
| CN112084315A (en) | Question-answer interaction method, device, storage medium and equipment | |
| CN112652302B (en) | Voice control method, device, terminal and storage medium | |
| CN110109981B (en) | Information display method and device for work queue, computer equipment and storage medium | |
| CN112905178B (en) | Service function page generation method, device, equipment and medium | |
| CN108664665A (en) | Data format method for transformation, device, equipment and readable storage medium storing program for executing | |
| CN110633959A (en) | Method, device, equipment and medium for creating approval task based on graph structure | |
| CN112231544A (en) | RPA robot search method, device and equipment combining RPA and AI | |
| CN111435367A (en) | Knowledge graph construction method, system, equipment and storage medium | |
| CN113191139A (en) | Data blood margin analysis method and device based on column-level data | |
| CN113760242B (en) | Data processing method, device, server and medium | |
| CN113705816A (en) | Flow chart generation method, electronic device, device and readable storage medium | |
| CN109829821A (en) | A kind of abnormal processing method of digital asset address transfer, apparatus and system | |
| CN111897942A (en) | Dialogue robot problem processing method, device and equipment combining RPA and AI | |
| CN112000786A (en) | Dialogue robot problem processing method, device and equipment combining RPA and AI | |
| US20220405658A1 (en) | Machine learning assisted automation of workflows based on observation of user interaction with operating system platform features | |
| CN115756692A (en) | Method for automatically combining and displaying pages based on style attributes and related equipment thereof | |
| US11328018B2 (en) | System and method for state dependency based task execution and natural language response generation | |
| CN111796733B (en) | Image display method, image display device and electronic equipment | |
| CN108334621B (en) | Database operation method, device, equipment and computer readable storage medium | |
| CN109542986B (en) | Element normalization method, device, equipment and storage medium of network data | |
| CN112966029A (en) | Information display and sending method, device, equipment and readable medium | |
| CN112036576A (en) | Data processing method and device based on data form and electronic equipment | |
| CN113515280A (en) | Page code generation method and device | |
| CN112835494A (en) | Voice recognition result error correction method and device |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: 1902, 19 / F, China Electronics Building, 3 Danling Road, Haidian District, Beijing 100080 Applicant after: BEIJING LAIYE NETWORK TECHNOLOGY Co.,Ltd. Applicant after: Laiye Technology (Beijing) Co.,Ltd. Address before: 1902, 19 / F, China Electronics Building, 3 Danling Road, Haidian District, Beijing 100080 Applicant before: BEIJING LAIYE NETWORK TECHNOLOGY Co.,Ltd. Country or region before: China Applicant before: BEIJING BENYING NETWORK TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |