CN112000786A - 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
- CN112000786A CN112000786A CN202010820949.1A CN202010820949A CN112000786A CN 112000786 A CN112000786 A CN 112000786A CN 202010820949 A CN202010820949 A CN 202010820949A CN 112000786 A CN112000786 A CN 112000786A
- Authority
- CN
- China
- Prior art keywords
- information
- processed
- identifier
- user
- outputting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims description 11
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000012217 deletion Methods 0.000 claims description 18
- 230000037430 deletion Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 15
- 239000000126 substance Substances 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 description 24
- 230000002452 interceptive effect Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 7
- 238000012546 transfer Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication 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
- G06F16/332—Query formulation
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The method comprises the steps of outputting page information of an information viewing scene, receiving a viewing instruction input by a user, and outputting at least one to-be-processed problem corresponding to the information according to the viewing instruction. By the method, the user can check the corresponding relation between the problem to be processed and the information through the information, the checking mode is simple, and the checking mode is enriched.
Description
Cross Reference to Related Applications
The present application claims priority of chinese patent application No. 202010615280.2, 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 technical 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. The richness of the content included in the knowledge base of the conversation robot has a large influence on the performance of the intelligent robot. To ensure the performance of the dialogue robot, the knowledge base is usually updated and refined according to the problem to be processed, so that the dialogue robot can identify the problem to be processed. The to-be-processed question refers to a question or an instruction which cannot be identified by the conversation robot.
When a user updates and perfects the knowledge base according to the problem to be processed, the corresponding relation between the problem to be processed and the information in the knowledge base needs to be determined. In the prior art, a user selects a problem to be processed, and then checks information in a knowledge base corresponding to the problem to be processed.
However, in the prior art, a user can only check information corresponding to a certain problem to be processed, and the checking mode is single, and different requirements of the user cannot be met.
Disclosure of Invention
The application provides a conversation robot problem processing method, device and equipment combining RPA and AI, which can enable a user to check the corresponding relation between the problem to be processed and information through the information, the checking mode is simple, the checking mode is enriched, and the requirements of more users can be met.
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 an information viewing scene; receiving a viewing instruction input by a user; and outputting at least one to-be-processed problem corresponding to the information according to the viewing instruction.
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-processed problems needing to be deleted 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 problems needing to be updated according to the updating information.
Optionally, the method further includes: receiving a control instruction input by a user, wherein the control instruction comprises an identifier of a problem to be processed and an identifier of target information; and establishing a target association relation between the problem to be processed and the target information according to the control instruction.
Optionally, the method further comprises: receiving a refreshing instruction input by a user; and refreshing the page information of the information viewing scene according to the refreshing instruction.
Optionally, before outputting the page information of the information viewing scene, the method further includes: receiving a selection instruction input by a user; correspondingly, the page information of the output information viewing scene includes:
and outputting page information of the information viewing scene according to the selection instruction.
Optionally, the outputting at least one to-be-processed question corresponding to the information according to the viewing instruction includes: determining the identification of the information; and determining the to-be-processed problem corresponding to the information identifier according to the information identifier, the pre-configured knowledge point and intention table and the pre-configured to-be-processed problem table, wherein at least one to-be-processed problem and the identifier of each to-be-processed problem are stored in the to-be-processed problem table, and at least one information identifier corresponding to the identifier of the to-be-processed problem is stored in the knowledge point and intention table.
Optionally, the page information of the output information viewing scene includes: inquiring an information base according to the identifier of any information to acquire data corresponding to the identifier of the information; and outputting page information, wherein the page information comprises data.
Optionally, the information includes knowledge points, and the data includes: the names of the knowledge points, the information of similar questions corresponding to the knowledge points and the answers corresponding to the knowledge points.
Optionally, the information includes an intent, and the data includes: the name of the intention, the trigger corresponding to the intention, and the word slot corresponding to the intention.
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 information viewing scene.
And the receiving module is used for receiving a viewing instruction input by a user.
The output module is further used for outputting at least one to-be-processed problem corresponding to the information according to the viewing instruction.
Optionally, the receiving module is further configured to receive deletion information input by a user, where the deletion information includes an identifier of a to-be-processed problem that needs to be deleted; and 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; and updating the to-be-processed problems needing to be updated according to the updating information.
Optionally, the receiving module is further configured to receive a control instruction input by a user, where the control instruction includes an identifier of a problem to be processed and an identifier of target information; and establishing a target association relation between the problem to be processed and the target information according to the control instruction.
Optionally, the receiving module is further configured to receive a refresh instruction input by a user; and refreshing the page information of the information viewing scene according to the refreshing instruction.
Optionally, the receiving module is further configured to receive a selection instruction input by a user; correspondingly, the output module is specifically used for outputting the page information of the information viewing scene according to the selection instruction.
Optionally, the output module is specifically configured to determine an identifier of the information; and determining the to-be-processed problem corresponding to the information identifier according to the information identifier, the pre-configured knowledge point and intention table and the pre-configured to-be-processed problem table, wherein at least one to-be-processed problem and the identifier of each to-be-processed problem are stored in the to-be-processed problem table, and at least one information identifier corresponding to the identifier of the to-be-processed problem is stored in the knowledge point and intention table.
Optionally, the receiving module is specifically configured to query an information base according to the identifier of any information, and obtain data corresponding to the identifier of the information; and outputting page information, wherein the page information comprises the data.
Optionally, the information includes knowledge points, and the data includes: the names of the knowledge points, the information of similar questions corresponding to the knowledge points and the answers corresponding to the knowledge points.
Optionally, the information includes an intent, and the data includes: the name of the intention, the trigger corresponding to the intention, and the word slot corresponding to the intention.
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 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 the method as described in the first aspect or the alternatives thereof when executed by a processor.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
on one hand, 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 scene is checked through output information, and a checking instruction input by a user is received; according to the checking instruction, at least one to-be-processed problem corresponding to the information is output, so that the user can check the corresponding relation between the to-be-processed problem and the information through the information, the checking mode is simple, and the checking mode is enriched.
On the other hand, deleting information input by a user is received, wherein the deleting information comprises an identifier of a to-be-deleted problem to be processed; according to the deleted information, deleting the to-be-processed problem which needs to be deleted, deleting the to-be-processed problem which is not matched with the information, and optimizing the corresponding relation between the to-be-processed problem and the information.
On the other hand, the updating information input by the user and the identification of the problem to be processed needing updating are received; and updating the to-be-processed problem to be updated according to the updating information, updating and perfecting the expression of the to-be-processed problem, and improving the readability of the to-be-processed problem.
On the other hand, a control instruction input by a user is received, wherein the control instruction comprises an identifier of a problem to be processed and an identifier of target information; establishing a target association relation between the problem to be processed and target information according to the control instruction, and transferring the problem to be processed into a similar problem corresponding to the knowledge point or a word slot corresponding to the intention; the method can also be used for receiving a refreshing instruction input by a user; and refreshing the page information of the information viewing scene according to the refreshing instruction, refreshing the page information, and presenting the latest corresponding relation between the information and the problem to be processed for the user.
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 a schematic view of an interactive interface of an electronic device provided herein;
FIG. 3 is another schematic view of an interactive interface of an electronic device provided herein;
FIG. 4 is another flow chart illustrating a method for processing a problem of a dialogue robot in combination with RPA and AI according to the present application;
FIG. 5 is a schematic view of an interactive interface of an electronic device provided herein;
FIG. 6 is a further schematic view of an interactive interface of the electronic device provided herein;
FIG. 7 is a schematic diagram of a structure of a dialogue robot problem processing device combining RPA and AI provided by the present application;
fig. 8 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.
The dialogue is to simulate the operation of human on the computer by specific robot software and automatically execute the flow task according to the rules. The richness of the content included in the knowledge base of the conversation robot has a large influence on the performance of the intelligent robot. To ensure the performance of the dialogue robot, the knowledge base is usually updated and refined according to the problem to be processed, so that the dialogue robot can identify the problem to be processed. The to-be-processed question refers to a question or an instruction which cannot be identified by the conversation robot.
When a user updates and perfects the knowledge base according to the problem to be processed, the corresponding relation between the problem to be processed and the information in the knowledge base needs to be determined. In the prior art, a user selects a problem to be processed, and then checks information in a knowledge base corresponding to the problem to be processed.
However, in the prior art, a user can only check information corresponding to a certain problem to be processed, and the checking mode is single, and different requirements of the user cannot be met.
If the corresponding to-be-processed problem can be checked according to the information, the checking mode can be enriched, and the requirements of different users are met. Based on the problem processing method, the conversation robot problem processing method combining the RPA and the AI is provided, and page information of a scene is checked through output information; receiving a viewing instruction input by a user; and outputting at least one to-be-processed problem corresponding to the information according to the viewing instruction. The user can check the corresponding to-be-processed problem according to the information, and checking modes of the corresponding relation between the information and the to-be-processed problem are enriched.
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 is shown in fig. 1, where the method includes:
and S101, outputting page information of the information viewing scene.
The electronic equipment can output the page information of the information viewing scene through a human-computer interaction interface of the electronic equipment. The information can be a knowledge point or an intention, and correspondingly, the page information can comprise the name of the knowledge point, similar problems corresponding to the knowledge point, answers corresponding to the knowledge point, attribute information of a problem to be processed corresponding to the knowledge point and the like; or, the page information may include a name of the intention, a trigger corresponding to the intention, a word slot corresponding to the intention, attribute information of the to-be-processed question corresponding to the intention, and the like, where the attribute information of the to-be-processed question may include content information of the to-be-processed question, the number of the to-be-processed questions, and the like. The following illustrates, by a schematic diagram, page information of an information viewing scenario output by an electronic device. Fig. 2 is a schematic diagram of an interactive interface of an electronic device provided in the present application, and as shown in fig. 2, the interactive interface shows page information including a name of a knowledge point, "where a coupon is viewed"; similar questions corresponding to the knowledge point include "how and how to see the coupon, where the coupon is located", and the answer corresponding to the knowledge point is "please click on my coupon to see the coupon that you have". The page information shown in fig. 2 further includes the number of to-be-processed problems corresponding to the knowledge point, specifically "284".
And S102, receiving a viewing instruction input by a user.
The electronic device can receive a viewing instruction input by a user through a human-computer interaction interface of the electronic device. With continued reference to fig. 2, the user may input a viewing instruction by clicking a "view" button to view the to-be-processed problem corresponding to the knowledge point.
S103, outputting at least one to-be-processed question corresponding to the information according to the checking instruction.
And after receiving the view input by the user, the electronic equipment displays and outputs at least one to-be-processed question corresponding to the information through the interactive interface. Fig. 3 is another schematic view of an interactive interface of the electronic device provided by the present application, and as shown in fig. 3, after a user clicks a "view" button on a first page 301 to input a view instruction to the electronic device, the interactive interface of the electronic device jumps from the first page 301 to a second page 302, and outputs at least one to-be-processed question corresponding to the information to the second page 302.
According to the conversation robot problem processing method combining the RPA and the AI, page information of a scene is checked through output information; receiving a viewing instruction input by a user; according to the checking instruction, at least one to-be-processed problem corresponding to the information is output, the user can check the to-be-processed problem related to certain information, and compared with the situation that the information corresponding to the to-be-processed problem can only be checked through the to-be-processed problem in the prior art, the method can enrich the checking mode of the corresponding relation between the information and the to-be-processed problem, and meets the checking requirements of different users.
The information concerned by different users may be different, and in order to meet the requirements of different users, before S101 in the above embodiment, the information may also be filtered according to the requirements of the users. Fig. 4 is another schematic flow chart of the dialogue robot problem processing method combining RPA and AI provided by the present application, which is applied to an electronic device, and as shown in fig. 4, the method includes:
s401, receiving a selection instruction input by a user.
The electronic device can receive a selection instruction input by a user through an interactive interface of the electronic device, and can also receive a selection instruction input by the user through a voice device of the electronic device.
S402, outputting page information of the information viewing scene according to the selection instruction.
Wherein the information may be a knowledge point or an intention.
Optionally, one possible implementation manner of outputting the page information of the information viewing scene is as follows: inquiring an information base according to the identifier of any information to acquire data corresponding to the identifier of the information; and outputting page information, wherein the page information comprises the data. By the method, the corresponding data can be accurately acquired according to the identification of any information.
Optionally, the information includes knowledge points, and the data includes: the names of the knowledge points, the information of similar questions corresponding to the knowledge points and the answers corresponding to the knowledge points.
Optionally, the information includes an intent, and the data includes: the name of the intention, the trigger corresponding to the intention, and the word slot corresponding to the intention.
The following description is given by way of example of the electronic device receiving a selection instruction input by a user through an interactive interface thereof. Fig. 5 is another schematic diagram of an interactive interface of the electronic device provided in the present application, as shown in fig. 5, a user clicks a "view by knowledge point" button on the interactive interface of the electronic device, and then can enter a page shown in a third page 501, where the third page 501 includes data related to knowledge points, including names of the knowledge points, similar question information corresponding to the knowledge points, and answers corresponding to the knowledge points; the user can jump from the third page 501 to the fourth interface 502 by clicking "view with intent" on the third page 501, and the fourth page 502 includes data related to intent, i.e., including the name of the intent, the trigger corresponding to the intent, and the word slot corresponding to the intent.
Specifically, according to the selection instruction, one possible implementation manner of outputting the page information of the information viewing scene is as follows: and outputting page information of the information viewing scene according to the selection instruction and the pre-configured knowledge points and the intention table. The selection instruction comprises the type of the information and/or a confidence value corresponding to the information.
For example, with continued reference to fig. 5, assume that the user clicks the "view knowledge points" button, that is, a selection instruction is output to the electronic device, and the type of information included in the selection instruction is a knowledge point; assume that the user clicks the "view with intention" button, that is, a selection instruction including information of which type is intention is output to the electronic apparatus.
And S403, receiving a viewing instruction input by a user.
S403 is similar to S102, and the specific description may refer to S102, which is not described herein.
S404, outputting at least one to-be-processed problem corresponding to the information according to the viewing instruction.
Optionally, one possible implementation manner of outputting at least one to-be-processed question corresponding to the information according to the viewing instruction is as follows: determining the identification of the information; and determining the to-be-processed problem corresponding to the information identifier according to the information identifier, the pre-configured knowledge point and intention table and the pre-configured to-be-processed problem table, wherein at least one to-be-processed problem and the identifier of each to-be-processed problem are stored in the to-be-processed problem table, and at least one information identifier corresponding to the identifier of the to-be-processed problem is stored in the knowledge point and intention table. By which identification based on information can be performed
For example, table 1 is a to-be-processed problem table provided by the present application, and table 2 is a knowledge point and intention table provided by the present application, and if the identifier of the information is "rec _ id-021", it can be known from tables 1 and 2 that the identifiers of to-be-processed problems corresponding to the information identified as "rec _ id-021" are "id-001" and "id-003"; where the pending issue identified as "id-001" is "where the coupon is"; wherein the pending issue identified as "id-003" is "does there is a coupon".
Table 1 pending problem table
| Pending issue identification | Problem to be treated |
| id-001 | Where the coupon is |
| id-002 | Does good weather |
| id-003 | Is there a coupon |
Table 2 points of knowledge and intention table
The user may check at least one to-be-processed problem corresponding to any information through the steps, and whether the corresponding relation between the to-be-processed problem and the information is reasonable or not can be determined through processing and analysis of the to-be-processed problem. If the corresponding relation between a certain problem to be processed and the information is not reasonable, the user can remove the corresponding relation between the problem to be processed and the information.
Based on this, optionally, may further include:
s405, receiving deletion information input by a user, wherein the deletion information comprises an identifier of a to-be-deleted problem to be processed.
The electronic device can receive a deletion instruction input by a user through the interactive interface.
And S406, deleting the to-be-processed problem to be deleted according to the deletion information.
Fig. 6 is a further schematic view of an interactive interface of the electronic device provided by the present application, and as shown in fig. 6, a user may delete any problem to be processed by clicking a "delete" key corresponding to the problem to be processed. In order to improve the deleting efficiency, the user can click the batch deleting button to delete the checked to-be-processed problems after the to-be-processed problems needing to be deleted are checked. It is understood that the two deletion modes can exist simultaneously or can be applied separately.
Of course, the user may check at least one to-be-processed question corresponding to any information through the above steps, and after processing and analysis, if it is determined that the corresponding relationship between a certain to-be-processed question and the information is reasonable, the user may establish a target association relationship between the to-be-processed question and the information, and specifically, when the information is a knowledge point, the information may be determined as a similar question of the knowledge point; when the information is an intent, the information may be determined to be a trigger for the intent.
Based on this, optionally, may further include:
and S407, receiving a control instruction input by a user.
The electronic device can receive control instructions input by a user through the interactive interface.
And S408, establishing a target association relation between the problem to be processed and the information according to the control instruction.
Continuing to refer to fig. 6, the user may establish a target association relationship between the to-be-processed question and the information by clicking a "transfer" button corresponding to any one of the to-be-processed questions, specifically, when the information is a knowledge point, the to-be-processed question may be transferred to a similar question of the knowledge point by clicking the "transfer" button; when the information is an intention, the pending question may be transferred to a trigger for the intention by clicking a "transfer" button. Similarly, in order to improve the transfer efficiency, the user can click the batch transfer button after performing the checking operation on the to-be-processed problem to be transferred, and establish the target association relationship between the checked to-be-processed problem and the information. It is understood that the two deletion modes can exist simultaneously or can be applied separately.
The pending question is generated by the fact that the robot fails to accurately answer the question or correctly execute the action command after the user asks the question or sends the action command to the dialogue robot. It is understood that the to-be-processed problem may be generated because the way expressed by the user is not accurate enough, or may be generated because the dialog robot fails to accurately identify the to-be-processed problem, and in order to accurately represent the to-be-processed problem and improve the readability of the to-be-processed problem, optionally, the to-be-processed problem may further include:
and S409, receiving the updating information input by the user and the identification of the to-be-processed problem needing to be updated.
The electronic device can receive the updating information input by the user and the identification of the to-be-processed problem needing to be updated through the interactive interface.
And S410, updating the to-be-processed problem to be updated according to the updating information.
By the method, the to-be-processed problems with incomplete and unclear expression can be supplemented and perfected, and the readability of the to-be-processed problems is improved.
Based on the fact that a user may delete a certain to-be-processed problem corresponding to certain information, a target association relationship may also be established between the certain to-be-processed problem and the information, and thus the to-be-processed problem corresponding to the information is changed. In order to timely know the current situation of the to-be-processed problem corresponding to a certain piece of information, optionally, the method may further include:
s411, receiving a refresh command input by a user.
The electronic device can receive a refresh command input by a user through the interactive interface.
And S412, refreshing the page information of the information viewing scene according to the refreshing instruction.
With continued reference to fig. 2, the user may input a refresh command by clicking a "refresh" button, so that the electronic device refreshes the page information of the information viewing scene according to the refresh command. For example, the number of the to-be-processed questions corresponding to the updated information, the similar questions corresponding to the information, and the like.
According to the conversation robot problem processing method combining the RPA and the AI, on the basis of the embodiment, the page information of the scene is checked by receiving the selection instruction input by the user and outputting the information according to the selection instruction, so that the inquiry requirements of different users can be met, and the user experience is improved.
Fig. 7 is a schematic structural diagram of a dialogue robot problem processing apparatus combining RPA and AI according to the present application, as shown in fig. 7, the apparatus includes:
and the output module 71 is used for outputting the page information of the information viewing scene.
The receiving module 72 is configured to receive a viewing instruction input by a user.
The output module 71 is further configured to output at least one to-be-processed question corresponding to the information according to the viewing instruction.
Optionally, the receiving module 72 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; and deleting the to-be-processed problems needing to be deleted according to the deletion information.
Optionally, the receiving module 72 is further configured to receive update information input by a user and an identifier of a to-be-processed question that needs to be updated; and updating the to-be-processed problems needing to be updated according to the updating information.
Optionally, the receiving module 72 is further configured to receive a control instruction input by a user, where the control instruction includes an identifier of a problem to be processed and an identifier of target information; and establishing a target association relation between the problem to be processed and the target information according to the control instruction.
Optionally, the receiving module 72 is further configured to receive a refresh command input by a user; and refreshing the page information of the information viewing scene according to the refreshing instruction.
Optionally, the receiving module 72 is further configured to receive a selection instruction input by a user; correspondingly, the output module 71 is specifically configured to output page information of the information viewing scene according to the selection instruction.
Optionally, the output module 71 is specifically configured to determine an identifier of the information; and determining the to-be-processed problem corresponding to the information identifier according to the information identifier, the pre-configured knowledge point and intention table and the pre-configured to-be-processed problem table, wherein at least one to-be-processed problem and the identifier of each to-be-processed problem are stored in the to-be-processed problem table, and at least one information identifier corresponding to the identifier of the to-be-processed problem is stored in the knowledge point and intention table.
Optionally, the receiving module 72 is specifically configured to query an information base according to the identifier of any information, and obtain data corresponding to the identifier of the information; and outputting page information, wherein the page information comprises the data.
Optionally, the information includes knowledge points, and the data includes: the names of the knowledge points, the information of similar questions corresponding to the knowledge points and the answers corresponding to the knowledge points.
Optionally, the information includes an intent, and the data includes: the name of the intention, the trigger corresponding to the intention, and the word slot corresponding to the intention.
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. 8 is a schematic structural diagram of an electronic device provided in the present application, and as shown in fig. 8, the electronic device of this embodiment includes: a processor 81, a memory 82; the processor 81 is communicatively connected to the memory 82. The memory 82 is used to store computer programs. The processor 81 is adapted to call a computer program stored in the memory 82 to implement the method in the above-described method embodiment.
Optionally, the electronic device further comprises: a transceiver 83 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 an information viewing scene;
receiving a viewing instruction input by a user;
and outputting at least one to-be-processed problem corresponding to the information according to the viewing instruction.
2. 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.
3. 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.
4. The method of claim 1, further comprising:
receiving a control instruction input by a user, wherein the control instruction comprises an identifier of a problem to be processed and an identifier of target information;
and establishing a target association relation between the problem to be processed and the target information according to the control instruction.
5. The method of claim 1, further comprising:
receiving a refreshing instruction input by a user;
and refreshing the page information of the information viewing scene according to the refreshing instruction.
6. The method of claim 1, wherein before outputting the page information of the information viewing scenario, further comprising:
receiving a selection instruction input by a user;
accordingly, the method can be used for solving the problems that,
the page information of the output information viewing scene comprises:
and outputting page information of the information viewing scene according to the selection instruction.
7. The method of claim 1, wherein outputting at least one to-be-processed question corresponding to the information according to the viewing instruction comprises:
determining an identity of the information;
determining the to-be-processed problem corresponding to the information identifier according to the information identifier, the preconfigured knowledge point and intention table and the preconfigured to-be-processed problem table, wherein at least one to-be-processed problem and each to-be-processed problem identifier are stored in the to-be-processed problem table, and at least one information identifier corresponding to the to-be-processed problem identifier is stored in the knowledge point and intention table.
8. The method of claim 1, wherein the outputting the page information of the information viewing scene comprises:
inquiring an information base according to any identifier of the information, and acquiring data corresponding to the identifier of the information;
and outputting page information, wherein the page information comprises the data.
9. The method of claim 8, wherein the information comprises knowledge points, and wherein the data comprises: the name of the knowledge point, the similar question information corresponding to the knowledge point and the answer corresponding to the knowledge point.
10. The method of claim 8, wherein the information comprises an intent, and wherein the data comprises: the name of the intention, the trigger corresponding to the intention, and the word slot corresponding to the intention.
11. A conversation robot problem processing apparatus combining RPA and AI, comprising:
the output module is used for outputting page information of the information viewing scene;
the receiving module is used for receiving a viewing instruction input by a user;
the output module is further used for outputting at least one to-be-processed question corresponding to the information according to the viewing instruction.
12. 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 to 10.
13. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, are configured to implement the method of any one of claims 1 to 10.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020106152802 | 2020-06-30 | ||
| CN202010615280 | 2020-06-30 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112000786A true CN112000786A (en) | 2020-11-27 |
Family
ID=73472503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010820949.1A Pending CN112000786A (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) | CN112000786A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113628758A (en) * | 2021-07-28 | 2021-11-09 | 北京来也网络科技有限公司 | Information processing method and device based on AI and RPA |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512228A (en) * | 2015-11-30 | 2016-04-20 | 北京光年无限科技有限公司 | Bidirectional question-answer data processing method and system based on intelligent robot |
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| 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 |
| CN109101624A (en) * | 2018-08-13 | 2018-12-28 | 腾讯科技（深圳）有限公司 | Dialog process method, apparatus, electronic equipment and storage medium |
| US20200125967A1 (en) * | 2018-10-18 | 2020-04-23 | Samsung Electronics Co., Ltd. | Electronic device and method for controlling the electronic device |
| CN111339280A (en) * | 2020-03-23 | 2020-06-26 | 上海奔影网络科技有限公司 | Question and answer sentence processing method, device, equipment and storage medium |
-
2020
- 2020-08-14 CN CN202010820949.1A patent/CN112000786A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512228A (en) * | 2015-11-30 | 2016-04-20 | 北京光年无限科技有限公司 | Bidirectional question-answer data processing method and system based on intelligent robot |
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| 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 |
| CN109101624A (en) * | 2018-08-13 | 2018-12-28 | 腾讯科技（深圳）有限公司 | Dialog process method, apparatus, electronic equipment and storage medium |
| US20200125967A1 (en) * | 2018-10-18 | 2020-04-23 | Samsung Electronics Co., Ltd. | Electronic device and method for controlling the electronic device |
| CN111339280A (en) * | 2020-03-23 | 2020-06-26 | 上海奔影网络科技有限公司 | Question and answer sentence processing method, device, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113628758A (en) * | 2021-07-28 | 2021-11-09 | 北京来也网络科技有限公司 | Information processing method and device based on AI and RPA |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3731161A1 (en) | Model application method and system, and model management method and server | |
| WO2020006827A1 (en) | Method and apparatus for intelligent response | |
| CN108519998B (en) | Problem guiding method and device based on knowledge graph | |
| CN111753075A (en) | Method and device for creating question and answer data of customer service robot and computer equipment | |
| CN111400473A (en) | Method and device for training intention recognition model, storage medium and electronic equipment | |
| CN112199007A (en) | Menu display method and device, electronic equipment and storage medium | |
| CN112507139A (en) | Knowledge graph-based question-answering method, system, equipment and storage medium | |
| CN112417122A (en) | Multi-turn question and answer method and device, computer readable storage medium and electronic equipment | |
| CN115544241A (en) | Intelligent pushing method and device for online operation | |
| CN111414217A (en) | Online teaching information feedback method, client, electronic equipment, medium and system | |
| CN111159344A (en) | Robot response method, device, equipment and storage medium | |
| CN112000786A (en) | Dialogue robot problem processing method, device and equipment combining RPA and AI | |
| CN113641804A (en) | Pre-training model obtaining method and device, electronic equipment and storage medium | |
| CN110750633B (en) | Method and device for determining answer of question | |
| CN109471935B (en) | Questionnaire survey object determining method and device, electronic equipment and storage medium | |
| CN115202907A (en) | Application program interface operation method, system, computer equipment and medium | |
| CN114816719A (en) | Training method and device of multi-task model | |
| CN113705816A (en) | Flow chart generation method, electronic device, device and readable storage medium | |
| CN113297371A (en) | Method, device and equipment for generating recommended question library and storage medium | |
| CN110472345B (en) | Post-processing system based on ABAQUS and implementation method | |
| CN114201594A (en) | Robot skill operating method, terminal and medium based on parameter expression knowledge base | |
| CN110727677B (en) | Method and device for tracing blood relationship of table in data warehouse | |
| CN113609268A (en) | Intelligent psychological knowledge question-answering method and device based on knowledge graph | |
| CN111897942A (en) | Dialogue robot problem processing method, device and equipment combining RPA and AI | |
| CN113628077A (en) | Method for generating non-repeated examination questions, terminal and readable 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 |