Method, device and equipment for handling problems of conversational robots combining RPA and AI

By combining RPA and AI, a method and device are provided to solve the problem of pending problem viewing that users cannot meet different needs, and the diversified operation of information viewing is realized, the correspondence between pending problem and information is optimized, and the user is improved Experience and the readability of the knowledge base.

CN112000786BActive Publication Date: 2024-11-05BEIJING LAIYE NETWORK TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010820949.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2020-06-30
Filing Date
2020-08-14
Publication Date
2024-11-05
Estimated Expiration
2040-08-14

AI Technical Summary

Technical Problem

In the prior art, users can only view the correspondence between the pending problem and the knowledge base information in a single way, and cannot meet the needs of different users.

Method used

By combining RPA and AI, a method and device is provided that allows users to view the corresponding relationship between pending issues and information through information, supports viewing, deleting, updating, controlling and refreshing operations, and uses natural language processing technology to identify user instructions, enriching the Information View the page information of the scene.

Benefits of technology

It realizes a simple and rich way for users to view the correspondence between pending problems and information through information, meets diverse needs, optimizes the correspondence between pending problems and information, and improves the readability of the user experience and knowledge base.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112000786B_ABST
    Figure CN112000786B_ABST
Patent Text Reader

Abstract

The present application provides a method, device and equipment for handling problems of a conversational robot in combination with RPA and AI, and relates to the technical field of artificial intelligence and natural language processing (NLP). The method includes outputting page information of an information viewing scene, receiving a viewing instruction input by a user, and outputting at least one pending problem corresponding to the information according to the viewing instruction. The present application enables users to view the corresponding relationship between pending problems and information through information through the method, and the viewing method is simple and enriched.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application number "202010615280.2" filed by Beijing Laiye Network Technology Co., Ltd. and Beijing Benying Network Technology Co., Ltd. on June 30, 2020, with application name "AI-based dialogue robot question review method, device and equipment". Technical Field

[0003] The embodiments of the present application relate to the technical field of artificial intelligence and natural language processing (NLP), and in particular to a method, device and equipment for handling problems of a conversational robot combining RPA and AI. Background Art

[0004] Robotic Process Automation (RPA) is a new technology science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence through specific "robot software". Research in the field of artificial intelligence includes robots, language recognition, image recognition, natural language processing (NLP) and expert systems. A conversational robot refers to a robot that can interact with users or complete corresponding tasks according to user instructions. The richness of the content included in the conversational robot's knowledge base has a great impact on the performance of the intelligent robot. In order to ensure the performance of the conversational robot, the knowledge base is usually updated and improved according to the pending problems so that the conversational robot can recognize the pending problems. Among them, the pending problems refer to the problems or instructions that the conversational robot cannot recognize.

[0005] When the user updates and improves the knowledge base according to the pending issues, the user needs to clarify the correspondence between the pending issues and the information in the knowledge base. In the prior art, the user selects the pending issue and then views the information in the knowledge base corresponding to the pending issue.

[0006] However, in the prior art, users can only view information corresponding to a certain pending issue, and the viewing method is single and cannot meet the different needs of users. Summary of the invention

[0007] The present application provides a method, device and equipment for problem handling of a conversational robot combining RPA and AI, which enables users to view the correspondence between pending problems and information through information. The viewing method is simple and enriched, and can meet the needs of more users.

[0008] In a first aspect, the present application provides a method for handling problems of a conversational robot combining RPA and AI, which is applied to an electronic device. The method includes: outputting page information of an information viewing scenario; receiving a viewing instruction input by a user; and outputting at least one pending question corresponding to the information according to the viewing instruction.

[0009] Optionally, the method further includes: receiving deletion information input by a user, wherein the deletion information includes an identification of the pending issues to be deleted; and deleting the pending issues to be deleted according to the deletion information.

[0010] Optionally, the method further includes: receiving update information input by a user and identification of pending issues that need to be updated; and updating the pending issues that need to be updated according to the update information.

[0011] Optionally, the method further includes: receiving a control instruction input by a user, the control instruction including an identifier of the problem to be processed and an identifier of the target information; and establishing a target association relationship between the problem to be processed and the target information according to the control instruction.

[0012] Optionally, the method further includes: receiving a refresh instruction input by a user; and refreshing page information of the information viewing scene according to the refresh instruction.

[0013] Optionally, before outputting the page information of the information viewing scene, the method further includes: receiving a selection instruction input by a user; the selection instruction may be obtained by identifying based on natural language processing (Natural Language Processing, NLP) technology;

[0014] Correspondingly, the page information of the output information viewing scene includes:

[0015] According to the selection instruction, page information of the information viewing scene is output.

[0016] Optionally, outputting at least one pending issue corresponding to the information according to the viewing instruction includes: determining the identification of the information; determining the pending issue corresponding to the identification of the information according to the identification of the information, a preconfigured knowledge point and intent table and a preconfigured pending issue table, the pending issue table storing at least one pending issue and the identification of each pending issue, and the knowledge point and intent table storing at least one information identification corresponding to the identification of the pending issue.

[0017] Optionally, the outputting of page information of the information viewing scenario includes: querying an information database according to an identifier of any information to obtain data corresponding to the identifier of the information; and outputting page information, wherein the page information includes the data.

[0018] Optionally, the information includes knowledge points, and the data includes: the name of the knowledge point, similar question information corresponding to the knowledge point, and the answer corresponding to the knowledge point.

[0019] Optionally, the information includes intent, and the data includes: the name of the intent, the trigger corresponding to the intent, and the word slot corresponding to the intent.

[0020] In a second aspect, the present application provides a conversational robot problem handling device combining RPA and AI, including:

[0021] The output module is used to output the page information of the information viewing scene.

[0022] The receiving module is used to receive the viewing instruction input by the user.

[0023] The output module is also used to output at least one pending issue corresponding to the information according to the viewing instruction.

[0024] Optionally, the receiving module is further used to receive deletion information input by the user, where the deletion information includes an identification of the pending issue to be deleted; and delete the pending issue to be deleted according to the deletion information.

[0025] Optionally, the receiving module is further used to receive update information input by the user and identifications of pending issues that need to be updated; and update the pending issues that need to be updated according to the update information.

[0026] Optionally, the receiving module is further used to receive a control instruction input by a user, wherein the control instruction includes an identifier of the problem to be processed and an identifier of the target information; and according to the control instruction, a target association relationship is established between the problem to be processed and the target information.

[0027] Optionally, the receiving module is further used to receive a refresh instruction input by a user; and refresh the page information of the information viewing scene according to the refresh instruction.

[0028] Optionally, the receiving module is also used to receive a selection instruction input by a user; the selection instruction can be identified based on natural language processing (NLP) technology; accordingly, the output module is specifically used to output page information of the information viewing scene according to the selection instruction.

[0029] Optionally, the output module is specifically used to determine the identification of the information; determine the pending problem corresponding to the identification of the information according to the identification of the information, a preconfigured knowledge point and intent table and a preconfigured pending problem table, the pending problem table storing at least one pending problem and the identification of each pending problem, and the knowledge point and intent table storing at least one information identification corresponding to the identification of the pending problem.

[0030] Optionally, the output module is specifically used to query the information database according to the identification of any information, and obtain data corresponding to the identification of the information; output page information, and the page information includes the data.

[0031] Optionally, the information includes knowledge points, and the data includes: the name of the knowledge point, similar question information corresponding to the knowledge point, and the answer corresponding to the knowledge point.

[0032] Optionally, the information includes intent, and the data includes: the name of the intent, the trigger corresponding to the intent, and the word slot corresponding to the intent.

[0033] In a third aspect, the present application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a method as in the first aspect or an optional manner of the first aspect.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement a method such as the first aspect or an optional method of the first aspect.

[0035] The technical solution provided by the embodiment of the present invention may include the following beneficial effects:

[0036] On the one hand, the conversational robot problem handling method, device and equipment combining RPA and AI provided in the present application receives viewing instructions input by users by outputting page information of information viewing scenarios; according to the viewing instructions, at least one pending problem corresponding to the information is output, so that users can view the correspondence between the pending problems and the information through the information, and the viewing method is simple and enriched.

[0037] On the other hand, by receiving deletion information input by the user, the deletion information includes the identification of the pending issues that need to be deleted; according to the deletion information, the pending issues that need to be deleted are deleted, the pending issues that do not match the information are deleted, and the correspondence between the pending issues and the information is optimized.

[0038] On the other hand, by receiving update information input by the user and identification of pending issues that need to be updated; updating the pending issues that need to be updated according to the update information, updating and improving the description of the pending issues, and improving the readability of the pending issues.

[0039] On the other hand, by receiving control instructions input by the user, the control instructions include the identification of the problem to be processed and the identification of the target information; according to the control instructions, a target association relationship is established between the problem to be processed and the target information, and the problem to be processed is transferred to a similar problem corresponding to the knowledge point or a word slot corresponding to the intention; it is also possible to receive refresh instructions input by the user; according to the refresh instructions, refresh the page information of the information viewing scene, refresh the page information, and present the latest correspondence between the information and the problem to be processed to the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A flowchart of a method for handling conversational robot problems combining RPA and AI provided in this application;

[0041] Figure 2 A schematic diagram of an interactive interface of an electronic device provided in this application;

[0042] Figure 3 Another schematic diagram of an interactive interface of an electronic device provided by the present application;

[0043] Figure 4 Another flowchart of the method for handling problems of a conversational robot combining RPA and AI provided in this application;

[0044] Figure 5 Another schematic diagram of an interactive interface of an electronic device provided by the present application;

[0045] Figure 6 Another schematic diagram of an interactive interface of an electronic device provided by the present application;

[0046] Figure 7 A structural diagram of a conversational robot problem handling device combining RPA and AI provided in this application;

[0047] Figure 8 A schematic diagram of the structure of an electronic device provided in this application.

[0048] The above drawings have shown clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0049] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0050] Below, the nouns involved in the embodiments of the present application are explained:

[0051] Open questions: Questions that the bot failed to answer correctly or tasks that the bot failed to respond to correctly.

[0052] Knowledge point: A collection of multiple similar questions and responses to a certain question.

[0053] Intent: The task that the user asks the bot to complete. For example, shut down the computer.

[0054] Similar questions: Different ways of expressing a problem.

[0055] Trigger: An "intention flow" consisting of multiple rounds of interactions.

[0056] Slots: are variables that need to be satisfied in order to complete a specific task.

[0057] The dialogue is to simulate the operation of people on the computer through specific robot software, and automatically execute the process tasks according to the rules. The richness of the content included in the knowledge base of the dialogue robot has a great impact on the performance of the intelligent robot. In order to ensure the performance of the dialogue robot, the knowledge base is usually updated and improved according to the pending problems so that the dialogue robot can recognize the pending problems. Among them, the pending problems refer to the problems or instructions that the dialogue robot cannot recognize.

[0058] When the user updates and improves the knowledge base according to the pending issues, the user needs to clarify the correspondence between the pending issues and the information in the knowledge base. In the prior art, the user selects the pending issue and then views the information in the knowledge base corresponding to the pending issue.

[0059] However, in the prior art, users can only view information corresponding to a certain pending issue, and the viewing method is single and cannot meet the different needs of users.

[0060] If the corresponding pending issues can be viewed according to the information, it can not only enrich the viewing method, but also meet the needs of different users. Based on this, the present application provides a conversational robot problem handling method combining RPA and AI, by outputting page information of the information viewing scene; receiving the viewing instruction input by the user; and outputting at least one pending issue corresponding to the information according to the viewing instruction. It enables users to view the corresponding pending issues according to the information, enriching the viewing method of the corresponding relationship between information and pending issues.

[0061] Figure 1 A flowchart of a method for handling problems of a conversational robot combining RPA and AI provided in this application, which is applied to electronic devices such as Figure 1 As shown, the method includes:

[0062] S101, outputting page information of an information viewing scene.

[0063] The electronic device can output the page information of the information viewing scenario through its human-computer interaction interface. The information can be a knowledge point or an intent, and accordingly, the page information can include the name of the knowledge point, similar questions corresponding to the knowledge point, answers corresponding to the knowledge point, attribute information of the pending questions corresponding to the knowledge point, etc.; or, the page information can include the name of the intent, the trigger corresponding to the intent, the word slot corresponding to the intent, attribute information of the pending questions corresponding to the intent, etc., wherein the attribute information of the pending questions can include the content information of the pending questions, the number of pending questions, etc. The following is an example of the page information of the information viewing scenario output by the electronic device through a schematic diagram. Figure 2 A schematic diagram of an interactive interface of an electronic device provided in this application, such as Figure 2 As shown, the page information shown in the interactive interface includes a knowledge point named "Where to view coupons"; similar questions corresponding to the knowledge point include "Are there coupons, how to view coupons, where are the coupons", and the answer corresponding to the knowledge point is "Please click My Coupons to view the coupons you have." Figure 2 The page information shown also includes the number of pending questions corresponding to the knowledge point, specifically "284".

[0064] S102: Receive a viewing instruction input by a user.

[0065] The electronic device can receive the viewing instruction input by the user through its human-computer interaction interface. Figure 2 , users can click the "View" button and enter the view command to view the pending issues corresponding to the knowledge point.

[0066] S103. According to the viewing instruction, output at least one pending issue corresponding to the information.

[0067] After receiving the user's input, the electronic device displays and outputs at least one pending question corresponding to the information through its interactive interface. The following is an illustration: Figure 3 Another schematic diagram of the interactive interface of the electronic device provided in this application, such as Figure 3 As shown, after the user clicks the "View" button on the 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 the second page 302, and outputs at least one pending issue corresponding to the information to the second page 302.

[0068] The conversational robot problem handling method combining RPA and AI provided in the present application outputs page information of an information viewing scenario; receives a viewing instruction input by a user; and outputs at least one pending issue corresponding to the information according to the viewing instruction, so that the user can view the pending issues related to a certain information. Compared with the prior art that can only view the information corresponding to the pending issue through the pending issue, this method can enrich the viewing method of the correspondence between the information and the pending issues, and meet the viewing needs of different users.

[0069] Different users may be interested in different information. To meet the needs of different users, before S101 in the above embodiment, the information may be filtered according to the needs of the users. Figure 4 Another flowchart of the method for handling problems of a conversational robot combining RPA and AI provided in this application is provided, and the method is applied to electronic devices, such as Figure 4 As shown, the method includes:

[0070] S401: Receive a selection instruction input by a user.

[0071] The electronic device can receive the selection instruction input by the user through its interactive interface, and can also receive the selection instruction input by the user through its voice device. As a possible implementation method, the voice input by the user is collected by the voice device, and the selection instruction carried in the user's voice is recognized by using a pre-trained recognition model based on natural language processing (Natural Language Processing, NLP) technology.

[0072] S402: According to the selection instruction, the page information of the information viewing scene is output.

[0073] The information may be a knowledge point or an intention.

[0074] Optionally, a possible implementation of outputting page information of the information viewing scenario is: according to the identifier of any information, querying the information library to obtain data corresponding to the identifier of the information; and outputting the page information, wherein the page information includes the data. This method can accurately obtain the corresponding data according to the identifier of any information.

[0075] Optionally, the information includes knowledge points, and the data includes: the name of the knowledge point, similar question information corresponding to the knowledge point, and the answer corresponding to the knowledge point.

[0076] Optionally, the information includes intent, and the data includes: the name of the intent, the trigger corresponding to the intent, and the word slot corresponding to the intent.

[0077] The following is an example of an electronic device receiving a selection instruction input by a user through its interactive interface. Figure 5 Another schematic diagram of the interactive interface of the electronic device provided in this application is as follows: Figure 5 As shown, the user clicks the "View by Knowledge Point" button on the interactive interface of the electronic device to enter the page shown in the third page 501. The third page 501 includes data related to the knowledge point, including the name of the knowledge point, similar question information corresponding to the knowledge point, and the answer corresponding to the knowledge point; the user can also jump from the third page 501 to the fourth interface 502 by clicking "View by Intent" on the third page 501. The fourth page 502 includes data related to the intent, including the name of the intent, the trigger corresponding to the intent, and the word slot corresponding to the intent.

[0078] Specifically, a possible implementation method of outputting page information of the information viewing scenario according to the selection instruction is: outputting page information of the information viewing scenario according to the selection instruction and the preconfigured knowledge point and intention table. The selection instruction includes the type of information and / or the confidence value corresponding to the information.

[0079] For example, see Figure 5 , assuming that the user clicks the "View by knowledge point" button, a selection instruction is output to the electronic device, and the type of information included in the selection instruction is knowledge point; assuming that the user clicks the "View by intention" button, a selection instruction is output to the electronic device, and the type of information included in the selection instruction is intention.

[0080] S403: Receive a viewing instruction input by the user.

[0081] S403 is similar to S102. For detailed description, please refer to S102, which will not be described in detail here.

[0082] S404. According to the viewing instruction, output at least one pending issue corresponding to the information.

[0083] Optionally, according to the viewing instruction, a possible implementation method of outputting at least one pending problem corresponding to the information is: determining the identification of the information; determining the pending problem corresponding to the identification of the information according to the identification of the information, a preconfigured knowledge point and intent table and a preconfigured pending problem table, the pending problem table storing at least one pending problem and the identification of each pending problem, and the knowledge point and intent table storing at least one information identification corresponding to the identification of the pending problem.

[0084] For example, Table 1 is a table of pending issues provided in this application, and Table 2 is a table of knowledge points and intentions provided in this application. Assuming that the information is identified as "rec_id-021", according to Table 1 and Table 2, the pending issues corresponding to the information identified as "rec_id-021" are identified as "id-001" and "id-003"; the pending issue identified as "id-001" is "Where is the coupon"; the pending issue identified as "id-003" is "Are there any coupons?"

[0085] Table 1 List of pending issues

[0086] Issue ID Pending issues id-001 Where is the coupon? id-002 Is the weather good? id-003 Are there any coupons?

[0087] Table 2 Knowledge points and intention table

[0088]

[0089] Through the above steps, the user may view at least one pending issue corresponding to any information. After processing and analysis, it can be determined whether the corresponding relationship between the pending issue and the information is reasonable. If the corresponding relationship between a pending issue and the information is unreasonable, the user can cancel the corresponding relationship between the pending issue and the information.

[0090] Based on this, optionally, it may also include:

[0091] S405: receiving deletion information input by the user, wherein the deletion information includes an identifier of the pending issue to be deleted.

[0092] The electronic device can receive a deletion instruction input by the user through the interactive interface.

[0093] S406. Delete the pending issues that need to be deleted according to the deletion information.

[0094] Figure 6 Another schematic diagram of the interactive interface of the electronic device provided in this application is as follows: Figure 6As shown, the user can delete any pending issue by clicking the "Delete" button corresponding to the pending issue. To improve the deletion efficiency, the user can also check the pending issues to be deleted, and then click the "Batch Delete" button to delete the checked pending issues. It can be understood that the above two deletion methods can exist at the same time or be applied separately.

[0095] Of course, through the above steps, the user may view at least one pending issue corresponding to any information. After processing and analysis, if it is determined that the correspondence between a pending issue and the information is reasonable, the user can establish a target association relationship between the pending issue and the information. Specifically, when the information is a knowledge point, the information can be determined as a similar issue to the knowledge point; when the information is an intention, the information can be determined as a trigger of the intention.

[0096] Based on this, optionally, it may also include:

[0097] S407: Receive a control instruction input by a user.

[0098] The electronic device can receive control instructions input by the user through the interactive interface.

[0099] S408: Establish a target association relationship between the problem to be processed and the information according to the control instruction.

[0100] Continue to see Figure 6 , the user can click the "Transfer" button corresponding to any pending issue to establish a target association relationship between the pending issue and the information. Specifically, when the information is a knowledge point, the pending issue can be transferred to a similar issue of the knowledge point by clicking the "Transfer" button; when the information is an intention, the pending issue can be transferred to a trigger of the intention by clicking the "Transfer" button. Similarly, to improve the transfer efficiency, the user can also check the pending issues that need to be transferred, and then click the "Batch Transfer" button to establish a target association relationship between the checked pending issues and the information. It can be understood that the above two deletion methods can exist at the same time or be applied separately.

[0101] Unprocessed questions are generated when the user asks a question or issues an action command to the conversation robot, but the robot fails to accurately answer or correctly execute the action command. It is understandable that unprocessed questions may be generated because the user's expression is not accurate enough, or because the conversation robot fails to accurately identify the question. In order to accurately express unprocessed questions and improve the readability of unprocessed questions, the following options may also be included:

[0102] S409: Receive the update information input by the user and the identification of the pending problem that needs to be updated.

[0103] The electronic device may receive update information and identification of pending issues that need to be updated input by the user through the interactive interface.

[0104] S410. Update pending issues that need to be updated according to the update information.

[0105] This method can be used to supplement and improve incomplete and unclear issues to be addressed, thereby improving the readability of the issues to be addressed.

[0106] Based on the fact that a user may delete a pending issue corresponding to a certain information, or establish a target association relationship between a pending issue and the information, the pending issue corresponding to the information may change. In order to timely understand the status of the pending issue currently corresponding to a certain information, the following may be optionally included:

[0107] S411: Receive a refresh instruction input by a user.

[0108] The electronic device can receive a refresh instruction input by the user through the interactive interface.

[0109] S412. Refresh the page information of the information viewing scene according to the refresh instruction.

[0110] Continue to see Figure 2 The user can click the "refresh" button to input a refresh instruction, so that the electronic device can refresh the page information of the information viewing scene according to the refresh instruction. For example, the number of pending issues corresponding to the refresh information, similar issues corresponding to the information, etc.

[0111] The conversational robot problem handling method combining RPA and AI provided in the present application, based on the above-mentioned embodiments, receives selection instructions input by the user, and outputs page information of the information viewing scenario according to the selection instructions, thereby meeting the query needs of different users and improving the user experience.

[0112] Figure 7 A structural diagram of a conversational robot problem handling device combining RPA and AI provided in this application, such as Figure 7 As shown, the device comprises:

[0113] The output module 71 is used to output the page information of the information viewing scene.

[0114] The receiving module 72 is used to receive a viewing instruction input by a user.

[0115] The output module 71 is also used to output at least one pending issue corresponding to the information according to the viewing instruction.

[0116] Optionally, the receiving module 72 is further configured to receive deletion information input by a user, wherein the deletion information includes an identification of the pending issue to be deleted; and delete the pending issue to be deleted according to the deletion information.

[0117] Optionally, the receiving module 72 is further configured to receive update information input by a user and identifiers of pending issues that need to be updated; and update the pending issues that need to be updated according to the update information.

[0118] Optionally, the receiving module 72 is further configured to receive a control instruction input by a user, wherein the control instruction includes an identifier of the problem to be processed and an identifier of the target information; and establish a target association relationship between the problem to be processed and the target information according to the control instruction.

[0119] Optionally, the receiving module 72 is further used to receive a refresh instruction input by a user; and refresh the page information of the information viewing scene according to the refresh instruction.

[0120] Optionally, the receiving module 72 is further used to receive a selection instruction input by a user; correspondingly, the output module 71 is specifically used to output page information of the information viewing scene according to the selection instruction.

[0121] Optionally, the output module 71 is specifically used to determine the identification of the information; determine the pending problem corresponding to the identification of the information according to the identification of the information, a preconfigured knowledge point and intent table and a preconfigured pending problem table, the pending problem table storing at least one pending problem and the identification of each pending problem, and the knowledge point and intent table storing at least one information identification corresponding to the identification of the pending problem.

[0122] Optionally, the output module 71 is specifically used to query the information database according to the identification of any information, obtain data corresponding to the identification of the information; and output page information, which includes the data.

[0123] Optionally, the information includes knowledge points, and the data includes: the name of the knowledge point, similar question information corresponding to the knowledge point, and the answer corresponding to the knowledge point.

[0124] Optionally, the information includes intent, and the data includes: the name of the intent, the trigger corresponding to the intent, and the word slot corresponding to the intent.

[0125] The conversational robot problem handling device combining RPA and AI can execute the above-mentioned conversational robot problem handling method combining RPA and AI. Its content and effects can be referred to the method embodiment part, which will not be repeated here.

[0126] Figure 8 A schematic diagram of the structure of an electronic device provided in this application, such as Figure 8 As shown, the electronic device of this embodiment includes: a processor 81 and a memory 82; the processor 81 is communicatively connected with the memory 82. The memory 82 is used to store computer programs. The processor 81 is used to call the computer program stored in the memory 82 to implement the method in the above method embodiment.

[0127] Optionally, the electronic device further includes: a transceiver 83 for communicating with other devices.

[0128] The electronic device can execute the above-mentioned conversational robot problem handling method combining RPA and AI. Its content and effects can be referred to the method implementation example part, which will not be repeated here.

[0129] The present application also provides a computer-readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed by a processor, they are used to implement the above-mentioned conversational robot problem handling method combining RPA and AI.

[0130] The computer executable instructions stored in the computer-readable storage medium can implement the above-mentioned conversational robot problem handling method combining RPA and AI when executed by the processor. Its content and effects can be referred to the method implementation example part, which will not be repeated here.

[0131] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are considered to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims. It should be understood that the present disclosure is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for handling problems of a conversational robot combining RPA and AI, characterized in that: Applied to electronic equipment, the method comprises: Receiving a selection instruction input by a user; the selection instruction is identified based on natural language processing (Natural Language Processing, NLP) technology; According to the selection instruction, output the page information of the information viewing scene; the page information includes the number of issues to be processed; Outputting at least one of the pending issues corresponding to the information according to the viewing instruction; Wherein, outputting at least one pending issue corresponding to the information according to the viewing instruction includes: determining an identity of the information; Determine the to-be-processed problem corresponding to the identifier of the information according to the identifier of the information, the preconfigured knowledge point and intent table, and the preconfigured to-be-processed problem table, wherein the to-be-processed problem table stores at least one to-be-processed problem and the identifier of each to-be-processed problem, and the knowledge point and intent table stores the identifier of at least one information corresponding to the identifier of the to-be-processed problem; The method further comprises: Receiving a control instruction input by the user, wherein the control instruction includes an identification of a problem to be processed and an identification of target information; According to the control instruction, a target association relationship is established between the problem to be processed and the target information; The output information viewing scene page information includes: According to the identifier of any of the information, query the information database to obtain data corresponding to the identifier of the information; Outputting page information, wherein the page information includes the data.

2. The method according to claim 1, characterized in that The method further comprises: Receiving deletion information input by a user, wherein the deletion information includes an identification of a pending issue to be deleted; According to the deletion information, the pending issues that need to be deleted are deleted.

3. The method according to claim 1, characterized in that The method further comprises: receiving update information input by the user and identification of pending issues that need to be updated; According to the update information, the pending issues that need to be updated are updated.

4. The method according to claim 1, characterized in that: The method further comprises: Receive refresh instructions input by the user; According to the refresh instruction, the page information of the information viewing scene is refreshed.

5. The method according to claim 1, characterized in that The information includes knowledge points, and the data includes: the name of the knowledge point, similar question information corresponding to the knowledge point, and the answer corresponding to the knowledge point.

6. The method according to claim 1, characterized in that The information includes intent, and the data includes: the name of the intent, the trigger corresponding to the intent, and the word slot corresponding to the intent.

7. A conversational robot problem handling device combining RPA and AI, characterized in that: include: A receiving module, used for receiving a selection instruction input by a user; The selection instruction is identified based on Natural Language Processing (NLP) technology; An output module, used to output page information of the information viewing scene according to the selection instruction; the page information includes the number of issues to be processed; The output module is further used to output at least one of the pending issues corresponding to the information according to the viewing instruction; The output module is specifically used to determine the identification of the information; Determine the to-be-processed problem corresponding to the identifier of the information according to the identifier of the information, the preconfigured knowledge point and intent table, and the preconfigured to-be-processed problem table, wherein the to-be-processed problem table stores at least one to-be-processed problem and the identifier of each to-be-processed problem, and the knowledge point and intent table stores the identifier of at least one information corresponding to the identifier of the to-be-processed problem; The receiving module is further configured to receive a control instruction input by the user, wherein the control instruction includes an identifier of the problem to be processed and an identifier of the target information; and establish a target association relationship between the problem to be processed and the target information according to the control instruction; The output module is further used to query the information database according to the identifier of any of the information, obtain data corresponding to the identifier of the information, and output page information, wherein the page information includes the data.

8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.