CN113704185A - Message reply method, device, equipment and medium based on RPA and AI - Google Patents
Message reply method, device, equipment and medium based on RPA and AI Download PDFInfo
- Publication number
- CN113704185A CN113704185A CN202111014662.0A CN202111014662A CN113704185A CN 113704185 A CN113704185 A CN 113704185A CN 202111014662 A CN202111014662 A CN 202111014662A CN 113704185 A CN113704185 A CN 113704185A
- Authority
- CN
- China
- Prior art keywords
- file
- rpa
- user
- robot
- knowledge corpus
- 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
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000001960 triggered effect Effects 0.000 claims description 15
- 238000003058 natural language processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 230000008676 import Effects 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 description 42
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000004801 process automation Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 235000019082 Osmanthus Nutrition 0.000 description 1
- 241000333181 Osmanthus Species 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G06F16/10—File systems; File servers
- G06F16/14—Details of searching files based on file metadata
- G06F16/148—File search 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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
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)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a message reply method, a device, equipment and a medium based on RPA and AI, wherein the method comprises the following steps: s1, identifying the file query sentence input by the user; s2, according to the recognition result, if the file link corresponding to the file query sentence exists in the knowledge corpus, returning the file link to the user; in the knowledge corpus, each file link and the corresponding file name are obtained from a shared storage space by the RPA robot at regular time and are added into the knowledge corpus. By adopting the technical scheme, the problem that the conversation robot cannot dynamically update the file link is solved.
Description
Technical Field
The embodiment of the invention relates to the technical field of flow automation, in particular to a message reply method, a message reply device, message reply equipment and a message reply medium based on RPA and AI.
Background
RPA (robot Process Automation) simulates human operations on a computer through specific "robot software" and automatically executes Process tasks according to rules.
AI (Artificial Intelligence) is a new technical science for studying and developing theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence.
RPA has unique advantages: low code, non-intrusive. The low code means that the RPA can be operated without high IT level, and business personnel who do not know programming can also develop the flow; non-invasively, the RPA can simulate human operation without opening the interface with a software system. However, conventional RPA has certain limitations: can only be based on fixed rules and application scenarios are limited. With the continuous development of the AI technology, the limitation of the traditional RPA is overcome by the deep fusion of the RPA and the AI, and the RPA + AI is a Hand work + Head work, which greatly changes the value of the labor force.
Currently, with the development of artificial intelligence technology, AI-based dialogue robots are more and more commonly used in daily life. The dialogue robot replies corresponding answers according to the question sentences of the user. In order to solve the problem that the manual searching of the files by workers wastes time and labor, a function of automatically replying the file link can be set for the conversation robot. The implementation of this function requires setting file links in the dialog bot in advance. However, if the file link changes or a new file appears, the file link in the conversation robot needs to be modified manually. The process of manually modifying the link is quite complicated, the efficiency is low, and the usability and the use satisfaction degree of the conversation robot are greatly reduced.
Disclosure of Invention
The embodiment of the invention provides a message reply method, a message reply device, message reply equipment and a message reply medium based on RPA and AI, which are used for solving the problem that a conversation robot cannot dynamically update file links.
In a first aspect, the present invention provides a message reply method for RPA and AI, which is applied to a conversation robot, and includes:
s1, identifying the file query sentence input by the user;
s2, according to the recognition result, if the file link corresponding to the file query sentence exists in the knowledge corpus, returning the file link to the user;
in the knowledge corpus, each file link and the corresponding file name are obtained from a shared storage space by the RPA robot at regular time and are added into the knowledge corpus.
Optionally, the method further includes:
s3, according to the recognition result, if the fact that the link of the answer corresponding to the file query sentence does not exist in the knowledge corpus is determined, the prompt information containing the query file option is returned to the user;
and S4, if receiving a directory query instruction triggered by the user according to the prompt information, returning secondary directory prompt information according to the directory query instruction, and returning the file name of the target file content and the corresponding link to the user when receiving the query instruction of the target file content triggered by the user.
Optionally, the prompt information further includes a submission requirement candidate of the file to be queried; correspondingly, the method further comprises the following steps:
and S5, if a file submission instruction triggered by the user based on the submission requirement information is received, sending the submission requirement information to a set mailbox.
Optionally, the S2 includes:
s21, judging whether a standard problem corresponding to the file query sentence exists in the knowledge corpus or not according to the recognition result;
s22, if the knowledge corpus does not have the standard problem corresponding to the file query sentence, judging whether the knowledge corpus has a similar problem corresponding to the file query sentence;
s23, if the knowledge corpus has similar problems corresponding to the file query sentences, determining a target similar problem with the highest similarity to the file query sentences from all similar problems;
and S24, taking the file link corresponding to the target similar question as an answer of the file query statement, and returning the answer to the user.
Optionally, the S1 includes:
and identifying the file query sentence input by the user by utilizing a semantic identification algorithm in the natural language processing NLP to obtain a keyword in the file query sentence as an identification result.
In a second aspect, an embodiment of the present invention further provides a message reply method based on RPA and AI, which is applied to an RPA robot, and the method includes:
s6, regularly acquiring file names and links of all files in the shared storage space;
and S7, adding the file names and the links of all the files into a knowledge corpus of the conversation robot according to a preset knowledge corpus template rule, wherein the knowledge corpus is used for providing corresponding file links for the file query sentences identified by the conversation robot.
Optionally, the preset knowledge base template rule includes:
the similar problems of the preset knowledge base template comprise file names of the files and the hierarchical relation of the folders in which the files are located.
In a third aspect, an embodiment of the present invention further provides a message reply device based on RPA and AI, where the message reply device includes:
a file query statement identification module configured to: identifying a file query sentence input by a user;
a file link return module configured to: according to the recognition result, if the file link corresponding to the file query sentence exists in the knowledge corpus, returning the file link to the user;
in the knowledge corpus, each file link and the corresponding file name are obtained from a shared storage space by the RPA robot at regular time and are added into the knowledge corpus.
Optionally, the apparatus further comprises:
a hint information return module configured to: according to the recognition result, if the fact that the link of the answer corresponding to the file query sentence does not exist in the knowledge corpus is determined, the prompt information containing the query file alternative is returned to the user;
a secondary hint information return module configured to: if receiving a directory query instruction triggered by the user according to the prompt information, returning secondary directory prompt information according to the directory query instruction, and returning the file name of the target file content and the corresponding link to the user when receiving a query instruction of the target file content triggered by the user.
Optionally, the prompt information further includes a submission requirement candidate of the file to be queried; correspondingly, the device further comprises:
a submission requirements information sending module configured to: and if a file submitting instruction triggered by the user based on the submitting requirement information is received, sending the submitting requirement information to a set mailbox.
Optionally, the file link returning module is specifically configured to:
judging whether a standard problem corresponding to the file query statement exists in the knowledge corpus or not according to the recognition result;
if the knowledge corpus does not have the standard problem corresponding to the file query statement, judging whether a similar problem corresponding to the file query statement exists in the knowledge corpus or not;
if the similar problems corresponding to the file query statement exist in the knowledge corpus, determining a target similar problem with the highest similarity to the file query statement from all similar problems;
and taking the file link corresponding to the target similar question as an answer of the file query statement, and returning the answer to the user.
Optionally, the file query statement identification module is specifically configured to:
and identifying the file query sentence input by the user by utilizing a semantic identification algorithm in the natural language processing NLP to obtain a keyword in the file query sentence as an identification result.
In a fourth aspect, an embodiment of the present invention further provides a message reply device based on RPA and AI, where the message reply device includes:
an information acquisition module configured to: regularly acquiring file names and links of all files in the shared storage space;
an information import module configured to: and adding the file names and the links of all the files into a knowledge corpus of the conversation robot according to a preset knowledge corpus template rule, wherein the knowledge corpus is used for providing corresponding file links for the file query sentences identified by the conversation robot.
Optionally, the preset knowledge base template rule includes:
the similar problems of the preset knowledge base template comprise file names of the files and the hierarchical relation of the folders in which the files are located.
In a fifth aspect, an embodiment of the present invention further provides a computing device, including:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program codes stored in the memory to execute the RPA and AI based message reply method applied to the dialogue robot provided by any embodiment of the invention.
In a sixth aspect, an embodiment of the present invention further provides a computing device, including:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program codes stored in the memory to execute the RPA and AI based message reply method applied to the RPA robot provided by any embodiment of the invention.
In a seventh aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the RPA and AI-based message reply method applied to the conversation robot, provided in any embodiment of the present invention.
In an eighth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the RPA and AI-based message reply method applied to an RPA robot, according to any of the embodiments of the present invention.
According to the technical scheme provided by the embodiment of the invention, the RPA is combined with the conversation robot, the file names and the links of all the files in the shared storage space are acquired at regular time through the RPA robot, and the acquired file names and the links are automatically updated into the language database of the conversation robot, so that the problem that the conversation robot cannot dynamically update the file links is solved, and the time for manually updating the file links by a user is saved. In the process that the user inquires the files through the conversation robot, the conversation robot can automatically send the links corresponding to the latest files to the user, so that the operation of manually logging in the shared storage space to search the files is avoided, the operation time is saved, and the working efficiency is improved.
The innovation points of the embodiment of the invention comprise:
1. the RPA is combined with the conversation robot, the file names and the links of all the files in the shared storage space are acquired at regular time through the RPA robot, and the acquired file names and the links are automatically updated into the language database of the conversation robot, so that the problem that the conversation robot cannot dynamically update the file links is solved, and the method is one of innovation points of the embodiment of the invention.
2. The method comprises the steps of identifying a file query statement input by a user by utilizing a semantic identification algorithm in Natural Language Processing (NLP), returning prompt information containing query file alternatives to the user when determining that a link corresponding to an answer of the file query statement introduced by an RPA robot does not exist in a knowledge corpus according to an identification result, providing more options for the user under the condition that the answer of a question of the user cannot be given, and improving the usability and user experience of a conversation robot.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1a is a flowchart of a message reply method based on RPA and AI according to an embodiment of the present invention;
fig. 1b is a screenshot of a timing plan set for an RPA robot according to an embodiment of the present invention;
fig. 1c is a screenshot of an RPA robot entering a shared storage space to obtain a file name and its link according to an embodiment of the present invention;
FIG. 1d is a screenshot of a default knowledge base template according to an embodiment of the present invention;
fig. 2a is a flowchart of a message reply method based on RPA and AI according to a second embodiment of the present invention;
fig. 2b is a screenshot of an effect of a conversation robot answering a user question according to a second embodiment of the present invention;
fig. 2c is a screenshot of an effect that the conversation robot returns to the user to inquire the prompt information according to the second embodiment of the present invention;
fig. 3 is a block diagram of a message reply apparatus based on RPA and AI according to a third embodiment of the present invention;
fig. 4 is a block diagram of a message reply apparatus based on RPA and AI according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computing device according to a fifth embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
In the description of the embodiments of the present invention, the term "conversation robot" broadly refers to a computer program capable of conversational interaction with a human being through voice or text.
In the description of the embodiments of the present invention, the term "knowledge corpus" is a structured set formed by a plurality of knowledge points in a business field. Each knowledge point in the knowledge base consists of a question and an answer. Creating a knowledge point requires a standard question, a plurality of similar questions, and one or more answers.
In the description of the embodiments of the present invention, the term "similar problem" refers to a plurality of problems that are semantically highly similar or consistent with the standard problem of the knowledge point to which it belongs, for example, a different expression of a certain problem, and the like.
In order to clearly and clearly explain the contents of the embodiments of the present invention, the following briefly introduces the basic operation principle of the embodiments of the present invention.
Robot Process Automation (RPA) is a Process task that simulates human operations on a computer through specific robot software and automatically executes according to rules.
Ai (intellectual intelligence) is an english abbreviation for artificial intelligence, which is a new technical science for studying and developing theories, methods, techniques and application systems for simulating, extending and expanding human intelligence. The application of AI-based dialogue robots in daily life is becoming more common, for example, semantic recognition of a question sentence of a user and returning an answer to the question sentence can be performed.
At present, both the RPA and the conversation robot are widely applied, the RPA can generally replace manual execution of repetitive work, the conversation robot can be applied to specific industries such as customer service, and the like, and both the RPA and the conversation robot lighten the work of people in respective fields. For the conversation robot, if the function of automatically replying to the file link is to be realized, the file link can be set in the conversation robot in advance. If the file link changes or a new file appears, the file link in the conversation robot needs to be modified manually. In consideration of the problem of low manual operation efficiency, the technical scheme provided by the embodiment of the invention combines the RPA and the dialogue robot, and solves the problem that the dialogue robot cannot dynamically update the file link by adopting the RPA technology to replace a mode of manually acquiring and updating the file link. The dialogue robot can identify the file query sentence of the user by adopting a semantic identification method in NLP (Natural Language Processing), and sends the latest link of the file to be queried of the user to the user according to an identification result, thereby achieving a full-automatic effect.
Hereinafter, the message reply method, device, apparatus, and medium based on RPA and AI according to the embodiments of the present invention will be described in detail from the perspective of the RPA robot and the conversation robot, respectively.
Example one
Fig. 1a is a flowchart of a message reply method based on RPA and AI according to an embodiment of the present invention, where an execution subject of the method is an RPA robot. Typically, the method can be applied to general office software, such as enterprise WeChat or flybook office software. These office software have shared storage space for corporate files. The RPA robot can acquire all files and corresponding links from the shared storage space and add the files and the corresponding links to the knowledge corpus of the conversation robot. The RPA and AI based conversation robot reply method provided by this embodiment can be executed by an RPA and AI based message reply device, which can be implemented by software and/or hardware. As shown in fig. 1a, the method comprises:
and S110, regularly acquiring file names and links of all files in the shared storage space.
The shared storage space stores document data for enterprise employees to view or download, such as company introduction, employee rules, technical documents, product data, and the like. The shared storage space may be a shared space of office software such as enterprise WeChat or flybook, or a cloud space used by enterprise applications.
In this embodiment, a timing plan may be set for the RPA robot, and the RPA robot may acquire file names and their links of all files in the shared storage space according to the set timing plan. The time in the timing plan can be set according to actual conditions, for example, the time can be set according to the update speed of the file in the shared storage space.
Specifically, fig. 1b is a screenshot of a timing plan set for an RPA robot according to an embodiment of the present invention, and fig. 1c is a screenshot of a file name and a link thereof obtained when the RPA robot enters a shared storage space according to an embodiment of the present invention. As shown in fig. 1b, the RPA robot logs in the shared space as shown in fig. 1c at 5 o' clock every day, and acquires file names and links thereof for all files in the shared space. Regardless of the situation of file addition or deletion in the shared storage space, the RPA can automatically update the latest file link to the corpus of the conversation robot, so that the operation of manually updating the corpus is saved, and the problem that the conversation robot cannot dynamically update the file link is solved.
When the RPA robot acquires the file names of all files in the shared storage space, the RPA robot can also store the hierarchical relationship among the folders in which the files are located. As shown in FIG. 1c, a 1 company introduction > document indicates a hierarchical relationship between folders in which a document is located, that is, a folder name of a file at the upper level of the document shown in FIG. 1c is "1 company introduction", and a folder name of a file at the upper level of the "1 company introduction" is "1 company introduction". The RPA robot may also acquire the hierarchical relationship when acquiring the file name and the file link of the document shown in fig. 1 c. The obtained hierarchical relation can be used for constructing similar problems of the preset knowledge base template.
And S120, adding the file names and the links of all the files into a knowledge corpus of the conversation robot according to a preset knowledge corpus template rule, wherein the knowledge corpus is used for providing corresponding file links for the file query sentences recognized by the conversation robot.
The knowledge corpus is a structured set formed by a plurality of knowledge points in a certain business field. Each knowledge point in the knowledge base consists of a question and an answer. Creating a knowledge point requires a standard question, a plurality of similar questions, and one or more answers. The similarity problem refers to a plurality of problems that are highly similar or consistent with the standard problem semantics of the knowledge points to which the similarity problem belongs, for example, a different expression of a certain problem. In this embodiment, the answer to the knowledge point is a file link of the file in the shared storage space.
In this embodiment, the RPA robot adds the filenames and the links of all documents to the knowledge corpus of the conversation robot according to the preset knowledge corpus template rule, and may specifically implement the following method:
the file names and the links of all the files are written into a preset knowledge base template, and then the preset knowledge base template is imported into a knowledge corpus of the conversation robot. In order to meet the requirement of creating the knowledge corpus, the preset knowledge base template is also provided with standard questions, similar questions and answers corresponding to each file link. In this embodiment, the standard problem may be composed of a file name and a file type thereof, and the similarity problem refers to a problem that the similarity of the standard problem with the knowledge point to which the standard problem belongs reaches a set threshold, for example, a statement that the same file name is different.
Further, the RPA robot may write the hierarchical relationship of folders in which the files acquired from the shared storage space are located into a similar problem. Fig. 1d is a screenshot of a preset knowledge base template according to an embodiment of the present invention. As shown in fig. 1d, the similar problem includes the file names of the files and the hierarchical relationship of the folders in which the files are located, for example, "organization architecture < < < <4 company architecture < < company introduction", the hierarchical relationship indicates that the folder name of the file at the previous level of the "organization architecture" is "4 company architecture", and the folder name of the file at the previous level of the "4 company architecture" is "company introduction". The method has the advantage that the file name of the file upper-level folder can be used as a question sentence under the condition that the user cannot accurately provide the file name of the file to be inquired. The dialogue robot can match with similar questions according to the question sentences of the users and return corresponding answers.
Further, as shown in fig. 1d, when the answer of the preset knowledge base template is set, the file name and the file type of the file may be used together with the file link as the answer. The method has the advantages that when the conversation robot returns the file link, the file name of the file and the file type of the file can be returned to the user together, so that the user can know the information of the file more clearly, and the user experience is improved.
In this embodiment, after the RPA robot imports the preset knowledge base template into the knowledge corpus of the dialogue robot, in the application process of the subsequent dialogue robot, the dialogue robot may identify the file query sentence input by the user by using the semantic identification algorithm in the NLP, so as to obtain the keyword in the file query sentence. And matching the obtained keywords with the standard questions in the knowledge corpus, and if the matching is successful, returning the file links of the answers corresponding to the standard questions to the user. And if the matching fails, matching the obtained keywords with similar questions in the knowledge corpus, determining a target similar question with the highest similarity to the file query statement from the similar questions, taking a file link corresponding to the target similar question as an answer of the file query statement, and returning the answer to the user. The user can click the link to perform operations such as file viewing or downloading.
According to the technical scheme provided by the embodiment, the RPA is combined with the conversation robot, the file names and the links of all the files in the shared storage space are acquired at regular time through the RPA robot, and the acquired file names and the links are automatically updated into the corpus of the conversation robot, so that the problem that the conversation robot cannot dynamically update the file links is solved, and the time for manually updating the corpus is saved. In the process that the user inquires the files through the conversation robot, the conversation robot can automatically send the links corresponding to the latest files to the user, so that the operation of manually logging in the shared storage space to search the files is avoided, the operation time is saved, and the working efficiency is improved.
Example two
Fig. 2a is a flowchart of a message reply method based on RPA and AI according to a second embodiment of the present invention, where an execution main body of the method is a conversation robot, and the method can be executed by a message reply device based on RPA and AI, and the device is implemented by software and/or hardware, and can be generally applied to office software such as flybooks, enterprise wechat, and the like. As shown in fig. 2a, the method comprises:
and S210, identifying the file query sentence input by the user.
Specifically, a semantic recognition algorithm in the NLP may be used to recognize a file query statement input by a user, and a keyword in the file query statement is obtained as a recognition result.
And S220, according to the recognition result, if the file link corresponding to the file query sentence exists in the knowledge corpus, returning the file link to the user.
In the knowledge corpus, each file link and the corresponding file name are obtained from the shared storage space at regular time by the RPA robot and added to the knowledge corpus, and the specific operation process of the RPA robot may refer to the description of the above embodiment, which is not described herein again.
In this embodiment, according to the recognition result, if it is determined that a file link corresponding to the file query statement exists in the knowledge corpus, the file link is returned to the user, which may specifically include:
and judging whether a standard problem corresponding to the file query statement exists in the knowledge corpus or not according to the identification result, and if so, taking a file link corresponding to the standard problem as an answer of the file query statement and returning the answer to the user.
Illustratively, according to the recognition result, if the knowledge corpus does not have the standard problem corresponding to the file query statement, whether the knowledge corpus has the similar problem corresponding to the file query statement or not is judged, if the knowledge corpus has the similar problem corresponding to the file query statement, a target similar problem with the highest similarity to the file query statement is determined from all the similar problems, a file link corresponding to the target similar problem is used as an answer of the file query statement, and the answer is returned to the user.
Furthermore, when the file link is returned to the user as an answer, the file description information of the file link, such as a file name, a file type, a file preview and the like, can be returned to the user as the answer, so that the user can know the information of the file to be queried more clearly, and the user experience is improved.
Furthermore, the dialogue robot can also return the relevant problems of the file query statement to the user for the user to query. When the file name of the file to be queried input by the user is deviated from the real file name, the user can click the correct file name to view the file according to the prompt of the listed related problems.
Specifically, fig. 2b is a screenshot of an effect of the dialog robot for answering a question of a user according to the second embodiment of the present invention. As shown in fig. 2b, after identifying the file query sentence "company introduction" input by the user, the conversation robot may query the file link corresponding to the file query sentence from the knowledge corpus according to the identification result, and return the file link and the related question to the user. The user can click the link to view or download and the like.
Illustratively, according to the recognition result, if it is determined that the knowledge corpus does not have the standard problem corresponding to the document query statement and does not have the similar problem corresponding to the document query statement, it indicates that the knowledge corpus does not have the link of the answer corresponding to the document query statement, and at this time, the prompt information containing the query document alternative can be returned to the user. If receiving the directory query instruction triggered by the user according to the prompt message, returning the secondary directory prompt message according to the directory query instruction, and returning the file name of the target file content and the corresponding link to the user until receiving the query instruction of the target file content triggered by the user. According to the method and the device, under the condition that answers of the user question sentences cannot be given, more options can be provided for the user, and the user experience is improved.
Specifically, fig. 2c is a screenshot of an effect that the conversation robot returns to the user to query the prompt information according to the second embodiment of the present invention. As shown in fig. 2c, when the dialog determines that there is no link corresponding to the answer of the file query statement "osmanthus cake" in the knowledge corpus, the dialog returns the prompt information including the alternative of "directory query" to the user, and prompts the user to search all files through the directory by clicking "directory query". The user can trigger a directory query instruction by clicking a directory query button, and when receiving the instruction, the conversation robot returns secondary directory prompt information, such as company introduction, white paper preview file, product manual and company logo shown in fig. 2c, and the user can continue to execute a click operation according to the prompt information until triggering the query instruction of the target file content, and the conversation robot returns the file name of the target file content and a corresponding link to the user.
For example, when it is determined that there is no link corresponding to an answer of a document query statement in the knowledge corpus, the prompt information returned to the user may further include a submission requirement candidate of the document to be queried. As shown in fig. 2c, the user may click on the alternate to trigger a file submission instruction. And if the conversation robot receives a file submitting instruction triggered by a user, sending the submitting requirement information to a set mailbox. And the related staff can upload the file to the shared storage space according to the received submission requirement information.
According to the technical scheme provided by the embodiment, the file link corresponding to the file query sentence in the knowledge corpus can be returned to the user according to the recognition result by recognizing the file query sentence input by the user. In the knowledge corpus, each file link and the corresponding file name are obtained from the shared storage space at regular time by the RPA robot and added into the knowledge corpus, so that the problem that the conversation robot cannot dynamically update the file link can be solved, the operation of manually updating the knowledge corpus is avoided, and the usability and the user satisfaction of the conversation robot are improved.
EXAMPLE III
Fig. 3 is a block diagram of a message reply device based on RPA and AI according to a third embodiment of the present invention, where the message reply device includes: a file query statement identification module 310 and a file link return module 320; wherein the content of the first and second substances,
a file query statement identification module 310 configured to: identifying a file query sentence input by a user;
a file link return module 320 configured to: according to the recognition result, if the file link corresponding to the file query sentence exists in the knowledge corpus, returning the file link to the user;
in the knowledge corpus, each file link and the corresponding file name are obtained from a shared storage space by the RPA robot at regular time and are added into the knowledge corpus.
Optionally, the apparatus further comprises:
a hint information return module configured to: according to the recognition result, if the fact that the link of the answer corresponding to the file query sentence does not exist in the knowledge corpus is determined, the prompt information containing the query file alternative is returned to the user;
a secondary hint information return module configured to: if receiving a directory query instruction triggered by the user according to the prompt information, returning secondary directory prompt information according to the directory query instruction, and returning the file name of the target file content and the corresponding link to the user when receiving a query instruction of the target file content triggered by the user.
Optionally, the prompt information further includes a submission requirement candidate of the file to be queried; correspondingly, the device further comprises:
a submission requirements information sending module configured to: and if a file submitting instruction triggered by the user based on the submitting requirement information is received, sending the submitting requirement information to a set mailbox.
Optionally, the file link returning module 320 is specifically configured to:
judging whether a standard problem corresponding to the file query statement exists in the knowledge corpus or not according to the recognition result;
if the knowledge corpus does not have the standard problem corresponding to the file query statement, judging whether a similar problem corresponding to the file query statement exists in the knowledge corpus or not;
if the similar problems corresponding to the file query statement exist in the knowledge corpus, determining a target similar problem with the highest similarity to the file query statement from all similar problems;
and taking the file link corresponding to the target similar question as an answer of the file query statement, and returning the answer to the user.
Optionally, the file query statement identification module 310 is specifically configured to:
and identifying the file query sentence input by the user by utilizing a semantic identification algorithm in the natural language processing NLP to obtain a keyword in the file query sentence as an identification result.
The message reply device based on the RPA and the AI provided by the embodiment of the invention can execute the message reply method based on the RPA and the AI applied to the conversation robot provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. Technical details that are not described in detail in the above embodiments can be referred to the message reply method based on RPA and AI applied to the conversation robot according to any embodiment of the present invention.
Example four
Fig. 4 is a block diagram of a message reply device based on RPA and AI according to a fourth embodiment of the present invention, as shown in fig. 4, the device includes: an information acquisition module 410 and an information import module 420; wherein the content of the first and second substances,
an information acquisition module 410 configured to: regularly acquiring file names and links of all files in the shared storage space;
an information import module 420 configured to: and adding the file names and the links of all the files into a knowledge corpus of the conversation robot according to a preset knowledge corpus template rule, wherein the knowledge corpus is used for providing corresponding file links for the file query sentences identified by the conversation robot.
Optionally, the preset knowledge base template rule includes:
the similar problems of the preset knowledge base template comprise file names of the files and the hierarchical relation of the folders in which the files are located.
The message reply device based on the RPA and the AI provided by the embodiment of the invention can execute the message reply method based on the RPA and the AI applied to the RPA robot provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. Technical details that are not described in detail in the above embodiments may be referred to an RPA and AI based message reply method applied to an RPA robot according to any embodiment of the present invention.
EXAMPLE five
Referring to fig. 5, fig. 5 is a schematic structural diagram of a computing device according to a fifth embodiment of the present invention. As shown in fig. 5, the computing device may include:
a memory 701 in which executable program code is stored;
a processor 702 coupled to the memory 701;
the processor 702 calls the executable program code stored in the memory 701 to execute the message reply method based on RPA and AI applied to the conversation robot according to any embodiment of the present invention.
An embodiment of the present invention further provides a computing device, where the computing device includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the message reply method based on the RPA and AI provided by any embodiment of the invention and applied to the RPA robot.
The embodiment of the invention discloses a computer-readable storage medium which stores a computer program, wherein the computer program enables a computer to execute the message reply method based on RPA and AI, which is applied to the conversation robot and provided by any embodiment of the invention.
The embodiment of the invention discloses a computer-readable storage medium which stores a computer program, wherein the computer program enables a computer to execute the message reply method based on RPA and AI, which is applied to the RPA robot and provided by any embodiment of the invention.
In various embodiments of the present invention, it should be understood that the sequence numbers of the above-mentioned processes do not imply an inevitable order of execution, and the execution order of the processes should be determined by their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
In the embodiments provided herein, it should be understood that "B corresponding to A" means that B is associated with A from which B can be determined. It should also be understood, however, that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present invention, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part or all of the steps of the above-described method of each embodiment of the present invention.
It will be understood by those skilled in the art that all or part of the steps in the methods of the embodiments described above may be implemented by hardware instructions of a program, and the program may be stored in a computer-readable storage medium, where the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM), or other Memory, such as a magnetic disk, or a combination thereof, A tape memory, or any other medium readable by a computer that can be used to carry or store data.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
Those of ordinary skill in the art will understand that: modules in the devices in the embodiments may be distributed in the devices in the embodiments according to the description of the embodiments, or may be located in one or more devices different from the embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A message reply method based on RPA and AI is applied to a dialogue robot ChatBot, and is characterized by comprising the following steps:
s1, identifying the file query sentence input by the user;
s2, according to the recognition result, if the file link corresponding to the file query sentence exists in the knowledge corpus, returning the file link to the user;
in the knowledge corpus, each file link and the corresponding file name are obtained from a shared storage space by the RPA robot at regular time and are added into the knowledge corpus.
2. The method of claim 1, further comprising:
s3, according to the recognition result, if the fact that the link of the answer corresponding to the file query sentence does not exist in the knowledge corpus is determined, the prompt information containing the query file option is returned to the user;
and S4, if receiving a directory query instruction triggered by the user according to the prompt information, returning secondary directory prompt information according to the directory query instruction, and returning the file name of the target file content and the corresponding link to the user when receiving the query instruction of the target file content triggered by the user.
3. The method according to claim 2, wherein the prompt message further includes a request for submission alternative of the file to be queried; correspondingly, the method further comprises the following steps:
and S5, if a file submission instruction triggered by the user based on the submission requirement information is received, sending the submission requirement information to a set mailbox.
4. The method according to claim 1, wherein the S2 includes:
s21, judging whether a standard problem corresponding to the file query sentence exists in the knowledge corpus or not according to the recognition result;
s22, if the knowledge corpus does not have the standard problem corresponding to the file query sentence, judging whether the knowledge corpus has a similar problem corresponding to the file query sentence;
s23, if the knowledge corpus has similar problems corresponding to the file query sentences, determining a target similar problem with the highest similarity to the file query sentences from all similar problems;
and S24, taking the file link corresponding to the target similar question as an answer of the file query statement, and returning the answer to the user.
5. The method according to claim 1, wherein the S1 includes:
and identifying the file query sentence input by the user by utilizing a semantic identification algorithm in the natural language processing NLP to obtain a keyword in the file query sentence as an identification result.
6. A message reply method based on RPA and AI is applied to the RPA robot, which is characterized in that the method comprises the following steps:
s6, regularly acquiring file names and links of all files in the shared storage space;
and S7, adding the file names and the links of all the files into a knowledge corpus of the conversation robot according to a preset knowledge corpus template rule, wherein the knowledge corpus is used for providing corresponding file links for the file query sentences identified by the conversation robot.
7. An apparatus for replying to a message based on RPA and AI, comprising:
a file query statement identification module configured to: identifying a file query sentence input by a user;
a file link return module configured to: according to the recognition result, if the file link corresponding to the file query sentence exists in the knowledge corpus, returning the file link to the user;
in the knowledge corpus, each file link and the corresponding file name are obtained from a shared storage space by the RPA robot at regular time and are added into the knowledge corpus.
8. An apparatus for replying to a message based on RPA and AI, comprising:
an information acquisition module configured to: regularly acquiring file names and links of all files in the shared storage space;
an information import module configured to: and adding the file names and the links of all the files into a knowledge corpus of the conversation robot according to a preset knowledge corpus template rule, wherein the knowledge corpus is used for providing corresponding file links for the file query sentences identified by the conversation robot.
9. A computing device, wherein the computing device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the RPA and AI-based message reply method applied to the conversation robot of any one of claims 1-5, or the RPA and AI-based message reply method applied to the RPA robot of claim 6.
10. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the RPA and AI-based message reply method applied to a conversation robot as claimed in any one of claims 1 to 5, or the RPA and AI-based message reply method applied to an RPA robot as claimed in claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111014662.0A CN113704185A (en) | 2021-08-31 | 2021-08-31 | Message reply method, device, equipment and medium based on RPA and AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111014662.0A CN113704185A (en) | 2021-08-31 | 2021-08-31 | Message reply method, device, equipment and medium based on RPA and AI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113704185A true CN113704185A (en) | 2021-11-26 |
Family
ID=78658190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111014662.0A Pending CN113704185A (en) | 2021-08-31 | 2021-08-31 | Message reply method, device, equipment and medium based on RPA and AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113704185A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117556087A (en) * | 2023-10-30 | 2024-02-13 | 广州圈量网络信息科技有限公司 | Customer service reply data processing method, device, equipment and storage medium |
-
2021
- 2021-08-31 CN CN202111014662.0A patent/CN113704185A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117556087A (en) * | 2023-10-30 | 2024-02-13 | 广州圈量网络信息科技有限公司 | Customer service reply data processing method, device, equipment and storage medium |
| CN117556087B (en) * | 2023-10-30 | 2024-04-26 | 广州圈量网络信息科技有限公司 | Customer service reply data processing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8566699B2 (en) | Intent-based information processing and updates | |
| US20130103391A1 (en) | Natural language processing for software commands | |
| US20030182391A1 (en) | Internet based personal information manager | |
| US7672908B2 (en) | Intent-based information processing and updates in association with a service agent | |
| JP7042693B2 (en) | Interactive business support system | |
| EP3502928A1 (en) | Intelligent natural language query processor | |
| CN110377712B (en) | Intelligent session switching method, device, equipment and storage medium | |
| EP3617896A1 (en) | Method and apparatus for intelligent response | |
| US11663255B2 (en) | Automatic collaboration between distinct responsive devices | |
| US11979361B2 (en) | Dialogue robot generation method, dialogue robot management platform, and storage medium | |
| CN109918494B (en) | Context association reply generation method based on graph, computer and medium | |
| CN116521893A (en) | Control method and control device of intelligent dialogue system and electronic equipment | |
| CN111597318A (en) | Method, device and system for executing business task | |
| CN112507139B (en) | Knowledge graph-based question and answer method, system, equipment and storage medium | |
| CN117573834B (en) | Multi-robot dialogue method and system for software-oriented instant service platform | |
| WO2020222999A1 (en) | Method, system, and data storage device for automating solution prompts based upon semantic representation | |
| CN112579733A (en) | Rule matching method, rule matching device, storage medium and electronic equipment | |
| CN111368029B (en) | Interaction method, device and equipment based on intention triples and storage medium | |
| CN113704185A (en) | Message reply method, device, equipment and medium based on RPA and AI | |
| Haqimi et al. | Timeline reminder system bot and telegram assistant chatbot for a university student and lecturer | |
| US20230409294A1 (en) | Adaptive user interfacing | |
| CN116841506B (en) | Program code generation method and device, and model training method and device | |
| Wilensky | Talking to UNIX in English: an overview of an on-line UNIX consultant | |
| Prabu et al. | Enhancing customer service using Chatbot application through artificial intelligence | |
| CN114024955B (en) | File processing method, device, equipment and medium based on RPA and AI |
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 |