Message reply method, device, equipment and medium based on RPA and AI

Abstract

The embodiment of the present invention discloses a message reply method, device, equipment and medium based on RPA and AI, the method comprising: S1, identifying the file query statement input by the user; S2, according to the recognition result, if it is determined that the file link corresponding to the file query statement exists in the knowledge corpus, the file link is returned to the user; wherein, in the knowledge corpus, each file link and the corresponding file name are periodically obtained by the RPA robot from the shared storage space and added to the knowledge corpus. By adopting the above technical solution, the problem that the dialogue robot cannot dynamically update the file link is solved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of process automation technology, and specifically, to a message reply method, device, equipment and medium based on RPA and AI. Background Art

[0002] RPA (Robotic Process Automation) uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules.

[0003] AI (Artificial Intelligence) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0004] RPA has unique advantages: low code and non-intrusive. Low code means that RPA does not require a high level of IT to operate, and business personnel who do not understand programming can also develop processes; non-intrusive means that RPA can simulate human operations without the need for software system open interfaces. However, traditional RPA has certain limitations: it can only be based on fixed rules and has limited application scenarios. With the continuous development of AI technology, the deep integration of RPA and AI has overcome the limitations of traditional RPA. RPA+AI=Hand work+Head work is greatly changing the value of labor.

[0005] At present, with the development of artificial intelligence technology, AI-based conversational robots are becoming more and more common in daily life. The conversational robot will reply to the corresponding answer according to the user's question statement. In order to solve the problem that the staff manually search for files, the function of automatically replying to the file link can be set for the conversational robot. The implementation of this function requires setting the file link in the conversational robot in advance. However, if the file link changes or a new file appears, it is necessary to manually modify the file link in the conversational robot. The process of manually modifying the link is quite cumbersome and inefficient, which greatly reduces the usability and user satisfaction of the conversational robot. Summary of the invention

[0006] The embodiments of the present invention provide a message reply method, apparatus, device and medium based on RPA and AI, so as to overcome the problem that a conversational robot cannot dynamically update file links.

[0007] In a first aspect, the present invention provides an RPA and AI message reply method, which is applied to a conversational robot. The method includes:

[0008] S1. Identify the file query statement input by the user;

[0009] S2. 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;

[0010] Among them, in the knowledge corpus, each file link and the corresponding file name are regularly obtained by the RPA robot from the shared storage space and added to the knowledge corpus.

[0011] Optionally, the method further includes:

[0012] S3. If it is determined that there is no link corresponding to the answer to the file query statement in the knowledge corpus according to the recognition result, a prompt message containing query file options is returned to the user;

[0013] S4. If a directory query instruction triggered by the user according to the prompt information is received, the secondary directory prompt information is returned according to the directory query instruction, until a query instruction for the target file content triggered by the user is received, the file name and the corresponding link of the target file content are returned to the user.

[0014] Optionally, the prompt information further includes submission requirement options for the file to be queried; accordingly, the method further includes:

[0015] S5. If a file submission instruction triggered by the user based on the submission requirement information is received, the submission requirement information is sent to a set mailbox.

[0016] Optionally, S2 includes:

[0017] S21, judging whether there is a standard question corresponding to the document query statement in the knowledge corpus according to the recognition result;

[0018] S22: if there is no standard question corresponding to the document query statement in the knowledge corpus, determining whether there is a similar question corresponding to the document query statement in the knowledge corpus;

[0019] S23, if there are similar questions corresponding to the document query statement in the knowledge corpus, determining a target similar question having the highest similarity to the document query statement from among the similar questions;

[0020] S24: Use the file link corresponding to the target similarity question as the answer to the file query statement, and return the answer to the user.

[0021] Optionally, the S1 includes:

[0022] The semantic recognition algorithm in natural language processing (NLP) is used to recognize the file query sentence input by the user, and the keywords in the file query sentence are obtained as the recognition result.

[0023] 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. The method includes:

[0024] S6, regularly obtaining the file names and links of all files in the shared storage space;

[0025] S7. Add the file names and links of all files to the knowledge corpus of the dialogue robot according to preset knowledge base template rules. The knowledge corpus is used to provide corresponding file links for the file query statements recognized by the dialogue robot.

[0026] Optionally, the preset knowledge base template rule includes:

[0027] The similar questions of the preset knowledge base template include the file names of various files and the hierarchical relationship of the folders where they are located.

[0028] In a third aspect, an embodiment of the present invention further provides a message reply device based on RPA and AI, the device comprising:

[0029] The file query statement recognition module is configured to: recognize the file query statement input by the user;

[0030] The file link returning module is configured to: according to the recognition result, if it is determined that the file link corresponding to the file query statement exists in the knowledge corpus, then return the file link to the user;

[0031] Among them, in the knowledge corpus, each file link and the corresponding file name are regularly obtained by the RPA robot from the shared storage space and added to the knowledge corpus.

[0032] Optionally, the device further comprises:

[0033] The prompt information returning module is configured to: according to the recognition result, if it is determined that there is no link corresponding to the answer of the file query statement in the knowledge corpus, then return the prompt information containing the query file options to the user;

[0034] The secondary prompt information return module is configured as follows: if a directory query instruction triggered by the user according to the prompt information is received, the secondary directory prompt information is returned according to the directory query instruction, until a query instruction for the target file content triggered by the user is received, and the file name and corresponding link of the target file content are returned to the user.

[0035] Optionally, the prompt information further includes an alternative submission requirement for the file to be queried; accordingly, the device further includes:

[0036] The submission requirement information sending module is configured to: if a file submission instruction triggered by the user based on the submission requirement information is received, send the submission requirement information to a set mailbox.

[0037] Optionally, the file link return module is specifically configured as follows:

[0038] According to the recognition result, determining whether there is a standard question corresponding to the document query statement in the knowledge corpus;

[0039] If there is no standard question corresponding to the document query statement in the knowledge corpus, determining whether there is a similar question corresponding to the document query statement in the knowledge corpus;

[0040] If there are similar questions corresponding to the document query statement in the knowledge corpus, determining a target similar question with the highest similarity to the document query statement from among the similar questions;

[0041] The document link corresponding to the target similarity question is used as the answer to the document query statement, and the answer is returned to the user.

[0042] Optionally, the file query statement identification module is specifically configured as follows:

[0043] The semantic recognition algorithm in natural language processing (NLP) is used to recognize the file query sentence input by the user, and the keywords in the file query sentence are obtained as the recognition result.

[0044] In a fourth aspect, an embodiment of the present invention further provides a message reply device based on RPA and AI, the device comprising:

[0045] The information acquisition module is configured to: regularly acquire the file names and links of all files in the shared storage space;

[0046] The information import module is configured to: add the file names and links of all files to the knowledge corpus of the dialogue robot according to the preset knowledge base template rules, and the knowledge corpus is used to provide corresponding file links for the file query statements recognized by the dialogue robot.

[0047] Optionally, the preset knowledge base template rule includes:

[0048] The similar questions of the preset knowledge base template include the file names of various files and the hierarchical relationship of the folders where they are located.

[0049] In a fifth aspect, an embodiment of the present invention further provides a computing device, including:

[0050] A memory storing executable program code;

[0051] a processor coupled to the memory;

[0052] The processor calls the executable program code stored in the memory to execute the RPA and AI-based message reply method applied to a conversational robot provided in any embodiment of the present invention.

[0053] In a sixth aspect, an embodiment of the present invention further provides a computing device, including:

[0054] A memory storing executable program code;

[0055] a processor coupled to the memory;

[0056] The processor calls the executable program code 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 present invention.

[0057] In the seventh aspect, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the RPA and AI-based message reply method applied to a conversational robot provided by any embodiment of the present invention is implemented.

[0058] In an eighth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the message reply method based on RPA and AI applied to an RPA robot provided by any embodiment of the present invention.

[0059] The technical solution provided by the embodiment of the present invention combines RPA with a conversational robot, and the RPA robot periodically obtains the file names and links of all files in the shared storage space, and automatically updates the obtained file names and links to the conversational robot corpus, which solves the problem that the conversational robot cannot dynamically update file links, and also saves the user's time to manually update file links. When the user queries files through the conversational robot, the conversational robot can automatically send the link corresponding to the latest file to the user, avoiding the operation of manually logging into the shared storage space to search for files, saving operation time, and improving work efficiency.

[0060] The innovative features of the embodiments of the present invention include:

[0061] 1. Combining RPA with a conversational robot, the RPA robot periodically obtains the file names and links of all files in the shared storage space, and automatically updates the obtained file names and links to the conversational robot corpus, which solves the problem that the conversational robot cannot dynamically update file links. This is one of the innovations of the embodiments of the present invention.

[0062] 2. By using the semantic recognition algorithm in natural language processing (NLP), the file query statement input by the user is recognized. When it is determined based on the recognition result that there is no link corresponding to the answer to the file query statement imported by the RPA robot in the knowledge corpus, prompt information containing query file options is returned to the user. This provides the user with more options when it is impossible to give an answer to the user's question, thereby improving the usability and user experience of the conversational robot, which is one of the innovations of the embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1a A flowchart of a message reply method based on RPA and AI provided in Example 1 of the present invention;

[0065] Figure 1b This is a screenshot of the timing plan set for the RPA robot provided in the first embodiment of the present invention;

[0066] Figure 1c This is a screenshot of the RPA robot provided in the first embodiment of the present invention entering the shared storage space to obtain the file name and its link;

[0067] Figure 1d A screenshot of the preset knowledge base template provided in the first embodiment of the present invention;

[0068] Figure 2a This is a flow chart of a message reply method based on RPA and AI provided in Embodiment 2 of the present invention;

[0069] Figure 2b This is a screenshot of the effect of a conversational robot answering user questions provided by the second embodiment of the present invention;

[0070] Figure 2c This is a screenshot of the effect of the conversational robot providing the second embodiment of the present invention returning query prompt information to the user;

[0071] Figure 3 This is a structural block diagram of a message reply device based on RPA and AI provided in Embodiment 3 of the present invention;

[0072] Figure 4 This is a structural block diagram of a message reply device based on RPA and AI provided in Embodiment 4 of the present invention;

[0073] Figure 5 A schematic diagram of the structure of a computing device provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0076] In the description of the embodiments of the present invention, the term "conversational robot" refers, in a broad sense, to a computer program that can interact with humans through voice or text.

[0077] In the description of the embodiments of the present invention, the term "knowledge corpus" is a structured collection of several 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, multiple similar questions, and one or more answers.

[0078] In the description of the embodiment of the present invention, the term "similar questions" refers to a plurality of questions that are highly similar or consistent in semantics to the standard questions of the knowledge point to which they belong, for example, different ways of saying a certain question.

[0079] In order to explain the contents of the embodiments of the present invention more clearly and clearly, the basic working principles of the embodiments of the present invention are briefly introduced below.

[0080] Robotic Process Automation (RPA), referred to as Robotic Process Automation, uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules.

[0081] AI (Artificial Intelligence) is the abbreviation of artificial intelligence. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI-based conversational robots are becoming more and more common in daily life. For example, they can perform semantic recognition on user questions and return answers to the questions.

[0082] At present, RPA and conversational robots have a wide range of applications. RPA can generally replace manual repetitive work, and conversational robots can be applied to specific industries such as customer service. Both reduce people's work in their respective fields. For conversational robots, if you want to realize the function of automatically replying to file links, you can only set the file links in the conversational robot in advance. If the file link changes or a new file appears, you need to manually modify the file link in the conversational robot. Considering the problem of low efficiency of manual operation, the technical solution provided by the embodiment of the present invention combines RPA and conversational robots, and solves the problem that the conversational robot cannot dynamically update file links by using RPA technology instead of manually obtaining and updating file links. The conversational robot can identify the user's file query statement by using the semantic recognition method in NLP (Natural Language Processing), and send the latest link of the file to be queried by the user to the user based on the recognition result, achieving a fully automated effect.

[0083] The following is a detailed introduction to the RPA and AI-based message reply method, device, equipment and medium provided in the embodiments of the present invention from the perspectives of the RPA robot and the conversational robot.

[0084] Embodiment 1

[0085] Figure 1a A flowchart of a message reply method based on RPA and AI provided in the first embodiment of the present invention, wherein the executor of the method is an RPA robot. Typically, the method can be applied to general office software, such as enterprise WeChat or Feishu and other office software. These office software have shared storage space for storing company files. The RPA robot can obtain all files and their corresponding links from the shared storage space, and add them to the knowledge corpus of the conversational robot. The conversational robot reply method based on RPA and AI provided in this embodiment can be executed by a message reply device based on RPA and AI, which can be implemented by software and / or hardware. Figure 1a As shown, the method includes:

[0086] S110, periodically obtaining the file names and links of all files in the shared storage space.

[0087] The shared storage space contains documents and materials for enterprise employees to view or download, such as company introductions, employee rules, technical documents, and product information. The shared storage space can be a shared space for office software such as WeChat for Enterprise or Feishu, or a cloud space applied for by the enterprise.

[0088] In this embodiment, a timing plan can be set for the RPA robot, and the RPA robot can obtain the file names and 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, it can be set according to the update speed of the files in the shared storage space.

[0089] Specifically, Figure 1b This is a screenshot of the timing plan set for the RPA robot provided in the first embodiment of the present invention. Figure 1c This is a screenshot of the RPA robot provided in the first embodiment of the present invention entering the shared storage space to obtain the file name and its link. Figure 1b As shown in the figure, the RPA robot logs in at 5 o'clock every day. Figure 1c In the shared space shown in the figure, the file names and links of all files in the shared space are obtained. Regardless of whether the files in the shared storage space are added or deleted, RPA will automatically update the latest file links to the corpus of the conversational robot, saving the manual operation of updating the corpus and solving the problem that the conversational robot cannot dynamically update file links.

[0090] When the RPA robot obtains the file names of all files in the shared storage space, it can also save the hierarchical relationship between the folders where the files are located. Figure 1c As shown in the figure, 1 Company Introduction > 1 Company Profile > Documents represents the hierarchical relationship between the folders where the documents are located, that is, Figure 1c The folder name of the parent file of the document shown is "1 Company Profile", and the folder name of the parent file of "1 Company Profile" is "1 Company Introduction". Figure 1c When the file name of the document and its file link are shown, the above hierarchical relationship can also be obtained. The obtained hierarchical relationship can be used to construct similar questions of the preset knowledge base template.

[0091] S120. Add the file names and links of all files to the knowledge corpus of the dialogue robot according to preset knowledge base template rules. The knowledge corpus is used to provide corresponding file links for the file query statements recognized by the dialogue robot.

[0092] The knowledge corpus is a structured collection of several knowledge points in a certain business field. Each knowledge point in the knowledge base consists of questions and answers. Creating a knowledge point requires a standard question, multiple similar questions, and one or more answers. Similar questions refer to multiple questions that are highly similar or consistent in semantics to the standard questions of the knowledge point to which they belong, such as different ways of saying a certain question. In this embodiment, the answer to a knowledge point is a file link of a file in a shared storage space.

[0093] In this embodiment, the RPA robot adds the file names and links of all files to the knowledge corpus of the conversational robot according to the preset knowledge base template rules, which can be specifically implemented in the following ways:

[0094] First, the file names and links of all files are written into the preset knowledge base template, and then the preset knowledge base template is imported into the knowledge corpus of the conversational robot. In order to meet the requirements for creating a knowledge corpus, the preset knowledge base template also provides standard questions, similar questions and their answers corresponding to each file link. In this embodiment, the standard question can be composed of the file name and its file type, and the similar question refers to a question whose similarity with the standard question of the knowledge point to which it belongs reaches a set threshold, for example, different statements of the same file name, etc.

[0095] Furthermore, the RPA robot can write the hierarchical relationship of the folders where each file is located obtained from the shared storage space into similar questions. Figure 1d This is a screenshot of the preset knowledge base template provided in Example 1 of the present invention. Figure 1d As shown, similar questions contain the hierarchical relationship between the file names of each file and the folders they are in, for example, "Organizational Structure<<<<4 Company Structure<<Company Introduction", this hierarchical relationship means that the folder name of the parent file of "Organizational Structure" is "4 Company Structure", and the folder name of the parent file of "4 Company Structure" is "Company Introduction". The advantage of this setting is that if the user cannot accurately provide the file name of the file to be queried, the file name of the parent folder of the file can be used as the question statement. The conversational robot can match the user's question statement with similar questions and return the corresponding answer.

[0096] Further, such as Figure 1d As shown in the figure, when setting the answer of the preset knowledge base template, the file name, file type and file link can be used as the answer. The advantage of this setting is that when the conversation robot returns the file link, it can return the file name and file type to the user together, so that the user can understand the file information more clearly, improving the user experience.

[0097] In this embodiment, after the RPA robot imports the preset knowledge base template into the knowledge corpus of the conversational robot, in the subsequent application process of the conversational robot, the conversational robot will use the semantic recognition algorithm in NLP to identify the file query statement entered by the user and obtain the keywords in the file query statement. By matching the obtained keywords with the standard questions in the knowledge corpus, if the match is successful, the file link corresponding to the answer to the standard question is returned to the user. If the match fails, the obtained keywords are matched with similar questions in the knowledge corpus, and the target similar question with the highest similarity to the file query statement is determined from each similar question, and the file link corresponding to the target similar question is used as the answer to the file query statement, and the answer is returned to the user. The user can click the link to view or download the file.

[0098] The technical solution provided in this embodiment combines RPA with a conversational robot, and uses the RPA robot to periodically obtain the file names and links of all files in the shared storage space, and automatically updates the obtained file names and links to the conversational robot corpus, solving the problem that the conversational robot cannot dynamically update file links, saving time for manually updating the corpus. When a user queries a file through a conversational robot, the conversational robot can automatically send the link corresponding to the latest file to the user, avoiding the operation of manually logging into the shared storage space to search for files, saving operation time, and improving work efficiency.

[0099] Embodiment 2

[0100] Figure 2a This is a flowchart of a message reply method based on RPA and AI provided in the second embodiment of the present invention. The execution subject of the method is a conversational robot. The method can be executed by an RPA and AI message reply device, which is implemented by software and / or hardware and can be generally applied to office software such as Feishu and Enterprise WeChat. Figure 2a As shown, the method includes:

[0101] S210: Identify the file query statement input by the user.

[0102] Specifically, the semantic recognition algorithm in NLP can be used to recognize the file query sentence input by the user, and obtain the keywords in the file query sentence as the recognition result.

[0103] S220: Based on 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.

[0104] Among them, in the knowledge corpus, each file link and the corresponding file name are periodically obtained by the RPA robot from the shared storage space and added to the knowledge corpus. The specific operation process of the RPA robot can refer to the description of the above embodiment, which will not be repeated here.

[0105] In this embodiment, according to the recognition result, if it is determined that there is a file link corresponding to the file query statement in the knowledge corpus, the file link is returned to the user, which may specifically include:

[0106] Based on the recognition results, it is determined whether there is a standard question corresponding to the file query statement in the knowledge corpus. If there is a standard question corresponding to the file query statement, the file link corresponding to the standard question is used as the answer to the file query statement and returned to the user.

[0107] Exemplarily, based on the recognition results, if there is no standard question corresponding to the file query statement in the knowledge corpus, then determine whether there is a similar question corresponding to the file query statement in the knowledge corpus; if there is a similar question corresponding to the file query statement, then determine the target similar question with the highest similarity to the file query statement from among the similar questions, and use the file link corresponding to the target similar question as the answer to the file query statement, and return it to the user.

[0108] Furthermore, when a file link is returned to the user as an answer, the file description information of the file link, such as the file name, file type, and a preview image of the file, can be returned to the user as an answer, so that the user can more clearly understand the information of the file to be queried and improve the user experience.

[0109] Furthermore, the conversational robot can also return questions related to 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 deviates from its actual file name, the user can click on the correct file name to view the file according to the prompts of the listed related questions.

[0110] Specifically, Figure 2b This is a screenshot of the effect of a conversational robot answering user questions provided by the second embodiment of the present invention. Figure 2b As shown in the figure, after the conversational robot recognizes the file query sentence "company introduction" input by the user, it can query the file link corresponding to the file query sentence from the knowledge corpus according to the recognition result, and return the file link and related questions to the user. The user can click the link to view or download.

[0111] Exemplarily, according to the recognition result, if it is determined that there is no standard question corresponding to the file query statement in the knowledge corpus, and there is no similar question corresponding to the file query statement, it means that there is no link to the answer corresponding to the file query statement in the knowledge corpus. At this time, prompt information containing query file options can be returned to the user. If a directory query instruction triggered by the user according to the prompt information is received, secondary directory prompt information can be returned according to the directory query instruction, until a query instruction for the target file content triggered by the user is received, the file name of the target file content and the corresponding link are returned to the user. This arrangement of this embodiment can provide users with more options and improve user experience when it is impossible to give an answer to the user's question statement.

[0112] Specifically, Figure 2c This is a screenshot of the effect of the conversational robot providing the second embodiment of the present invention returning query prompt information to the user. Figure 2c As shown in the figure, when the dialogue determines that there is no link corresponding to the answer to the file query sentence "osmanthus cake" in the knowledge corpus, it returns a prompt message containing the "directory query" option to the user, and prompts the user to click "directory query" to find all files through the directory. The user can trigger the directory query command by clicking the "directory query" button. When the dialogue robot receives the command, it will return the secondary directory prompt information, such as Figure 2c The user can continue to click on the "Company Introduction", "White Paper Preview File", "Product Manual" and "Company Logo" shown in the figure until the query instruction of the target file content is triggered. The conversational robot returns the file name and corresponding link of the target file content to the user.

[0113] For example, when it is determined that there is no link to the answer corresponding to the file query statement in the knowledge corpus, the prompt information returned to the user may also include an alternative option for submitting the file to be queried. Figure 2c As shown, the user can click on the option to trigger the file submission instruction. If the conversational robot receives the file submission instruction triggered by the user, it will send the submission requirement information to the set mailbox. The relevant staff can upload the file to the shared storage space according to the received submission requirement information.

[0114] The technical solution provided in this embodiment can identify the file query statement input by the user, and return the file link corresponding to the file query statement in the knowledge corpus to the user according to the identification result. Since each file link and the corresponding file name in the knowledge corpus are obtained from the shared storage space by the RPA robot at regular intervals and added to the knowledge corpus, this setting can solve the problem that the conversation robot cannot dynamically update the file link, and also avoid the operation of manually updating the knowledge corpus, thereby improving the usability and user satisfaction of the conversation robot.

[0115] Embodiment 3

[0116] Figure 3 The structural block diagram of a message reply device based on RPA and AI provided in the third embodiment of the present invention includes: a file query statement recognition module 310 and a file link return module 320; wherein,

[0117] The file query statement recognition module 310 is configured to: recognize the file query statement input by the user;

[0118] The file link returning module 320 is configured to: according to the recognition result, if it is determined that the file link corresponding to the file query statement exists in the knowledge corpus, then return the file link to the user;

[0119] Among them, in the knowledge corpus, each file link and the corresponding file name are regularly obtained by the RPA robot from the shared storage space and added to the knowledge corpus.

[0120] Optionally, the device further comprises:

[0121] The prompt information returning module is configured to: according to the recognition result, if it is determined that there is no link corresponding to the answer of the file query statement in the knowledge corpus, then return the prompt information containing the query file options to the user;

[0122] The secondary prompt information return module is configured as follows: if a directory query instruction triggered by the user according to the prompt information is received, the secondary directory prompt information is returned according to the directory query instruction, until a query instruction for the target file content triggered by the user is received, and the file name and corresponding link of the target file content are returned to the user.

[0123] Optionally, the prompt information further includes an alternative submission requirement for the file to be queried; accordingly, the device further includes:

[0124] The submission requirement information sending module is configured to: if a file submission instruction triggered by the user based on the submission requirement information is received, send the submission requirement information to a set mailbox.

[0125] Optionally, the file link returning module 320 is specifically configured as follows:

[0126] According to the recognition result, determining whether there is a standard question corresponding to the document query statement in the knowledge corpus;

[0127] If there is no standard question corresponding to the document query statement in the knowledge corpus, determining whether there is a similar question corresponding to the document query statement in the knowledge corpus;

[0128] If there are similar questions corresponding to the document query statement in the knowledge corpus, determining a target similar question with the highest similarity to the document query statement from among the similar questions;

[0129] The document link corresponding to the target similarity question is used as the answer to the document query statement, and the answer is returned to the user.

[0130] Optionally, the file query statement identification module 310 is specifically configured to:

[0131] The semantic recognition algorithm in natural language processing (NLP) is used to recognize the file query sentence input by the user, and the keywords in the file query sentence are obtained as the recognition result.

[0132] The message reply device based on RPA and AI provided in the embodiment of the present invention can execute the message reply method based on RPA and AI applied to the dialogue robot provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in the above embodiments, please refer to the message reply method based on RPA and AI applied to the dialogue robot provided in any embodiment of the present invention.

[0133] Embodiment 4

[0134] Figure 4 A structural block diagram of a message reply device based on RPA and AI provided in Embodiment 4 of the present invention, such as Figure 4 As shown, the device includes: an information acquisition module 410 and an information import module 420; wherein,

[0135] The information acquisition module 410 is configured to: regularly acquire the file names and links of all files in the shared storage space;

[0136] The information import module 420 is configured to add the file names and links of all files to the knowledge corpus of the dialogue robot according to the preset knowledge base template rules, and the knowledge corpus is used to provide corresponding file links for the file query statements recognized by the dialogue robot.

[0137] Optionally, the preset knowledge base template rule includes:

[0138] The similar questions of the preset knowledge base template include the file names of various files and the hierarchical relationship of the folders where they are located.

[0139] The message reply device based on RPA and AI provided in the embodiment of the present invention can execute the message reply method based on RPA and AI applied to the RPA robot provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in the above embodiments, please refer to the message reply method based on RPA and AI applied to the RPA robot provided in any embodiment of the present invention.

[0140] Embodiment 5

[0141] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a computing device provided in Embodiment 5 of the present invention. Figure 5 As shown, the computing device may include:

[0142] A memory 701 storing executable program codes;

[0143] a processor 702 coupled to the memory 701;

[0144] Among them, the processor 702 calls the executable program code stored in the memory 701 to execute the RPA and AI-based message reply method applied to the dialogue robot provided by any embodiment of the present invention.

[0145] An embodiment of the present invention further provides a computing device, the computing device comprising:

[0146] one or more processors;

[0147] a storage device for storing one or more programs,

[0148] When the one or more programs are executed by the one or more processors, the one or more processors implement the RPA and AI-based message reply method applied to the RPA robot provided in any embodiment of the present invention.

[0149] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the RPA and AI-based message reply method for a conversational robot provided by any embodiment of the present invention.

[0150] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the RPA and AI-based message reply method applied to an RPA robot provided by any embodiment of the present invention.

[0151] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the above-mentioned processes does not mean the necessary order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0152] In the embodiments provided by the present invention, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0153] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0154] If the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, 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 a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the above methods of various embodiments of the present invention.

[0155] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0156] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0157] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed accordingly and located in one or more devices different from the embodiment. The modules in the above embodiment can be combined into one module, or can be further divided into multiple sub-modules.

[0158] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A message reply method based on RPA and AI, applied to a conversational robot ChatBot, characterized in that: include: The RPA robot obtains the file names and links of all files in the shared storage space according to the set timing plan, wherein the time in the timing plan is set according to the update speed of the files in the shared storage space; The RPA robot first writes the file names and links of all files into a preset knowledge base template, and then imports the preset knowledge base template into the knowledge corpus of the conversational robot. The preset knowledge base template is provided with standard questions, similar questions and their answers corresponding to each file link. The standard question is composed of the file name and its file type. The similar question refers to a question whose similarity to the standard question of the knowledge point to which it belongs reaches a set threshold. The RPA robot writes the hierarchical relationship of the folders where each file is located obtained from the shared storage space into the similarity question; S1. The conversational robot recognizes the file query sentence input by the user; S2. If the conversational robot determines that a file link corresponding to the file query statement exists in the knowledge corpus based on the recognition result, the conversational robot returns the file link to the user; S3. If the conversational robot determines that there is no link corresponding to the answer to the file query statement in the knowledge corpus based on the recognition result, it returns prompt information containing query file options to the user; S4. If the conversational robot receives a directory query instruction triggered by the user according to the prompt information, it returns the secondary directory prompt information according to the directory query instruction until it receives a query instruction for the target file content triggered by the user, and then returns the file name and corresponding link of the target file content to the user.

2. The method according to claim 1, characterized in that The prompt information also includes submission requirement options for the file to be queried; accordingly, the method further includes: S5. If a file submission instruction triggered by the user based on submission requirement information is received, the submission requirement information is sent to a set mailbox.

3. The method according to claim 1, characterized in that The S2 includes: S21, judging whether there is a standard question corresponding to the document query statement in the knowledge corpus according to the recognition result; S22: if there is no standard question corresponding to the document query statement in the knowledge corpus, determining whether there is a similar question corresponding to the document query statement in the knowledge corpus; S23, if there are similar questions corresponding to the document query statement in the knowledge corpus, determining a target similar question having the highest similarity to the document query statement from among the similar questions; S24: Use the file link corresponding to the target similarity question as the answer to the file query statement, and return the answer to the user.

4. The method according to claim 1, characterized in that The S1 includes: The semantic recognition algorithm in natural language processing (NLP) is used to recognize the file query sentence input by the user, and the keywords in the file query sentence are obtained as the recognition result.

5. A message reply method based on RPA and AI, applied to an RPA robot, characterized in that: include: S6. Obtaining the file names and links of all files in the shared storage space at a regular interval, wherein the regular interval is set according to the update speed of the files in the shared storage space; S7, first write the file names and links of all files into a preset knowledge base template, and then add the file names and links of all files into the knowledge corpus of the dialogue robot according to the rules of the preset knowledge base template, wherein the knowledge corpus is used to provide corresponding file links for the file query statements recognized by the dialogue robot, wherein the preset knowledge base template is provided with standard questions, similar questions and their answers corresponding to each file link, wherein the standard question is composed of the file name and its file type, and the similar question refers to a question whose similarity to the standard question of the knowledge point to which it belongs reaches a set threshold; The hierarchical relationship of the folders where the files are located obtained from the shared storage space is written into the similarity question.

6. A message reply device based on RPA and AI, characterized in that: include: The information acquisition module is configured to: the RPA robot acquires the file names and links of all files in the shared storage space according to a set timing plan, wherein the time in the timing plan is set according to the update speed of the files in the shared storage space; The information import module is configured as follows: the RPA robot first writes the file names and links of all files into a preset knowledge base template, and then imports the preset knowledge base template into the knowledge corpus of the conversational robot. The RPA robot writes the hierarchical relationship of the folders where the files are located obtained from the shared storage space into similar questions, wherein the preset knowledge base template is provided with standard questions, similar questions and their answers corresponding to each file link, wherein the standard question is composed of the file name and its file type, and the similar question refers to a question whose similarity to the standard question of the knowledge point to which it belongs reaches a set threshold; The file query statement recognition module is configured as follows: the conversational robot recognizes the file query statement input by the user; The file link returning module is configured to: if the conversational robot determines that a file link corresponding to the file query statement exists in the knowledge corpus according to the recognition result, then return the file link to the user; The prompt information returning module is configured to: if the conversational robot determines that there is no link corresponding to the answer of the file query statement in the knowledge corpus according to the recognition result, then return the prompt information containing the query file options to the user; The secondary prompt information return module is configured as follows: if the conversational robot receives a directory query instruction triggered by the user based on the prompt information, it returns the secondary directory prompt information based on the directory query instruction, until it receives a query instruction for the target file content triggered by the user, and then returns the file name and corresponding link of the target file content to the user.

7. A message reply device based on RPA and AI, characterized in that: include: The information acquisition module is configured to: regularly acquire the file names and links of all files in the shared storage space, wherein the regular time is set according to the update speed of the files in the shared storage space; The information import module is configured to: first write the file names and links of all files into a preset knowledge base template, and then add the file names and links of all files into the knowledge corpus of the dialogue robot according to the preset knowledge base template rules, the knowledge corpus is used to provide corresponding file links for the file query statements recognized by the dialogue robot, and write the hierarchical relationship of the folders where the files are located obtained from the shared storage space into similar questions. Among them, the preset knowledge base template is provided with standard questions, similar questions and their answers corresponding to each file link, the standard question is composed of the file name and its file type, and a similar question refers to a question whose similarity with the standard question of the knowledge point to which it belongs reaches a set threshold.

8. A computing device, characterized in that The computing device comprises: 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 RPA and AI-based message reply method applied to a conversational robot as described in any one of claims 1 to 4, or the RPA and AI-based message reply method applied to an RPA robot as described in claim 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by the processor, it implements the message reply method based on RPA and AI applied to a conversational robot as described in any one of claims 1 to 4, or the message reply method based on RPA and AI applied to an RPA robot as described in claim 5.

Images