CN114442883A

CN114442883A - Service processing method and device based on AI and RPA

Info

Publication number: CN114442883A
Application number: CN202210061176.2A
Authority: CN
Inventors: 陈林平; 翁嘉颀; 范振健; 叶熠昕; 岳毅; 欧阳杰; 魏伟
Original assignee: Laiye Technology Beijing Co Ltd
Current assignee: Laiye Technology Beijing Co Ltd
Priority date: 2022-01-19
Filing date: 2022-01-19
Publication date: 2022-05-06

Abstract

The disclosure provides a service processing method and device based on Artificial Intelligence (AI) and Robot Process Automation (RPA), and relates to the technical field of RPA and AI. Acquiring a service processing demonstration request, wherein the demonstration request comprises an identifier of a target service; acquiring a target operation document corresponding to the identification of the target service from a preset operation document library, wherein the target operation document is a document generated by the RPA based on recorded operation data related to the target service; and calling the target operation document to demonstrate the target business process. Therefore, the corresponding target operation document can be determined based on the identification of the target service, and then the target operation document is called, so that the processing flow of the target service can be demonstrated, a user can clearly and visually know the processing process of the target service, the target service can be simply and quickly processed, the time is saved, and the efficiency is improved.

Description

Service processing method and device based on AI and RPA

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to the fields of Artificial Intelligence (AI) and Robot Process Automation (RPA), and more particularly, to a service processing method and apparatus based on AI and RPA.

Background

Robot Process Automation (RPA) is a Process task that simulates human operations on a computer by specific "robot software" and executes automatically according to rules.

Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence.

With the development of computer technology, the internet is also more and more widely used. In the related art, if each employee in a department needs to complete the same business inside an enterprise, each employee may need to complete the task in the same way on a computer, but sometimes the operation flow in the process of completing the business may be complex, and each employee needs to spend a lot of time to research a specific operation flow, thereby not only wasting time, but also having low efficiency. Therefore, how to improve the efficiency of service processing is very important.

Disclosure of Invention

The disclosure provides a business processing method and device based on AI and RPA and electronic equipment.

An embodiment of the disclosure provides a service processing method based on AI and RPA, including:

acquiring a service processing demonstration request, wherein the demonstration request comprises an identifier of a target service;

acquiring a target operation document corresponding to the identification of the target service from a preset operation document library, wherein the target operation document is a document generated by the RPA based on recorded operation data related to the target service;

and calling the target operation document to demonstrate the target business process.

Optionally, before the obtaining the target operation document corresponding to the identifier of the target service from the preset operation document library, the method further includes:

receiving a recording instruction, wherein the instruction comprises an identifier of the target service;

starting recording to acquire operation data corresponding to the identification of the target service;

processing the operation data to generate the target operation document;

and storing the target operation document and the target service identifier in a preset operation document library in a correlated manner.

Optionally, the operation data is at least one of: operation type, operation object, operation position and operation time.

Optionally, the starting recording to obtain operation data corresponding to the identifier of the target service includes:

under the condition that any operation action is detected, screenshot is conducted on the current page and stored, wherein the operation action is at least one of the following actions: clicking and keyboard inputting;

and analyzing the screenshot to determine the corresponding operation type, operation object and operation position.

Optionally, after analyzing the screenshot to determine an operation type, an operation object, and an operation position, the method further includes:

and combining a plurality of adjacent continuous operation data into one operation behavior aiming at the operation object under the condition that the operation object, the operation type and the operation position in each operation data are consistent and the difference value between every two adjacent operation time instants is less than a first threshold value.

under the condition that any operation data is matched with the adjacent last N operation data, the difference value between the operation moments corresponding to every two operation data is smaller than a second threshold value, and the operation types are click operations, reserving the any operation data, and deleting the N operation data; wherein N is any even number greater than 2;

alternatively, the first and second electrodes may be,

determining any operation data as a double-click operation aiming at an operation object in any operation data under the conditions that the operation data is matched with the adjacent last N operation data, the difference value between the operation time corresponding to every two operation data is smaller than a second threshold value, and the operation types are click operations; wherein N is any odd number greater than 2.

Optionally, the processing the operation data to generate the target operation document includes:

displaying the candidate storage formats on a storage interface in response to receiving the data storage request;

and according to the selected target candidate storage format, translating the operation data into a target operation document corresponding to the target candidate storage format.

Optionally, the translating the operation data into a target operation document corresponding to the target candidate storage format includes:

analyzing the operation data to acquire an operation type, an operation object and an operation position which are contained in the operation data;

based on the operation type, the operation object and the operation position, calling a Natural Language Processing (NLP) service to acquire an RPA system function corresponding to the operation data from a preset translation table;

and generating a corresponding target operation document based on the operation type, the operation object, the operation position and the RPA system function.

Another embodiment of the present disclosure provides a service processing apparatus based on AI and RPA, including:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a service processing demonstration request, and the demonstration request comprises an identifier of a target service;

a second obtaining module, configured to obtain, from a preset operation document library, a target operation document corresponding to the identifier of the target service, where the target operation document is a document generated by an RPA based on recorded operation data related to the target service;

and the demonstration module is used for calling the target operation document so as to demonstrate the target business process.

Optionally, the method further includes:

the receiving module is used for receiving a recording instruction, wherein the instruction comprises the identification of the target service;

the starting module is used for starting recording to acquire operation data corresponding to the identification of the target service;

the generating module is used for processing the operation data to generate the target operation document;

and the storage module is used for storing the target operation document and the target service identifier into the preset operation document library in a correlation manner.

Optionally, the starting module is specifically configured to:

Optionally, the starting module is further specifically configured to:

alternatively, the first and second electrodes may be,

Optionally, the generating module includes:

the display unit is used for responding to the received data storage request and displaying the candidate storage format on the storage interface;

and the translation unit is used for translating the operation data into a target operation document corresponding to the target candidate storage format according to the selected target candidate storage format.

Optionally, the display unit is specifically configured to:

and generating a corresponding target operation document based on the operation type, the operation object, the operation position and the RPA system function. An embodiment of another aspect of the present disclosure provides an electronic device, which includes: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the AI and RPA based traffic processing method as described above when executing the program.

A further aspect of the present disclosure is directed to a computer-readable storage medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the AI and RPA based traffic processing method as described above.

In another aspect of the present disclosure, a computer program product is provided, which includes a computer program, and when the computer program is executed by a processor, the AI and RPA based service processing method according to an embodiment of the foregoing aspect is implemented.

The service processing method, the device and the electronic device based on the AI and the RPA provided by the embodiments of the present disclosure may first obtain a service processing demonstration request, where the demonstration request includes an identifier of a target service, then obtain a target operation document corresponding to the identifier of the target service from a preset operation document library, where the target operation document is a document generated by the RPA based on recorded operation data related to the target service, and then call the target operation document to demonstrate a target service flow. Therefore, the corresponding target operation document can be determined based on the identification of the target service, and then the target operation document is called, so that the processing flow of the target service can be demonstrated, a user can clearly and visually know the processing process of the target service, the target service can be simply and quickly processed, the time is saved, and the efficiency is improved.

Additional aspects and advantages of the disclosure will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the disclosure.

Drawings

The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a schematic flowchart of a service processing method based on AI and RPA according to an embodiment of the present disclosure;

fig. 2 is a schematic flowchart of a service processing method based on AI and RPA according to another embodiment of the present disclosure;

FIG. 2A is a schematic page diagram of a target operation document according to an embodiment of the present disclosure;

fig. 3 is a schematic flowchart of a service processing method based on AI and RPA according to another embodiment of the present disclosure;

fig. 3A is a schematic page diagram of a screenshot provided in an embodiment of the present disclosure;

fig. 3B is a schematic page diagram of another screenshot provided by an embodiment of the present disclosure;

fig. 4 is a schematic flowchart of a service processing method based on AI and RPA according to still another embodiment of the present disclosure;

FIG. 4A is a schematic page diagram of a target operation document according to an embodiment of the present disclosure;

FIG. 4B is a schematic page diagram of another target operation document provided by an embodiment of the present disclosure;

FIG. 4C is a schematic diagram of a storage interface according to an embodiment of the disclosure;

fig. 4D is a schematic diagram of AI and RPA based service processing according to an embodiment of the disclosure;

fig. 5 is a schematic structural diagram of a service processing device based on AI and RPA according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the like or similar elements throughout. The embodiments described below with reference to the drawings are exemplary and intended to be illustrative of the present disclosure, and should not be construed as limiting the present disclosure.

The AI and RPA based service processing method, apparatus, and electronic device provided by the present disclosure are described in detail below with reference to the accompanying drawings.

For convenience of understanding, terms related to the present disclosure are explained below.

In the description of the present disclosure, Artificial Intelligence (AI) is a subject that studies computers to simulate certain mental processes and intelligent behaviors of humans (e.g., learning, reasoning, thinking, planning, etc.), both hardware-level and software-level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning technology, a deep learning technology, a big data processing technology, a knowledge map technology and the like.

In the description of the present disclosure, a Robotic Process Automation (RPA) may provide another way to automate an end user's manual Process by mimicking the way an end user manually operates at a computer.

In the description of the present disclosure, the term "business process demonstration request" may be a request that can be used to indicate that a business process demonstration is required, and may be any type of request, which is not limited by the present disclosure.

In the description of the present disclosure, the term "operation data" may be action data performed when a certain service is processed, such as "single click", "double click", "key input", and the like, which is not limited by the present disclosure. Fig. 1 is a schematic flow chart of a service processing method based on AI and RPA according to an embodiment of the present disclosure.

It should be noted that the RPA technology can intelligently understand the existing application of the electronic device through the user interface, automate repeated regular operations based on rules and in large batch, such as automatically and repeatedly reading mails, reading Office components, operating databases, web pages, client software, and the like, collect data and perform complex calculations, so as to generate files and reports in large batch, thereby greatly reducing the input of labor cost and effectively improving the Office efficiency through the RPA technology.

The main executing body of the AI and RPA based service processing method according to the embodiment of the present disclosure may be an RPA system, and may also be an AI and RPA based service processing device according to the embodiment of the present disclosure, and the RPA system and/or the AI and RPA based service processing device may be configured in any electronic device to execute the AI and RPA based service processing method according to the embodiment of the present disclosure. Optionally, the RPA system may include an RPA robot.

As shown in fig. 1, the service processing method based on AI and RPA includes the following steps:

step 101, a service processing demonstration request is obtained, wherein the demonstration request comprises an identification of a target service.

Generally, if each employee in a department required by the enterprise inside completes the same business, each employee may need to complete the task in the same way on a computer, but sometimes the operation flow in the process of completing the business may be complicated, and each employee needs to spend a lot of time on researching a specific operation flow, thereby not only wasting time, but also having low efficiency.

Therefore, in the embodiment of the present disclosure, before processing an unfamiliar service, a user may send a service processing demonstration request, so that after receiving the service processing demonstration request, the RPA system may determine the identifier of the target service by analyzing the service processing demonstration request.

The style or presentation form of the identifier of the target service may be set in advance, for example, "service 1", "service a 2", and the like, which is not limited in this disclosure.

In addition, the service processing demonstration request may be triggered manually, or may be triggered automatically according to a set period, and the like, which is not limited in this disclosure.

Step 102, obtaining a target operation document corresponding to the identifier of the target service from a preset operation document library, wherein the target operation document is a document generated by the RPA based on the recorded operation data related to the target service.

The preset operation document library stores operation documents corresponding to the services, and the operation documents and the corresponding services may be stored in association. For example, the operation document 1 is a document corresponding to the bank pipelining service; the operation document 2 is a document corresponding to the express bill number processing service, and the like. The present disclosure is not limited thereto.

Optionally, the processing procedure corresponding to each service may be recorded in advance to generate operation data, and then the operation data is processed to generate an operation document corresponding to the service, and the like, which is not limited in this disclosure.

Step 103, calling the target operation document to demonstrate the target business process.

It can be understood that, after the target operation document is determined, the RPA system may demonstrate the target business process corresponding to the target operation document by calling the target operation document.

For example, the target business is "banking pipelining business" and the target operation document is "document 1". If the content recorded in the document 1 is: first, open "apply 1"; second, enter "AW" in the input box. The RPA system may load and run the document 1 first and then may expose the flow of the "bank pipelining service". For example, the icon of "application 1" may be double-clicked first, and then the keyboard may be invoked, so that the keys "a" and "W" in the keyboard are in a selected state, thereby inputting "AW" in the input box, and so on.

It should be noted that the above examples are only illustrative, and should not be taken as limitations on target services, target operation documents, and the like in the embodiments of the present disclosure.

Therefore, in the embodiment of the disclosure, the operation process and the operation steps during the processing of the target service can be displayed to the user by demonstrating the target service flow, so that the user can clearly and intuitively know the processing process of the target service, the target service is simply and quickly processed, the time is saved, and the efficiency is improved.

The method and the device for demonstrating the business process can firstly obtain a business processing demonstration request, wherein the demonstration request comprises an identification of a target business, then obtain a target operation document corresponding to the identification of the target business from a preset operation document library, wherein the target operation document is a document generated by an RPA based on recorded operation data related to the target business, and then call the target operation document to demonstrate a target business process. Therefore, the corresponding target operation document can be determined based on the identification of the target service, and then the target operation document is called, so that the processing flow of the target service can be demonstrated, a user can clearly and visually know the processing process of the target service, the target service can be simply and quickly processed, the time is saved, and the efficiency is improved.

It can be understood that, in the actual implementation process, operation documents corresponding to each service may be generated in advance, and each service and the corresponding operation document may be stored in the operation document library in an associated manner. Therefore, after the service processing request is obtained, the target operation document corresponding to the identifier of the target service can be obtained from the preset operation document library based on the identifier of the target service, and the process is further described with reference to fig. 2.

Fig. 2 is a schematic flowchart of a service processing method based on AI and RPA according to an embodiment of the present disclosure.

As shown in fig. 2, the service processing method based on AI and RPA includes the following steps:

step 201, receiving a recording instruction, where the recording instruction includes an identifier of a target service.

The recording instruction may be an instruction in any form, for example, a voice form, or may also be a form triggered by a control, and the like, which is not limited in this disclosure.

Optionally, the recording instruction may be analyzed to determine the identifier of the target service included in the recording instruction. For example, by analyzing the recording instruction and determining that "service 1" is included therein, it may be determined that the corresponding target service is "service 1" and the like. The present disclosure is not limited thereto.

Step 202, start recording to obtain the operation data corresponding to the identifier of the target service.

It can be understood that after the identifier of the target service included in the recording instruction is determined, the processing procedure corresponding to the service may be recorded to obtain the operation data corresponding to the identifier of the target service.

Optionally, the operational data may be at least one of: operation type, operation object, operation position, operation time, etc., which are not limited in this disclosure.

The operation type may be various, for example, a mouse click action, or a key input action in a keyboard, and the like, which is not limited in this disclosure.

In addition, the operation object may also be any operated object, for example, any control, button, text, application, and the like, which is not limited in this disclosure.

In addition, the operation position may be a position where the operation action or the processing action occurs, for example, the operation position may be represented in a coordinate form, or may also be represented in other forms, and the like, which is not limited in this disclosure.

The operation time may be a time at which the operation action occurs, for example, the operation time may be a time at which the operation action occurs

For example, the recording instruction is analyzed to determine that the corresponding target service is 'express bill number processing', and then recording can be started. In the recording process, if it is detected that the recording medium is in the keyboard input state, where the key 1 is pressed, the operation data may be: key 1 is pressed. Alternatively, if it is detected that the "notepad" is clicked, the operation data may be: click behavior data of notepad.

Or, if it is detected that the key "ctrl" and the key "C" are simultaneously pressed in the "notepad", it may be determined that the shortcut combination key is pressed, and the operation objects are: the selected words.

Or, if it is detected that a "search box" in the browser is selected, the behavior of clicking the search box object once may be recorded. If it is detected that the acquisition keys "a", "m", "y", and "enter" are pressed when the "search box" is in the selected state, the corresponding operation data may be: input of the character string Amy.

It should be noted that the above examples are merely illustrative, and cannot be used as limitations on the manner of acquiring operation data and the like in the embodiments of the present disclosure.

Optionally, the acquired original operation data may be preprocessed based on a preset rule to determine corresponding operation data.

The preset rules may be various. For example, the following can be taken: if the time difference between two consecutive single-click operations on the same object is smaller than the first threshold, the two single-click operations may be determined as a double-click operation on the object, and the like, which is not limited in this disclosure.

For example, if the first threshold is 500ms, at t₀The time instant is obtained to the click action on the application 1 icon, and is at (t)₀+200ms) to the application 1 icon, and because the time difference between two consecutive clicking actions for the application 1 is 200ms, which is smaller than the first threshold 500m, the two clicking data for the application 1 can be processed, where the processed operation data is: double-click operation for application 1.

Alternatively, auxiliary keys, such as keys "ctrl", "shift", "alt", etc., may be set in advance, and these keys have no meaning of inputting information and may generally appear in a combination shortcut key, so that when the operation data is preprocessed, the operation data may be merged with other operation data to generate the preprocessed operation data. Alternatively, special input keys, such as "enter", "tab", etc., may be set, and these keys may generally appear after the user has finished inputting, and may generally be used to indicate the next step or the target of the transfer, etc. The present disclosure is not limited thereto.

For example, if the operation objects in the acquired operation data 1 are: the notebook, the operation type is keyboard input, the key "h" is pressed down, the operation object in the operation data 2 is: the notebook, the operation type is keyboard input, the key "e" is pressed down, the operation object in the operation data 3 is: the notebook, the operation type is keyboard input, the key "l" is pressed down, the operation object in the operation data 4 is: the notebook, the operation type is keyboard input, the key "l" is pressed down, the operation object in the operation data 5 is: the notebook, the operation type is keyboard input, the key "0" is pressed. If each operation data is stored in each row correspondingly, the operation data may be processed, for example, the 5 operation data are deleted and merged, for example, the current row is retained, and the next row is deleted, so that the processed operation data is "hello".

Or, if the operation objects in the operation data 1 and the operation data 2 are consistent, the operation types are all input by a keyboard, and the keys "enter" are all pressed, any one of the operation data may be retained, and the other operation data may be deleted. For example, the operation data 1 may be retained and the operation data 2 may be deleted.

Or, the operation data 1 and the operation data 2 are adjacent operation data, wherein the operation data 1 is at t₁At any time when any one of the auxiliary keys is pressed, operation data 2 is in (t)₁+10 seconds), any other key than the auxiliary key, the special input key is pressed, such as key "S" is pressed. Since the time difference between the operation data 1 and the operation data 2 is 10 seconds, which is greater than the set time threshold value of 5 seconds, it can be considered that "any one auxiliary key is pressed" in the operation data 1 is invalid data, and it can be deleted, and the key "S" in the reserved operation data 2 is pressed.

Step 203, processing the operation data to generate a target operation document.

The target operation document may be a document that can characterize the target business processing flow, and its form may be various, for example, it may be a flow definition document, or it may also be a flow analysis document, or it may also be a flow that the RPA system can directly run, and so on. The present disclosure is not limited thereto.

For example, the operation data is processed, and a page in the generated target operation document 1 may be as shown in fig. 2A. As can be seen from fig. 2A, in step 1, when "1122" is in the selected state, pressing "Ctrl" and "C" that is, copying "1122"; step 2: click "site 1", that is, open "site 1".

It should be noted that the above examples are only illustrative, and should not be taken as limitations on the format, content, and the like of the target operation document in the embodiments of the present disclosure.

And step 204, storing the target operation document and the target service identifier in a preset operation document library in a correlated manner.

The target operation document and the target service may be stored in a table form, or may also be stored in a document format, and the like, which is not limited in this disclosure.

For example, for a banking pipelining service, the corresponding service identifier may be "banking pipelining", and the operation document may be "1"; or, for the service for processing the express waybill number, the corresponding service identifier may be "express waybill number", the operation document may be "2", and the like.

Or, coding may be performed in advance for each service to determine a service identifier corresponding to each service. For example, for the banking business, the set business identifier may be "1", and the operation document may be "1A"; for the express bill number processing service, the set service identifier may be "2", and the corresponding operation document may be "2A", and so on.

It should be noted that the above examples are only illustrative, and should not be taken as limitations on target service identifiers, target operation documents, and the like in the embodiments of the present disclosure.

Therefore, in the embodiment of the present disclosure, the operation process corresponding to each service may be recorded in advance to generate the operation document corresponding to each service, and each service and the corresponding operation document are stored in a preset operation document library in an associated manner. Therefore, in the actual implementation process, if a service processing demonstration request is received, the demonstration request can be firstly analyzed to determine the mark of the target service contained in the demonstration request, and then the corresponding target operation document can be acquired from the operation document library according to the target service mark so as to show the operation process and the operation steps of the target service processing to the user, so that the time is saved, and the efficiency is improved.

According to the embodiment of the disclosure, a recording instruction may be received first, then recording is started to obtain operation data corresponding to the identifier of the target service, then the operation data is processed to generate a corresponding target operation document, and then the target operation document and the target service identifier may be stored in a preset operation document library in an associated manner. Therefore, the operation documents corresponding to the services can be generated in advance, each service and the corresponding operation document are stored in the preset operation document library in a correlation mode, and therefore in the actual use process, the corresponding operation document can be obtained from the operation document library according to the target service identification, efficiency is improved, and time is saved.

Fig. 3 is a schematic flow chart of a service processing method based on AI and RPA according to an embodiment of the present disclosure.

As shown in fig. 3, the service processing method based on AI and RPA includes the following steps:

step 301, receiving a recording instruction, where the recording instruction includes an identifier of a target service.

Step 302, under the condition that any operation action is detected, screenshot is conducted on the current page and the current page is stored, wherein the operation action is at least one of the following actions: clicking and keyboard input.

For example, if the operation is "click", it may be a click on any application icon, or may also be a click on a certain control, such as a click on an input box, so that the input box is in a selected state; or may be clicking on the text to make the text in a selected state, and the like, which is not limited by the present disclosure.

Step 303, analyzing the screenshot to determine the corresponding operation type, operation object and operation position.

The screenshot may be analyzed in any desirable manner, which is not limited in this disclosure.

For example, if the screenshot is as shown in fig. 3A, by analyzing the screenshot, it may be determined that the operation objects included in the screenshot are: the express bill number is '1122', the operation type is 'click', namely '1122' is in a selected state, and the operation positions are as follows: the position of "1122" in the "logistics information" table, so that the corresponding operation data can be determined, may be: "1122" and so on are selected, and this disclosure is not limited thereto.

Or, when any operation action is detected, performing screenshot on the current page, where the screenshot may be as shown in fig. 3B, and by analyzing the screenshot, it may be determined that the corresponding operation type is: the keyboard input, for example, the keys "Ctrl" and "C" are pressed, the operation object is "3344", the operation position is "3344" in the "logistics information" table, and the corresponding operation data is: copy "3344".

It should be noted that the above examples are only illustrative, and cannot be taken as a limitation on the style of the screenshot and the like in the embodiment of the present disclosure.

And 304, combining the plurality of operation data into one operation behavior aiming at the operation object under the condition that the operation object, the operation type and the operation position in each operation data are consistent and the difference value between every two adjacent operation time instants is less than a first threshold value in the plurality of adjacent continuous operation data.

For example, if the operation data 1 is: in the case where "single number 1" is in the selected state, t₁At any moment, the keyboard is in an input state, wherein the keys Ctrl and C are pressed down; the operation data 2 is: in the case where "single number 1" is in the selected state, t₂At any moment, the keyboard is in an input state, wherein the keys Ctrl and C are pressed down; the operation data 3 is: in the case where "single number 1" is in the selected state, t₃At the moment, the keyboard is in an input state, wherein the keys "Ctrl" and "C" are pressed.

Wherein, t₁Time and t₂The difference between the moments is 100ms, t₂Time and t₃The time difference is 200ms, and if the first threshold is 500ms, the operation data 1, the operation data 2, and the operation data 3 may be combined into one order number for the operation target1 "operational behavior: when the single number 1 is in the selected state, the keys Ctrl and C are pressed. Alternatively, it may be understood that only any one of the operation data is retained, such as retaining operation data 1, deleting operation data 2, and deleting operation data 3; alternatively, the operation data 2 is retained, the operation data 1 and the operation data 3 are deleted, and the like. It should be noted that the above example is only an illustrative example, and cannot be taken as an operation behavior for an operation object in one merging of a plurality of operation data in the embodiment of the present disclosure.

Optionally, when any operation data is matched with the next N adjacent operation data, the difference between the operation times corresponding to each two operation data is smaller than the second threshold, and the operation types are all click operations, retaining any operation data, and deleting the N operation data; wherein N is any odd number greater than 2.

For example, operation data 0 is: t is t₀Clicking operation aiming at the input box at moment; followed by operation data 1 and operation data 2, which are adjacent in sequence thereto. Wherein, the operation data 1 is: t is t₁Clicking operation aiming at the same input box at any moment; the operation data 2 is: t is t₂The time is the click operation for the same "input box". If the second threshold is 2s, where t₀Time and t₁The difference between the moments is 500ms, t₁Time and t₂If the time difference is 1s and is smaller than the second threshold 2 seconds, it may be considered that the operation is repeated, and only the operation data 0 may be retained and the operation data 1 and the operation data 2 may be deleted. Alternatively, the operation data 1 may be retained, and the operation data 0 and the operation data 2 may be deleted; alternatively, the operation data 2 is retained, the operation data 0 and the operation data 1 are deleted, and so on.

It should be noted that the above examples are merely illustrative, and should not be taken as limitations on retaining operation data, deleting operation data, and the like in the embodiments of the present disclosure.

Optionally, when any operation data is matched with the next N adjacent operation data, the difference between the operation times corresponding to each two operation data is smaller than the second threshold, and the operation types are all click operations, determining that the operation data is a double-click operation for the operation object in any operation data; wherein N is any even number greater than 2.

For example, operation data 0 is: t is t₀Clicking operation aiming at the icon of the application program 1 at moment; next to this are operation data 1, operation data 2, and operation data 3 in this order. Wherein, the operation data 1 is: t is t₁Clicking operation aiming at the icon of the application program 1 at moment; the operation data 2 is: t is t₂Clicking operation aiming at the icon of the application program 1 at moment; the operation data 3 is: t is t₃The time is the click operation for the "application 1" icon. If the second threshold is 2s, where t₀Time and t₁The difference between the moments is 1ms, t₁Time and t₂The difference between the moments is 0.8s, t₂Time and t₃If the time difference is 1.2s and is less than the second threshold 2 seconds, the above operation may be regarded as being repeated, and may be determined as a double-click operation on the "application 1" icon.

According to the embodiment of the disclosure, a recording instruction may be received first, then, when any operation action is detected, a current page is subjected to screenshot and stored, then, the screenshot may be analyzed to determine a corresponding operation type, an operation object, and an operation position, in a plurality of adjacent continuous operation data, the operation object, the operation type, and the operation position in each operation data are consistent, and a difference between every two adjacent operation times is smaller than a first threshold, the plurality of operation data are merged into one operation behavior for the operation object, then, the operation data may be processed to generate a target operation document, and then, the target operation document and the target service identifier may be stored in a preset operation document library in an associated manner. Therefore, the corresponding operation data can be determined by analyzing the screenshot corresponding to any operation, and then the operation data can be processed to generate the operation document corresponding to each service in advance, so that the corresponding operation document can be obtained from the operation document library according to the target service identifier in the actual use process, the efficiency is improved, and the time is saved.

Fig. 4 is a schematic flowchart of a service processing method based on AI and RPA according to an embodiment of the present disclosure.

As shown in fig. 4, the service processing method based on AI and RPA includes the following steps:

step 401, receiving a recording instruction, where the instruction includes an identifier of a target service.

Step 402, recording is started to obtain operation data corresponding to the identification of the target service.

It should be noted that specific contents and implementation manners of step 401 and step 402 may refer to descriptions of other embodiments of the present disclosure, and are not described herein again.

Step 403, in response to receiving the data storage request, displaying the candidate storage format on the storage interface.

The data storage request may be any request for representing the storage of the operation data, and the expression form, the type, and the like of the data storage request are not limited in the present disclosure.

For example, if it is detected that the "save as" control is triggered, it may be determined that a data storage request is received; or detecting that the "export" control is triggered, it may be determined that a data storage request is received, etc., which is not limited by this disclosure.

In addition, the storage interface may be an interface when storing the operation data, and the style, the display interface, and the like of the storage interface are not limited in the present disclosure.

In addition, the candidate format may be multiple formats, for example, may be a "process definition document" format, or may also be a "process analysis document" format, or may also be an "RPA process" format, and the like, which is not limited in this disclosure.

It will be appreciated that for the "RPA flow" format, it may be a document format that the RPA system may directly invoke. For example, the RPA system can automatically perform the demonstration of the target service processing process by loading the generated target operation document in the format of the "RPA flow".

Or, for the "flow definition document", it may contain operation data in the target business processing process.

For example, as for the service 1, if the schematic diagram of any page in the corresponding target operation document is shown in fig. 4A, as can be seen from fig. 4A, the operation data in the processing process of the service 1 may be: step 1, pressing down a key Ctrl and a key C, namely copying 1122; and 2, clicking the website 'WWW.xx', namely opening the website 'WWW.xx'.

Optionally, statistics may be summarized for the entire operation process. For example, as shown in fig. 4A, a total of 2 applications involved in the processing flow can be displayed, and the steps total 6, where 1 key pressing action, 4 single clicking actions, 1 double clicking action, and the duration is 38 seconds. Specific statistical data are that in Excel, the key press behavior is 1 time, the click behavior is 2 times, and the double click behavior is 1 time; in "Explorer", the button is pressed 0 times, the click is performed 2 times, and the double click is performed 0 times.

It should be noted that the above examples are only illustrative, and should not be taken as limitations on the style, content, and the like of the target operation document in the embodiments of the present disclosure.

Step 404, translating the operation data into a target operation document corresponding to the target candidate storage format according to the selected target candidate storage format.

For example, the schematic diagram of the storage interface may be as shown in fig. 4C, and then it may be determined that the selected target candidate storage format should be a "flow definition document" or the like, which is not limited by the present disclosure.

It will be appreciated that the format or type of the target operation document is related to the target candidate storage format. For example, the target candidate storage format is "flow definition document", and the generated target operation document may be a document of type 1. Alternatively, the target candidate storage format is a "task file", and the generated target operation document may be a document of type 2, and so on. The present disclosure is not limited thereto.

Optionally, in the process of translating the operation data to generate a corresponding target operation document, the operation data may be analyzed to obtain an operation type, an operation object and an operation position included in the operation data, and then, based on the operation type, the operation object and the operation position, a natural language processing NLP service may be invoked to obtain an RPA system function corresponding to the operation data from a preset translation table; and then generating a corresponding target operation document based on the operation type, the operation object, the operation position and the RPA system function.

Natural Language Processing (NLP) is a computer used to process, understand and use human languages (such as chinese and english), which is a cross discipline between computer science and linguistics and is also commonly called computational linguistics. Since natural language is the fundamental mark that humans distinguish from other animals. Without language, human thinking has not been talk about, so natural language processing embodies the highest task and context of artificial intelligence, that is, only when a computer has the capability of processing natural language, the machine has to realize real intelligence.

In addition, the RPA system function may be a function required for running an RPA process, which is not limited in this disclosure.

In addition, the translation table may be a resource file predefined according to the RPA system, where the resource file may include an operation type, an operation object, a correspondence between an operation location and an RPA system function, and the like, which is not limited in this disclosure.

It is understood that the operation types are different, and the RPA system functions corresponding to the operation data may be the same or may be different.

For example, when the target candidate storage format is "RPA flow", the operation type included in the operation data is determined to be "double-click operation", the operation object is "application 2", and the operation position is "icon for application 2" by analyzing the operation data. The NLP service may then be invoked to look up the data associated with the "double-click" operation in a preset translation table to determine the corresponding RPA system function. Then, the "double-click operation", "application 2", and "icon of application 2" may be used as the parameter of the RPA system function, so that the target operation document corresponding to the operation data may be generated.

It should be noted that the above examples are only illustrative, and should not be taken as limitations on the operation data, the RPA system function, and the manner of generating the target operation document in the embodiments of the present disclosure.

It can be understood that, if there are multiple pieces of operation data in a certain service flow, each piece of operation data may be sequentially analyzed and traversed in a preset translation table to determine a corresponding RPA system function, and then a target operation document corresponding to the service flow may be generated according to the RPA system function corresponding to each piece of operation data, and the like, which is not limited in this disclosure.

Alternatively, the operation data may be translated into the target operation document corresponding to the target candidate storage format in any desirable manner, such as any translation technique, and the like, which is not limited by the present disclosure.

Step 405, storing the target operation document and the target service identifier in a preset operation document library in a correlated manner.

The AI and RPA based service processing method provided by the present disclosure may be applied to any RPA scenario, and the execution subject may be any RPA robot, for example, may be a process recorder, or may also be a process creator, or may also be a process recorder and a process creator, etc., which is not limited by the present disclosure.

The procedure of AI and RPA based traffic processing provided by the present disclosure is explained below with reference to fig. 4D.

For example, in the schematic diagram shown in fig. 4D, a recording instruction may be sent when processing a service. After receiving the recording instruction, the flow recorder (recorder) may determine the identifier of the corresponding target service first, and then may start recording. And then, acquiring operation data corresponding to the identifier of the target service, and generating an Tc File File based on the operation data when receiving a recording stop instruction. After receiving the data storage request, for example, in the case that the "export" control is triggered, the Tc File may be translated to generate a target operation document, for example, a Task script File. The Task script file is imported into a process Creator (UIBot Creator), and the Task script file can be loaded and run, so that the previously recorded service processing process can be reproduced.

It should be noted that the foregoing examples are merely illustrative, and should not be taken as limitations on the service processing procedures and the like in the embodiments of the present disclosure.

According to the embodiment of the disclosure, a recording instruction may be received first, then recording may be started to obtain operation data corresponding to an identifier of a target service, in the case of receiving a data storage request, a candidate storage format may be displayed on a storage interface, and then the operation data may be translated into a target operation document corresponding to the target candidate storage format according to the selected target candidate storage format. Therefore, after the operation data of a certain business process is obtained, a corresponding operation document can be generated based on the selected target candidate storage format and the operation data, and then the operation document is called to demonstrate the processing flow of the business, so that a user can clearly and intuitively know the processing process of the target business, the target business is simply and quickly processed, the time is saved, and the efficiency is improved.

In order to implement the above embodiments, the present disclosure further provides a service processing device based on AI and RPA.

Fig. 5 is a schematic structural diagram of a service processing device based on AI and RPA according to an embodiment of the present disclosure.

As shown in fig. 5, the AI and RPA based service processing apparatus 500 includes: a first acquisition module 510, a second acquisition module 520, and a presentation module 530.

The first obtaining module 510 is configured to obtain a service processing demonstration request, where the demonstration request includes an identifier of a target service.

A second obtaining module 520, configured to obtain, from a preset operation document library, a target operation document corresponding to the identifier of the target service, where the target operation document is a document generated by the RPA based on the recorded operation data related to the target service.

And the demonstration module 530 is used for calling the target operation document so as to demonstrate the target business process.

Optionally, the method further includes:

Optionally, the starting module is specifically configured to:

Optionally, the starting module is further specifically configured to:

alternatively, the first and second electrodes may be,

Optionally, the generating module includes:

Optionally, the display unit is specifically configured to:

It should be noted that, for the functions and the specific implementation principles of the modules in the embodiments of the present disclosure, reference may be made to the embodiments of the methods described above, and details are not described here again.

The service processing device based on the AI and the RPA according to the embodiment of the present disclosure may first obtain a service processing demonstration request, where the demonstration request includes an identifier of a target service, then obtain a target operation document corresponding to the identifier of the target service from a preset operation document library, where the target operation document is a document generated by the RPA based on recorded operation data related to the target service, and then call the target operation document to demonstrate a target service flow. Therefore, the corresponding target operation document can be determined based on the identification of the target service, and then the target operation document is called, so that the processing flow of the target service can be demonstrated, a user can clearly and visually know the processing process of the target service, the user can simply and quickly process the target service, the time is saved, and the efficiency is improved.

In order to implement the above embodiments, the present disclosure also provides an electronic device, including: the device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the program, the AI and RPA based service processing method as proposed by the foregoing embodiments of the disclosure is realized.

In order to implement the foregoing embodiments, the present disclosure also proposes a non-transitory computer-readable storage medium storing a computer program which, when executed by a processor, implements the AI and RPA based traffic processing method as proposed by the foregoing embodiments of the present disclosure.

In order to implement the foregoing embodiments, the present disclosure also proposes a computer program product, which when being executed by an instruction processor in the computer program product, executes the AI and RPA based traffic processing method proposed by the foregoing embodiments of the present disclosure.

FIG. 6 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure. The electronic device 12 shown in fig. 6 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present disclosure.

As shown in FIG. 6, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. These architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, to name a few.

Electronic device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, and commonly referred to as a "hard drive"). Although not shown in FIG. 6, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the disclosure.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described in this disclosure.

Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with electronic device 12, and/or with any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via the Network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes various functional applications and data processing, for example, implementing the methods mentioned in the foregoing embodiments, by executing programs stored in the system memory 28.

According to the technical scheme of the embodiment of the disclosure, a service processing demonstration request can be obtained first, wherein the demonstration request comprises an identifier of a target service, then a target operation document corresponding to the identifier of the target service is obtained from a preset operation document library, wherein the target operation document is a document generated by an RPA based on recorded operation data related to the target service, and then the target operation document is called to demonstrate a target service process. Therefore, the corresponding target operation document can be determined based on the identification of the target service, and then the target operation document is called, so that the processing flow of the target service can be demonstrated, a user can clearly and visually know the processing process of the target service, the user can simply and quickly process the target service, the time is saved, and the efficiency is improved.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, "plurality" means at least two, e.g., two, three, etc., unless explicitly defined otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present disclosure in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure, and that changes, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present disclosure.

Claims

1. A service processing method based on artificial intelligence AI and robot flow automation RPA is characterized by comprising the following steps:

2. The method according to claim 1, wherein before the obtaining of the target operation document corresponding to the identifier of the target service from the preset operation document library, the method further comprises:

processing the operation data to generate the target operation document;

3. The method of claim 2, wherein the operational data is at least one of: operation type, operation object, operation position and operation time.

4. The method of claim 2, wherein the initiating recording to obtain operational data corresponding to the identity of the target service comprises:

5. The method of claim 4, after said parsing said screenshot to determine a corresponding operation type, operation object, and operation location, further comprising:

6. The method of claim 2, wherein the initiating recording to obtain operational data corresponding to the identity of the target service comprises:

alternatively, the first and second electrodes may be,

7. The method of claim 2, wherein said processing the operational data to generate the target operational document comprises:

8. The method of claim 7, wherein said translating said operational data into a target operational document corresponding to said target candidate storage format comprises:

analyzing the operation data to obtain an operation type, an operation object and an operation position which are contained in the operation data;

9. An AI and RPA based service processing apparatus, comprising:

10. The apparatus of claim 9, further comprising:

11. The apparatus of claim 10, wherein the operational data is at least one of: operation type, operation object, operation position and operation time.

12. The apparatus of claim 10, wherein the start module is specifically configured to:

13. An electronic device, comprising: a memory, a processor and a program stored on the memory and executable on the processor, the processor implementing the AI and RPA based traffic processing method according to any one of claims 1-8 when executing the program.

14. A computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements the AI and RPA based traffic processing method according to any one of claims 1-8.

15. A computer program product comprising a computer program which, when executed by a processor, implements the AI and RPA based traffic processing method according to any one of claims 1-8.