Information extraction method, device, medium and electronic device combining RPA and AI

By selecting artificial intelligence AI modules and obtaining information extraction templates in the editing interface of robot process automation RPA, the problem of low code development and design efficiency is solved, the information extraction efficiency and effect is improved, and the degree of intelligence is enhanced.

CN112558954BActive Publication Date: 2024-11-12BEIJING LAIYE NETWORK TECH CO LTD +1
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202011599189.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-29
Publication Date
2024-11-12
Estimated Expiration
2040-12-29

AI Technical Summary

Technical Problem

When using artificial intelligence AI capabilities to develop and design codes for robot process automation RPA, it requires a lot of labor costs, is not efficient and is not intelligent enough, which affects the efficiency and effect of information extraction.

Method used

By displaying multiple candidate AI modules in the editing and guidance interface of robot process automation RPA, selecting target modules, obtaining corresponding information extraction templates from the artificial intelligence AI platform, and extracting information of target text based on the templates, improving code development and design efficiency and intelligence.

Benefits of technology

It effectively improves the information extraction efficiency and effect of RPA based on robot process automation, reduces the complexity and labor cost of code development, and improves the degree of intelligence.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112558954B_ABST
    Figure CN112558954B_ABST
Patent Text Reader

Abstract

The present application proposes an information extraction method, device, medium and electronic device combining RPA and AI, which is applied to natural language processing (NLP). The method includes displaying an editing guide interface for implementing robotic process automation (RPA), and the editing guide interface includes: multiple candidate artificial intelligence (AI) modules; in response to a first selection instruction, determining a target artificial intelligence (AI) module selected by the selection instruction from multiple candidate artificial intelligence (AI) modules; obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from an artificial intelligence (AI) platform; and extracting information from the target text according to the information extraction template. Through this application, when using artificial intelligence (AI) capabilities to design robotic process automation (RPA), the efficiency and intelligence of code development and design can be effectively improved, thereby assisting in improving the efficiency and effect of information extraction based on robotic process automation (RPA).
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of natural language processing technology, and in particular to an information extraction method, device, medium and electronic device combining RPA (Robotic Process Automation) and AI (Artificial Intelligence). Background Art

[0002] 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.

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

[0004] In the related art, when using artificial intelligence (AI) capabilities to develop RPA applications to achieve natural language processing (NLP), it is usually done by developing extension plug-ins and using the extension plug-ins in the tools for developing RPA. For example, to implement an RPA+AI automation process, developers need to first complete the configuration on the artificial intelligence (AI) platform to achieve the output of the expected extraction results, and then use other programming languages ​​to write extension plug-ins based on the interface provided by the platform to achieve repeated calls to the extension plug-ins to obtain results. Finally, reference the extension plug-in in the RPA development tool and write a large amount of program code for extracting results to achieve the use of the extracted results in RPA.

[0005] In this way, when using artificial intelligence (AI) capabilities to develop and design code for robotic process automation (RPA), a lot of labor costs are required to write program code, which is inefficient and not intelligent enough, thus affecting the efficiency and effectiveness of information extraction based on robotic process automation (RPA). Summary of the invention

[0006] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0007] To this end, the purpose of this application is to propose an information extraction method, device, medium and electronic device that combines RPA and AI, which can effectively improve the efficiency and intelligence of code development and design when using artificial intelligence AI capabilities to design robotic process automation RPA, thereby assisting in improving the efficiency and effect of information extraction based on robotic process automation RPA.

[0008] To achieve the above-mentioned objectives, the information extraction method combining RPA and AI proposed in the first aspect of the embodiment of the present application is applied to natural language processing (Natural Language Processing, NLP), including: displaying an editing guidance interface for implementing robotic process automation RPA, the editing guidance interface including: multiple candidate artificial intelligence AI modules; in response to a first selection instruction, determining the target artificial intelligence AI module selected by the selection instruction from the multiple candidate artificial intelligence AI modules; obtaining an information extraction template corresponding to the target artificial intelligence AI module from the artificial intelligence AI platform; and extracting information from the target text according to the information extraction template.

[0009] The information extraction method combining RPA and AI proposed in the first aspect of the embodiment of the present application realizes the editing guidance interface of the robotic process automation (RPA) by displaying, and the editing guidance interface includes: multiple candidate artificial intelligence (AI) modules, in response to a first selection instruction, determining the target artificial intelligence (AI) module selected by the selection instruction from the multiple candidate artificial intelligence (AI) modules, obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, and extracting information from the target text according to the information extraction template. When using artificial intelligence (AI) capabilities to design robotic process automation (RPA), it can effectively improve the efficiency and intelligence of code development and design, thereby assisting in improving the efficiency and effect of information extraction based on robotic process automation (RPA).

[0010] To achieve the above-mentioned purpose, the information extraction device combining RPA and AI proposed in the second aspect embodiment of the present application is applied to natural language processing (Natural Language Processing, NLP), including: a first display module, used to display an editing guide interface for implementing robotic process automation RPA, and the editing guide interface includes: multiple candidate artificial intelligence AI modules; a determination module, used to respond to a first selection instruction, and determine the target artificial intelligence AI module selected by the selection instruction from the multiple candidate artificial intelligence AI modules; an acquisition module, used to obtain an information extraction template corresponding to the target artificial intelligence AI module from the artificial intelligence AI platform; and an extraction module, used to extract information from the target text according to the information extraction template.

[0011] The information extraction device combining RPA and AI proposed in the second aspect of the embodiment of the present application realizes the editing guidance interface of the robotic process automation RPA by displaying, and the editing guidance interface includes: multiple candidate artificial intelligence AI modules, responding to the first selection instruction, determining the target artificial intelligence AI module selected by the selection instruction from the multiple candidate artificial intelligence AI modules, obtaining the information extraction template corresponding to the target artificial intelligence AI module from the artificial intelligence AI platform, and extracting information from the target text according to the information extraction template. When using artificial intelligence AI capabilities to design robotic process automation RPA, it can effectively improve the efficiency and intelligence of code development and design, thereby assisting in improving the efficiency and effect of information extraction based on robotic process automation RPA.

[0012] To achieve the above-mentioned objectives, the non-temporary computer-readable storage medium proposed in the third aspect embodiment of the present application, when the instructions in the storage medium are executed by the processor of the electronic device, enables the electronic device to execute an information extraction method combining RPA and AI, and the method includes: the information extraction method combining RPA and AI proposed in the first aspect embodiment of the present application.

[0013] The non-temporary computer-readable storage medium proposed in the third aspect embodiment of the present application realizes the editing guidance interface of the robotic process automation (RPA) by displaying, and the editing guidance interface includes: multiple candidate artificial intelligence (AI) modules, in response to a first selection instruction, determining the target artificial intelligence (AI) module selected by the selection instruction from the multiple candidate artificial intelligence (AI) modules, obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, and extracting information from the target text according to the information extraction template. When using artificial intelligence (AI) capabilities to design robotic process automation (RPA), it can effectively improve the efficiency and intelligence of code development and design, thereby assisting in improving the efficiency and effect of information extraction based on robotic process automation (RPA).

[0014] The fourth aspect of the present application also proposes an electronic device, which includes a shell, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is placed inside the space enclosed by the shell, and the processor and the memory are arranged on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the electronic device; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the information extraction method combining RPA and AI proposed in the embodiment of the first aspect of the present application.

[0015] The electronic device proposed in the fourth aspect of the embodiment of the present application realizes the editing guide interface of the robotic process automation (RPA) by displaying, and the editing guide interface includes: multiple candidate artificial intelligence (AI) modules, in response to a first selection instruction, determining the target artificial intelligence (AI) module selected by the selection instruction from the multiple candidate artificial intelligence (AI) modules, obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, and extracting information from the target text according to the information extraction template. When using artificial intelligence (AI) capabilities to design the robotic process automation (RPA), it can effectively improve the efficiency and intelligence of code development and design, thereby assisting in improving the efficiency and effect of information extraction based on the robotic process automation (RPA).

[0016] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0018] Figure 1 It is a flowchart of an information extraction method combining RPA and AI proposed in one embodiment of the present application;

[0019] Figure 2 This is a schematic diagram of the editing guide interface in the embodiment of the present application;

[0020] Figure 3 This is a schematic diagram of the text editing area in the embodiment of the present application;

[0021] Figure 4 This is a schematic diagram of an initial information extraction template in an embodiment of the present application;

[0022] Figure 5 This is a schematic diagram of a visual structure code in an embodiment of the present application;

[0023] Figure 6 is a flowchart of an information extraction method combining RPA and AI proposed in another embodiment of the present application;

[0024] Figure 7 This is a schematic diagram of the creation interface of the process engineering in the embodiment of the present application;

[0025] Figure 8 This is a schematic diagram of the process editing interface in the embodiment of this application;

[0026] Fig. 9 It is a structural diagram of an information extraction device combining RPA and AI proposed in one embodiment of the present application;

[0027] Fig.10 is a schematic diagram of the structure of an information extraction device combining RPA and AI proposed in another embodiment of the present application;

[0028] Fig.11 It is a schematic diagram of the structure of an electronic device proposed in one embodiment of the present application. DETAILED DESCRIPTION

[0029] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be construed as limiting the present application. On the contrary, the embodiments of the present application include all changes, modifications and equivalents that fall within the spirit and connotation of the appended claims.

[0030] In order to solve the technical problem in the related art that when using artificial intelligence (AI) capabilities to develop and design the code of Robotic Process Automation (RPA), a lot of labor costs are required to write program codes, which is inefficient and not intelligent enough, thereby affecting the efficiency and effect of information extraction based on Robotic Process Automation (RPA), the embodiment of the present application provides an information extraction method combining RPA and AI, which realizes the editing guidance interface of Robotic Process Automation (RPA) by displaying, and the editing guidance interface includes: multiple candidate artificial intelligence (AI) modules, in response to a first selection instruction, determining a target artificial intelligence (AI) module selected by the selection instruction from multiple candidate artificial intelligence (AI) modules, obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, and extracting information from the target text according to the information extraction template. When using artificial intelligence (AI) capabilities to design Robotic Process Automation (RPA), the efficiency and intelligence of code development and design can be effectively improved, thereby assisting in improving the efficiency and effect of information extraction based on Robotic Process Automation (RPA).

[0031] Figure 1 This is a flowchart of an information extraction method combining RPA and AI proposed in one embodiment of the present application.

[0032] This embodiment is illustrated by taking the information extraction method combining RPA and AI as an information extraction device combining RPA and AI.

[0033] In this embodiment, the information extraction method combining RPA and AI can be configured in an information extraction device combining RPA and AI. The information extraction device combining RPA and AI can be set in a server, or can also be set in an electronic device. The embodiment of the present application is not limited to this.

[0034] This embodiment takes the information extraction method combining RPA and AI configured in an electronic device as an example.

[0035] Among them, electronic devices such as smart phones, tablet computers, personal digital assistants, e-books and other hardware devices have various operating systems.

[0036] It should be noted that the execution entity of the embodiments of the present application may be, for example, a central processing unit (CPU) in an electronic device in terms of hardware, or may be, for example, a natural language processing (NLP) related service in an electronic device in terms of software, without limitation.

[0037] In addition, the "extraction" in this application refers to the process of information extraction that combines robotic process automation (RPA) and artificial intelligence (AI). That is to say, the information extraction process is a fully automated information extraction process, and the information extraction process is also combined with artificial intelligence (AI) to realize automated information extraction in natural language processing (Natural Language Processing, NLP).

[0038] The present application can be specifically applied to Natural Language Processing (NLP) of Artificial Intelligence AI, Natural Language Processing (NLP), that is, the field of computer science, artificial intelligence, and linguistics that focuses on the interaction between computers and human (natural) language.

[0039] For example, the process of information extraction based on the full-process automation in this application can trigger the full-process automation execution of obtaining the information extraction template corresponding to the target artificial intelligence AI module from the artificial intelligence AI platform after determining the target artificial intelligence AI module, and extracting information from the target text according to the information extraction template.

[0040] See also Figure 1 , the method comprising:

[0041] S101: Displaying an editing guide interface for implementing Robotic Process Automation (RPA), wherein the editing guide interface includes: a plurality of candidate artificial intelligence (AI) modules.

[0042] Among them, the editing guidance interface is used to guide developers to select the required artificial intelligence AI module. The artificial intelligence AI module selected by the developer can be one or more of multiple candidate artificial intelligence AI modules. Different candidate artificial intelligence AI modules correspond to different artificial intelligence AI information extraction rules. Candidate artificial intelligence AI modules include: general text recognition, general table recognition, general multi-bill recognition, general card recognition, custom template recognition, information extraction, etc., and there is no restriction on this.

[0043] Among them, the information extraction rules corresponding to the candidate artificial intelligence AI modules can be pre-configured on the artificial intelligence AI platform. When the information extraction rules corresponding to the required artificial intelligence AI module are determined, they can be directly obtained from the artificial intelligence AI platform without any restriction.

[0044] For example, on an artificial intelligence (AI) platform, some extraction rules (such as regular expressions, custom vocabularies, text, arbitrary text, preset vocabularies, etc.) can be pre-adopted. After configuring these extraction rules, massive sample texts can be used to perform machine learning training on the configured extraction rules, and a stable extraction template can be trained (the extraction template can correspond to the extraction rules), which can then be called by the platform to implement robotic process automation (RPA).

[0045] like Figure 2 As shown, Figure 2 This is a schematic diagram of the editing guidance interface in the embodiment of the present application. The editing guidance interface 21 includes: multiple candidate artificial intelligence AI modules, different candidate artificial intelligence AI modules correspond to the above-mentioned different artificial intelligence AI information extraction rules, and each candidate artificial intelligence AI module can be some operable controls, so that the user can trigger the selection of one or more required artificial intelligence AI modules from multiple candidate artificial intelligence AI modules by clicking.

[0046] S102: In response to a first selection instruction, determining a target artificial intelligence AI module selected by the selection instruction from a plurality of candidate artificial intelligence AI modules.

[0047] The AI ​​module selected by the developer can be called the target AI module. Figure 2 , the information extraction rule corresponding to the target artificial intelligence AI module can be information extraction.

[0048] Among them, information extraction (IE) is to structure the information contained in the text and turn it into information in a tabular form (which can be called structured data). For example, the input to the information extraction system is the original text, and the output is information points in a fixed format. The information points are extracted from various texts and then integrated in a unified form. Information extraction technology can be used to analyze the part of the text that contains relevant information. In short, it is to extract structured data from unstructured text.

[0049] The above-mentioned first selection instruction can be that the platform implementing the robotic process automation RPA recognizes the click action of the developer, determines the click position corresponding to the click action, matches the click position with the layout position of each candidate artificial intelligence AI module to determine the target layout position, and generates it according to the target layout position. Then, the platform implementing the robotic process automation RPA can respond to the first selection instruction and determine the target artificial intelligence AI module selected by the selection instruction from multiple candidate artificial intelligence AI modules.

[0050] In some other embodiments, the above Figure 2 The display area 22 (for displaying selected information) is also included, and the information of the target artificial intelligence AI module can be displayed in the display area without any restriction.

[0051] Optionally, in some embodiments, Figure 2 As shown, the editing guidance interface also includes: a text configuration control 23, after determining the target artificial intelligence AI module selected by the selection instruction from multiple candidate artificial intelligence AI modules, it also responds to the first operation instruction of the text configuration control to display the text editing area in the editing guidance interface; in response to the editing instruction of the text editing area, the text edited by the editing instruction is used as the target text, thereby effectively improving the coherence of each link in the information extraction process, so that developers can quickly and conveniently implement robotic process automation RPA combined with artificial intelligence AI capabilities for information extraction.

[0052] See also Figure 3 , Figure 3 This is a schematic diagram of the text editing area in the embodiment of the present application. The text configuration control is, for example, Figure 2 When the first operation instruction for [Select text source] is detected, the text editing area ( Figure 3 31), and then, in response to an editing instruction to the text editing area, the text edited by the editing instruction is used as the target text.

[0053] For example, the target texts could be the following four announcements:

[0054] Announcement 1: Xiao Baoyu, a senior executive who holds 300,000 shares of the Company (accounting for 0.0284% of the Company's total share capital), intends to reduce his holdings of the Company's shares by no more than 75,000 shares (accounting for 0.0071% of the Company's total share capital) through centralized bidding within six months after fifteen trading days from the date of this announcement, and has confirmed this with the supervisor.

[0055] Announcement 2: Supervisor Zhao Yi, who holds 158,858 shares of the Company (accounting for 0.0150% of the Company's total share capital), plans to reduce his holdings of the Company's shares by no more than 39,715 shares (accounting for 0.0038% of the Company's total share capital) through centralized bidding or block trading within six months after fifteen trading days from the date of this announcement.

[0056] Announcement 3: Ao Zhiqiang, a senior executive who holds 1,208,035 shares of the Company (accounting for 0.1143% of the Company's total share capital), plans to reduce his holdings of the Company's shares by no more than 250,000 shares (accounting for 0.0237% of the Company's total share capital) through centralized bidding or block trading within six months after fifteen trading days from the date of this announcement.

[0057] Announcement 4: Huo Weiping, the controlling shareholder and one of the actual controllers who holds 130,162,360 shares of the Company (accounting for 12.3180% of the Company's total share capital), intends to reduce his holdings of the Company's shares by no more than 2,000,000 shares (accounting for 0.1893% of the Company's total share capital) through centralized bidding or block trading within six months after fifteen trading days from the date of this announcement.

[0058] The developer's information extraction requirements may be to extract the values ​​of the four fields, namely, name, method, increase / decrease, and number of shares, from the above four announcement texts with similar formats, and form the following Table 1 (this table is the structured data extracted from the target text):

[0059] Table 1

[0060]

[0061] The target text may be directly input into the text editing area, or may be text in a file selected from a local storage area, and there is no limitation to this.

[0062] S103: Obtaining an information extraction template corresponding to the target artificial intelligence AI module from the artificial intelligence AI platform.

[0063] After the target artificial intelligence AI module selected by the selection instruction is determined from multiple candidate artificial intelligence AI modules in response to the first selection instruction, an information extraction template corresponding to the target artificial intelligence AI module can be automatically obtained from the artificial intelligence AI platform.

[0064] There can also be one or more AI platforms, which can be set by the developer in the editing guide interface. See the above Figure 2 ,exist Figure 2 The extractor selection control 24 is also included. When the developer selects the extractor selection control, the platform for implementing the robotic process automation (RPA) can be triggered to automatically obtain the information extraction template corresponding to the target artificial intelligence (AI) module from the preset artificial intelligence (AI) platform.

[0065] Before displaying the editing guide interface for implementing the robotic process automation (RPA), first configuration information for connecting to the artificial intelligence (AI) platform may also be obtained; and second configuration information for configuring the platform for implementing the robotic process automation (RPA) may be configured based on the first configuration information.

[0066] That is to say, the first configuration information of the artificial intelligence AI platform is directly used to configure the second configuration information of the platform for implementing robotic process automation RPA, so that after the configuration, the artificial intelligence AI platform and the platform for implementing robotic process automation RPA maintain data connectivity, and support automatic acquisition of information extraction templates corresponding to the target artificial intelligence AI module from the artificial intelligence AI platform.

[0067] The above-mentioned information extraction template corresponding to the target artificial intelligence AI module can be pre-configured in the artificial intelligence AI platform, and there is no restriction on this.

[0068] The information extraction template may carry some information extraction rules, and when the text is processed based on the information extraction rules, corresponding information can be extracted from the text.

[0069] Optionally, in some embodiments, obtaining an information extraction template corresponding to a target artificial intelligence AI module from an artificial intelligence AI platform may be obtaining an initial information extraction template corresponding to a target artificial intelligence AI module from an artificial intelligence AI platform, wherein the initial information extraction template includes: a plurality of candidate fields; determining at least one target field from the plurality of candidate fields in response to a second selection instruction; and forming a corresponding information extraction template based on the initial information extraction template and the at least one target field.

[0070] Therefore, by directly obtaining the initial information extraction template corresponding to the target artificial intelligence AI module from the artificial intelligence AI platform, the development of code programs when implementing robotic process automation RPA can be effectively avoided, the reusability of templates in the artificial intelligence AI platform can be improved, and the efficiency of implementing robotic process automation RPA can be improved. In addition, the initial information extraction template also includes: multiple candidate fields, supporting response to a second selection instruction, determining at least one target field from multiple candidate fields, and forming a corresponding information extraction template based on the initial information extraction template and at least one target field. This not only improves the reusability of templates in the artificial intelligence AI platform and improves the efficiency of implementing robotic process automation RPA, but also can make corresponding adjustments and updates to the information extraction template according to the actual usage requirements of robotic process automation RPA, enriching the application functions of the platform for implementing robotic process automation RPA and improving the development experience of developers.

[0071] Optionally, in some embodiments, after determining at least one target field from multiple candidate fields in response to the second selection instruction, the attributes of the target field can also be configured in response to a configuration instruction for the attributes of the target field, which can effectively enrich the information extraction function and effectively expand the application scenarios of the information extraction method combining RPA and AI.

[0072] The above-mentioned attributes of the target field are normalized attributes, or may be any other possible attributes, such as the format of displaying the target field, etc.

[0073] like Figure 4 As shown, Figure 4 Schematic diagram of the initial information extraction template in the embodiment of the present application, the initial information extraction template includes: multiple candidate fields (for example, name, method, increase / decrease, number of shares), and the developer can select some fields from the multiple candidate fields as target fields according to needs (for example, select by checking, Figure 4 The target field in may include various candidate fields at the same time), and then, the normalization attribute corresponding to the target field is configured.

[0074] For example, you can choose to configure the initial information extraction template and target field on the platform that implements robotic process automation (RPA), select the initial information extraction template "Announcement Extraction" ("Announcement Extraction" can be the name of the information extraction template configured in the artificial intelligence (AI) platform), select all candidate fields (candidate fields under the template "Announcement Extraction" configured on the artificial intelligence (AI) platform), and set the attributes of the target field as normalized attributes (when the attributes of the target field are configured as normalized attributes, the normalized explanation is: for example, values ​​such as "potatoes", "potatoes", "sweet potatoes", and "potatoes" can all be called "potatoes".

[0075] Optionally, in some embodiments, after obtaining an information extraction template corresponding to a target artificial intelligence AI module from an artificial intelligence AI platform, a visual structure code corresponding to the executable program code of the information extraction template can also be generated; and the visual structure code is displayed, wherein when the executable program code is run, information corresponding to the target field and its attributes can be extracted from the target text based on the information extraction template.

[0076] like Figure 5 As shown, Figure 5 This is a diagram of the visual structure code in the embodiment of the present application. That is to say, after obtaining the information extraction template corresponding to the target artificial intelligence AI module, a visual structure code can be generated in the visual view. In the visual view, the order and inclusion relationship of all commands are displayed in the form of stacked blocks, and some details are appropriately hidden, which is easier to understand. The "visual view" reflects the important feature of the "simplicity" of the platform for implementing robotic process automation RPA. The visual structure code is displayed based on the visual view, which can effectively reduce the learning threshold for developers to adopt the visual structure code and improve the application scope of the platform for implementing robotic process automation RPA.

[0077] S104: Extracting information from the target text according to the information extraction template.

[0078] In the embodiment of the present application, when generating Figure 5 After reading the visual structure code in the figure above (the visual structure code in the figure above can be read from top to bottom to understand its operation logic), it can be run directly. The running engine will automatically extract the results from top to bottom according to the template condition loop according to the command instructions, and assign them to the "Result" variable (an abstract concept in computer language that can store calculation results or represent values). Developers can insert other operation commands under the command block of "Get the result in the block..." to output the result of the Result variable or use it for other development. For example, write the "Result" results of the name, method, increase / decrease, and number of shares into Excel cells in sequence, so that the intelligent robot process of extracting the information of the unstructured target text into a structured table can be completed through simple operations and drag-and-drop selection without writing any code.

[0079] In this embodiment, an editing guidance interface for implementing Robotic Process Automation (RPA) is displayed, and the editing guidance interface includes: multiple candidate artificial intelligence (AI) modules, in response to a first selection instruction, determining a target artificial intelligence (AI) module selected by the selection instruction from among the multiple candidate artificial intelligence (AI) modules, obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, and extracting information from the target text according to the information extraction template. When using artificial intelligence (AI) capabilities to design Robotic Process Automation (RPA), the efficiency and intelligence of code development and design can be effectively improved, thereby assisting in improving the efficiency and effect of information extraction based on Robotic Process Automation (RPA).

[0080] Figure 6 It is a flowchart of an information extraction method combining RPA and AI proposed in another embodiment of the present application.

[0081] See also Figure 6 , the method comprising:

[0082] S601: Displaying a process editing interface for implementing Robotic Process Automation (RPA), where the process editing interface includes: at least one process block component.

[0083] like Figure 7 As shown, Figure 7 This is a schematic diagram of the creation interface of the process engineering in the embodiment of the present application. It can support the platform of robotic process automation (RPA) through account login of the artificial intelligence (AI) platform, and support the creation of a new process engineering. For example, the process engineering can be named: Extract structured data.

[0084] S602: In response to a second operation instruction on the process block component, display a process block editing view, where the process block editing view includes: a functional control for implementing robotic process automation (RPA).

[0085] like Figure 8 As shown, Figure 8 This is a schematic diagram of the process editing interface in the embodiment of the present application. The process editing interface includes: at least one process block component 81. When a developer operates a process block component 81, the operation instruction can be called a second operation instruction. For example, the developer clicks the edit icon in the upper right corner of the process block component 81, and the process block editing view is displayed. The process block editing view includes: functional controls for implementing robotic process automation RPA, for example, the Mage AI icon (Mage is a product that implements robotic process automation RPA, and there is no restriction on this).

[0086] S603: In response to the third operation instruction on the function control, jump from the display process editing interface to the display editing guide interface.

[0087] The above-mentioned process block editing view is displayed in response to the second operation instruction of the process block component, and the process block editing view includes: after implementing the functional control (Mage AI icon) of robotic process automation RPA, when it is detected that the developer triggers the Mage AI icon (the trigger instruction can be called the third operation instruction), it can jump from the display process editing interface to the display editing guide interface.

[0088] In this embodiment, a process editing interface for implementing robotic process automation (RPA) is displayed, the process editing interface includes: at least one process block component, and in response to a second operation instruction on the process block component, a process block editing view is displayed, the process block editing view includes: a functional control for implementing robotic process automation (RPA), and in response to a third operation instruction on the functional control, jumping from the displayed process editing interface to the displayed editing guide interface, the editing guide interface includes: multiple candidate artificial intelligence (AI) modules, in response to a first selection instruction, determining a target artificial intelligence (AI) module selected by the selection instruction from multiple candidate artificial intelligence (AI) modules, obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, and extracting information from the target text according to the information extraction template, which can realize low-code or even zero-code development of the automated development process of robotic process automation (RPA) combined with artificial intelligence (AI), simplify the development difficulty of robotic process automation (RPA) combined with artificial intelligence (AI), thereby effectively improving the efficiency and intelligence of code development and design, thereby assisting in improving the efficiency and effect of information extraction based on robotic process automation (RPA).

[0089] Fig. 9 It is a structural diagram of an information extraction device combining RPA and AI proposed in one embodiment of the present application.

[0090] like Fig. 9 As shown, the information extraction device 90 combining RPA and AI includes:

[0091] The first display module 901 is used to display an editing guide interface for implementing the robotic process automation RPA, where the editing guide interface includes: a plurality of candidate artificial intelligence AI modules;

[0092] A determination module 902, configured to determine, in response to a first selection instruction, a target artificial intelligence AI module selected by the selection instruction from a plurality of candidate artificial intelligence AI modules;

[0093] An acquisition module 903 is used to acquire an information extraction template corresponding to a target artificial intelligence AI module from an artificial intelligence AI platform;

[0094] The extraction module 904 is used to extract information from the target text according to the information extraction template.

[0095] In some embodiments of the present application, the editing guide interface further includes: a text configuration control, wherein:

[0096] The first display module 901 is further used to display a text editing area in the editing guide interface in response to a first operation instruction on the text configuration control;

[0097] The acquisition module 903 is further configured to respond to an editing instruction on the text editing area and use the text edited by the editing instruction as the target text.

[0098] In some embodiments of the present application, the acquisition module 903 is specifically used to:

[0099] Obtaining an initial information extraction template corresponding to a target artificial intelligence (AI) module from an artificial intelligence (AI) platform, wherein the initial information extraction template includes: a plurality of candidate fields;

[0100] In response to a second selection instruction, determining at least one target field from a plurality of candidate fields;

[0101] A corresponding information extraction template is formed according to the initial information extraction template and at least one target field.

[0102] In some embodiments of the present application, the acquisition module 903 is specifically used to:

[0103] In response to the configuration instruction for the attribute of the target field, the attribute of the target field is configured.

[0104] In some embodiments of the present application, the attribute of the target field is a normalized attribute.

[0105] In some embodiments of the present application, Fig.10 As shown, it also includes:

[0106] The second display module 905 is used to display a process editing interface for implementing the robotic process automation (RPA), the process editing interface including: at least one process block component, and in response to a second operation instruction on the process block component, display a process block editing view, the process block editing view including: a functional control for implementing the robotic process automation (RPA);

[0107] The first display module 901 is specifically used for:

[0108] In response to the third operation instruction on the function control, the display process editing interface jumps to the display editing guide interface.

[0109] In some embodiments of the present application, Fig.10 As shown, it also includes:

[0110] A generating module 906, used to generate a visual structure code corresponding to the executable program code of the information extraction template;

[0111] The third display module 907 is used to display the visual structure code, wherein when the executable program code is run, information corresponding to the target field and its attributes can be extracted from the target text based on the information extraction template.

[0112] In some embodiments of the present application, Fig.10 As shown, it also includes:

[0113] The configuration module 908 is used to obtain first configuration information for connecting to the artificial intelligence AI platform, and configure second configuration information of the platform for implementing the robotic process automation RPA according to the first configuration information.

[0114] It should be noted that the above Figure 1-Figure 8 The explanation of the information extraction method combining RPA and AI in the embodiment is also applicable to the information extraction device 90 combining RPA and AI in this embodiment. The implementation principle is similar and will not be repeated here.

[0115] In this embodiment, an editing guidance interface for implementing Robotic Process Automation (RPA) is displayed, and the editing guidance interface includes: multiple candidate artificial intelligence (AI) modules, in response to a first selection instruction, determining a target artificial intelligence (AI) module selected by the selection instruction from among the multiple candidate artificial intelligence (AI) modules, obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, and extracting information from the target text according to the information extraction template. When using artificial intelligence (AI) capabilities to design Robotic Process Automation (RPA), the efficiency and intelligence of code development and design can be effectively improved, thereby assisting in improving the efficiency and effect of information extraction based on Robotic Process Automation (RPA).

[0116] Fig.11 It is a schematic diagram of the structure of an electronic device proposed in one embodiment of the present application.

[0117] The electronic device may be a mobile phone, a tablet computer, etc.

[0118] See also Fig.11The electronic device 110 of this embodiment includes: a housing 1101, a processor 1102, a memory 1103, a circuit board 1104, and a power circuit 1105. The circuit board 1104 is arranged inside the space surrounded by the housing 1101, and the processor 1102 and the memory 1103 are arranged on the circuit board 1104; the power circuit 1105 is used to supply power to various circuits or devices of the electronic device 110; the memory 1103 is used to store executable program codes; wherein the processor 1102 runs a program corresponding to the executable program code by reading the executable program code stored in the memory 1103, so as to execute:

[0119] Displaying an editing guide interface for implementing Robotic Process Automation (RPA), the editing guide interface includes: multiple candidate artificial intelligence (AI) modules;

[0120] In response to the first selection instruction, determining a target artificial intelligence AI module selected by the selection instruction from a plurality of candidate artificial intelligence AI modules;

[0121] Obtaining an information extraction template corresponding to a target artificial intelligence (AI) module from an artificial intelligence (AI) platform; and

[0122] Extract information from the target text according to the information extraction template.

[0123] It should be noted that the above Figure 1-Figure 8 The explanation of the information extraction method combining RPA and AI in the embodiment is also applicable to the electronic device 110 of this embodiment. The implementation principle is similar and will not be repeated here.

[0124] The electronic device in this embodiment realizes the editing guidance interface of the Robotic Process Automation (RPA) by displaying, and the editing guidance interface includes: multiple candidate artificial intelligence (AI) modules, in response to a first selection instruction, determining the target artificial intelligence (AI) module selected by the selection instruction from the multiple candidate artificial intelligence (AI) modules, obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, and extracting information from the target text according to the information extraction template. When using artificial intelligence (AI) capabilities to design Robotic Process Automation (RPA), it can effectively improve the efficiency and intelligence of code development and design, thereby assisting in improving the efficiency and effect of information extraction based on Robotic Process Automation (RPA).

[0125] In order to implement the above embodiment, the present application also proposes a non-transitory computer-readable storage medium. When the instructions in the storage medium are executed by the processor of the terminal, the terminal is enabled to execute an information extraction method combining RPA and AI, the method comprising:

[0126] Displaying an editing guide interface for implementing Robotic Process Automation (RPA), the editing guide interface includes: multiple candidate artificial intelligence (AI) modules;

[0127] In response to the first selection instruction, determining a target artificial intelligence AI module selected by the selection instruction from a plurality of candidate artificial intelligence AI modules;

[0128] Obtaining an information extraction template corresponding to a target artificial intelligence (AI) module from an artificial intelligence (AI) platform; and

[0129] Extract information from the target text according to the information extraction template.

[0130] The non-temporary computer-readable storage medium in this embodiment realizes the editing guidance interface of the robotic process automation (RPA) by displaying, and the editing guidance interface includes: multiple candidate artificial intelligence (AI) modules, in response to a first selection instruction, determining the target artificial intelligence (AI) module selected by the selection instruction from the multiple candidate artificial intelligence (AI) modules, obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, and extracting information from the target text according to the information extraction template. When using artificial intelligence (AI) capabilities to design the robotic process automation (RPA), it can effectively improve the efficiency and intelligence of code development and design, thereby assisting in improving the efficiency and effect of information extraction based on the robotic process automation (RPA).

[0131] It should be noted that, in the description of this application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0132] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0133] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0134] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0135] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0136] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0137] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0138] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An information extraction method combining RPA and AI, characterized in that: Applied to Natural Language Processing (NLP), the method comprises: Displaying an editing guide interface for implementing Robotic Process Automation (RPA), wherein the editing guide interface includes: a plurality of candidate artificial intelligence (AI) modules, and the editing guide interface is used to guide developers to select the artificial intelligence (AI) module required; In response to a first selection instruction, determining a target artificial intelligence AI module selected by the selection instruction from among the plurality of candidate artificial intelligence AI modules; Acquire an information extraction template corresponding to the target artificial intelligence (AI) module from an artificial intelligence (AI) platform; and Extracting information from the target text according to the information extraction template; Before the display of the editing guide interface for implementing the Robotic Process Automation (RPA), it also includes: Displaying a process editing interface for implementing Robotic Process Automation (RPA), wherein the process editing interface includes: at least one process block component; In response to a second operation instruction on the process block component, displaying a process block editing view, the process block editing view including: a functional control for implementing robotic process automation (RPA); The display of the editing guide interface for implementing the Robotic Process Automation (RPA) includes: In response to a third operation instruction on the function control, the display jumps from the process editing interface to the editing guide interface.

2. The method according to claim 1, characterized in that The editing guide interface further includes: a text configuration control, after determining the target artificial intelligence AI module selected by the selection instruction from the plurality of candidate artificial intelligence AI modules, further including: In response to a first operation instruction on the text configuration control, displaying a text editing area in the editing guide interface; In response to an editing instruction for the text editing area, the text edited by the editing instruction is used as the target text.

3. The method according to claim 1, characterized in that The step of obtaining an information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform includes: Acquire an initial information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, wherein the initial information extraction template includes: a plurality of candidate fields; In response to a second selection instruction, determining at least one target field from the plurality of candidate fields; The corresponding information extraction template is formed according to the initial information extraction template and the at least one target field.

4. The method according to claim 3, characterized in that After determining at least one target field from the plurality of candidate fields in response to the second selection instruction, the method further includes: In response to the configuration instruction for the attribute of the target field, the attribute of the target field is configured.

5. The method according to claim 4, characterized in that The attributes of the target field are normalized attributes.

6. The method according to claim 3, characterized in that After obtaining the information extraction template corresponding to the target artificial intelligence AI module from the artificial intelligence AI platform, the method further includes: Generating a visual structure code corresponding to the executable program code of the information extraction template; The visual structure code is displayed, wherein when the executable program code is run, information corresponding to the target field and its attributes can be extracted from the target text based on the information extraction template.

7. The method according to claim 1, characterized in that Before the display of the editing guide interface for implementing the robotic process automation (RPA), it also includes: Obtain the first configuration information for connecting to the artificial intelligence AI platform; According to the first configuration information, second configuration information of a platform for implementing robotic process automation (RPA) is configured.

8. An information extraction device combining RPA and AI, characterized in that: Applied to Natural Language Processing (NLP), the device comprises: A first display module is used to display an editing guide interface for implementing Robotic Process Automation (RPA), wherein the editing guide interface includes: a plurality of candidate artificial intelligence (AI) modules, and the editing guide interface is used to guide developers to select the artificial intelligence (AI) module required; a determination module, configured to determine, in response to a first selection instruction, a target artificial intelligence AI module selected by the selection instruction from among the plurality of candidate artificial intelligence AI modules; an acquisition module, used to acquire an information extraction template corresponding to the target artificial intelligence AI module from an artificial intelligence AI platform; and An extraction module, used to extract information from the target text according to the information extraction template; The device further comprises: A second display module is used to display a process editing interface for implementing the robotic process automation (RPA), wherein the process editing interface includes: at least one process block component, and in response to a second operation instruction on the process block component, display a process block editing view, wherein the process block editing view includes: a function control for implementing the robotic process automation (RPA); The first display module is specifically used for: In response to a third operation instruction on the function control, the display jumps from the process editing interface to the editing guide interface.

9. The device according to claim 8, characterized in that The editing guide interface also includes: a text configuration control, wherein: The first display module is further configured to display a text editing area in the editing guide interface in response to a first operation instruction on the text configuration control; The acquisition module is further configured to respond to an editing instruction for the text editing area and use the text edited by the editing instruction as the target text.

10. The device according to claim 8, characterized in that The acquisition module is specifically used for: Acquire an initial information extraction template corresponding to the target artificial intelligence (AI) module from the artificial intelligence (AI) platform, wherein the initial information extraction template includes: a plurality of candidate fields; In response to a second selection instruction, determining at least one target field from the plurality of candidate fields; The corresponding information extraction template is formed according to the initial information extraction template and the at least one target field.

11. The device according to claim 10, characterized in that The acquisition module is specifically used for: In response to the configuration instruction for the attribute of the target field, the attribute of the target field is configured.

12. The device according to claim 11, characterized in that The attributes of the target field are normalized attributes.

13. The device according to claim 10, characterized in that Also includes: A generating module, used for generating a visual structure code corresponding to the executable program code of the information extraction template; The third display module is used to display the visual structure code, wherein when the executable program code is run, information corresponding to the target field and its attributes can be extracted from the target text based on the information extraction template.

14. The device according to claim 8, characterized in that Also includes: The configuration module is used to obtain first configuration information for connecting to an artificial intelligence (AI) platform, and configure second configuration information of a platform for implementing robotic process automation (RPA) based on the first configuration information.

15. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the information extraction method combining RPA and AI as described in any one of claims 1 to 7 is implemented.

16. An electronic device comprising a housing, a processor, a memory, a circuit board and a power supply circuit, wherein: The circuit board is placed inside the space enclosed by the housing, and the processor and the memory are arranged on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the electronic device; and the memory is used to store executable program codes; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the information extraction method combining RPA and AI as described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Interface display method and related product

    CN107291328A

  • Text extraction method and device

    CN109739416A

  • Electronic medical record data mining method and device, equipment and a medium

    CN111199802A

  • Template generation method and device for artificial intelligence AI solution and storage medium

    CN111639859A

  • Information extraction method and device combining RPA and AI, equipment and medium

    CN111881664A