Power grid robot process automatic construction method and system based on RPA + AI

Abstract

The invention discloses a power grid robot process automation construction method and system based on RPA + AI, and relates to the technical field of electric power automation and artificial intelligence, and the method comprises the steps: capturing to-be-acquired non-standardized scene data; identifying a data type based on a pre-constructed power grid text data detection rule by using an OCR file detection technology, and determining a service mode; analyzing the grabbed non-standardized scene data and the determined business mode by using a decision tree model, and determining specific operation steps of an automatic process; a man-machine interaction mechanism is applied, and at the same time, an RPA background collects state information of task execution and feedback opinions of a user to form closed-loop feedback, and decision optimization is carried out; according to the invention, the ability of power grid business to cope with non-standardized scenes is significantly improved, the stability of the power grid business process is improved, a man-machine interaction mechanism is established, secondary verification of data is realized, and the accuracy and interaction ability of the power grid business process are improved.

Description

Technical Field

[0001] The present invention relates to the field of power automation and artificial intelligence technology, and in particular to a method and system for constructing power grid robot process automation based on RPA+AI. Background Art

[0002] As the scale of power grids continues to expand and the business becomes increasingly complex, power grid companies need to process a large amount of data and information, including equipment status monitoring, fault diagnosis, load forecasting, power dispatching, etc. These data processing tasks are usually repetitive and standardized, but manual processing is not only inefficient but also prone to errors. Therefore, power grid companies are in urgent need of a method that can automatically process this data to improve work efficiency and accuracy.

[0003] The existing power grid process automation system has problems such as low system stability, low data accuracy, low degree of autonomy, and poor interactivity: Low system stability: This method involves information interaction between multiple systems (distribution automation system, control cloud system, etc.). The actual business scenarios are complex, with a large amount of non-standardized data and complex operation steps. The application of traditional robotic process automation (Robotic process : Traditional RPA lacks a data verification mechanism and has the following risks: data collection errors lead to errors in the source of business system data; when multiple systems interact with each other, the sent data is lost or the data is wrong; when processing data, the existence of non-standard scenarios leads to abnormal data processing; some key data requires manual review and confirmation, but the existing RPA technology cannot realize manual verification during process execution, and data parsing anomalies cause system operation risks; low degree of autonomy and insufficient efficiency: traditional RPA can only perform fixed operations according to the set steps or time, and cannot realize monitoring autonomy. The process handling is too rigid and the handling efficiency is low; lack of interaction and poor controllability: lack of human-computer interaction mechanism, unable to manually supplement the data that RPA cannot automatically obtain, and lack of information perception and status control of the RPA task execution process. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to improve the stability, data accuracy, degree of autonomy and interactivity of the power grid robotic process automation system to meet the needs of non-standardized scenarios, high accuracy and dynamic response in power grid dispatching.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for constructing a power grid robot process automation based on RPA+AI, including:

[0008] The non-standardized scene data to be acquired are captured by using two methods: web page data capture and file data capture;

[0009] Based on the captured non-standardized scenario data, OCR file detection technology is used to identify data types based on pre-built power grid text data detection rules to determine business models;

[0010] Use the decision tree model to analyze the captured non-standardized scenario data and the determined business model, and determine the specific operation steps of the automation process based on the analysis results;

[0011] The human-computer interaction mechanism is applied based on the specific operating steps of the automated process, and active interaction is carried out in the steps that require manual data supplementation or manual data verification. At the same time, the RPA background collects task execution status information and user feedback to form a closed-loop feedback and optimize decision-making.

[0012] As a preferred solution for the construction method of power grid robotic process automation based on RPA+AI, it includes:

[0013] The web page data crawling includes:

[0014] Determine the pages that need to be accessed and the target elements to be captured in the power grid business scenario;

[0015] Use the RPA robot to issue an access request based on the target page to obtain the HTML document of the target page;

[0016] Load the acquired HTML document and perform web page style parsing to obtain the element nodes and style information of the target page, and calculate the position and size of the element to be acquired or operated;

[0017] Based on the calculated element position and size information, the RPA robot locates the element by calling the browser plug-in and grabs the located target element.

[0018] As a preferred solution for the construction method of power grid robotic process automation based on RPA+AI, it includes:

[0019] The file data capture includes:

[0020] Identify the file type of power grid business files;

[0021] Different tool libraries are called to extract the file data content according to the identified file type.

[0022] As a preferred solution for the construction method of power grid robotic process automation based on RPA+AI, it includes:

[0023] The method of using OCR file detection technology to identify data types based on pre-built power grid text data detection rules includes:

[0024] Obtain the image text file of the power grid business executed by RPA;

[0025] Applying OCR recognition technology to decode and extract characters from the image text file;

[0026] Based on the decoded file content and extracted character sequences, a language model is applied for text recognition;

[0027] Data extraction is performed on the identified content.

[0028] As a preferred solution for the construction method of power grid robotic process automation based on RPA+AI, it includes:

[0029] The method of using OCR file detection technology to identify data types based on pre-built power grid text data detection rules also includes:

[0030] Collect grid business text data, including grid specification documents, grid rules and regulations, and grid business data;

[0031] According to the actual power grid business application scenarios, some texts containing interference information, sensitive information, and key information features are artificially generated to form a text data set for algorithm training;

[0032] Preprocess the text data set to remove noise from the text and convert the text data into a unified format;

[0033] According to the specific needs of power grid business, the preprocessed text data set is divided into different categories and classification features are extracted;

[0034] Manually or semi-automatically annotate the extracted classification features to distinguish normal text from text containing bad, sensitive or critical information, and label them accordingly;

[0035] Build a text detection model based on the extracted features and labels;

[0036] Based on the text detection model, key discrimination rules or feature combinations are extracted to form a specific rule set for interference information filtering, sensitive information detection and key information extraction;

[0037] Integrate the rule set into the RPA system to detect newly generated text data in real time; at the same time, continuously monitor the performance of the system and adjust the rules or retrain the text detection model according to actual conditions.

[0038] As a preferred solution for the construction method of power grid robotic process automation based on RPA+AI, it includes:

[0039] The decision tree model is used to analyze the captured non-standardized scenario data and the determined business model, and the specific operation steps of the automation process are determined according to the analysis results, including:

[0040] Based on the captured non-standardized scenario data and determined business models, the repetitive tasks and data processing requirements in the power grid business are analyzed to build a decision tree model;

[0041] Based on the decision tree model, perform anomaly detection or fault prediction on the RPA execution status;

[0042] The data interaction channel is used to interact the business data and status information of the actual execution process of the RPA robot with the result information predicted and detected by the decision tree model, and the prediction mechanism of the decision tree model and the data processing mechanism of the RPA robot are coordinated;

[0043] Analyze the actual application problems of RPA based on the actual business execution, collect user feedback through the RPA robot background, and optimize the operation process and decision-making of the RPA robot based on the problems in the actual business process.

[0044] As a preferred solution for the construction method of power grid robotic process automation based on RPA+AI, it includes:

[0045] The specific operation steps based on the automation process using the human-computer interaction mechanism include:

[0046] Perceive the contextual information during the execution of the RPA robot;

[0047] Based on the context information, obtaining execution content of previous and subsequent operation steps;

[0048] Interactively judge the content to determine whether manual operation is required;

[0049] If interaction with the user is required, the RPA robot will automatically pop up a window or issue a voice prompt;

[0050] Add secondary judgment for special data types. If special data or security information is detected, the RPA robot will pop up a prompt window again, requiring the dispatcher to confirm the information for the second time.

[0051] In a second aspect, an embodiment of the present invention provides a power grid robot process automation construction system based on RPA+AI, including:

[0052] The data capture module is used to capture the non-standardized scene data to be acquired by using two methods: web page data capture and file data capture;

[0053] The detection and recognition module is used to identify data types and determine business models based on the captured non-standardized scene data and the pre-built power grid text data detection rules using OCR file detection technology;

[0054] The process establishment module is used to analyze the captured non-standardized scenario data and the determined business model using the decision tree model, and determine the specific operation steps of the automation process based on the analysis results;

[0055] The human-computer interaction module is used to apply the human-computer interaction mechanism based on the specific operation steps of the automated process, and actively interact in steps that require manual data supplementation or manual data verification. At the same time, the RPA background collects task execution status information and user feedback to form a closed-loop feedback and optimize decision-making.

[0056] In a third aspect, an embodiment of the present invention provides a computing device, including:

[0057] Memory and processor;

[0058] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the one or more programs are executed by the one or more processors, the one or more processors implement the RPA+AI-based power grid robotic process automation construction method as described in any embodiment of the present invention.

[0059] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the RPA+AI-based power grid robotic process automation construction method.

[0060] Beneficial effects of the present invention: The present invention realizes pattern recognition of business scenarios by introducing AI technology, customizes rules according to scenarios and automatically executes process tasks, assists dispatchers to complete daily tedious work, reduces the workload of dispatchers, improves work efficiency, solves the problem of complex power grid application scenarios and strong limitations of traditional RPA, and improves the stability of power grid operation; adopts machine learning algorithms to establish RPA robot adaptive learning models, adds feedback data according to the actual needs and feedback of power grid regulation, forms closed-loop feedback, and realizes RPA self-learning and decision optimization. And uses OCR recognition technology to identify data types, confirm business models, and select the optimal operation process through decision models, thereby optimizing process execution efficiency; applies the controller and actuator mechanism of intelligent robots, solves key data supplementation, data secondary verification, execution authority confirmation and other problems through human-computer active interaction during execution, and improves the interactivity of the system and the accuracy of data; develops a real-time event perception mechanism to monitor the process execution status in real time, identify the key moments that require dispatcher intervention, ensure that dispatchers can respond in time, and achieve efficient decision-making and operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0062] Figure 1 It is an overall flow chart of the method for constructing power grid robot process automation based on RPA+AI described in the first embodiment of the present invention;

[0063] Figure 2 It is a flowchart of constructing text detection rules of the method for constructing power grid robot process automation based on RPA+AI described in the first embodiment of the present invention;

[0064] Figure 3 It is a schematic diagram of the anomaly detection process of the RPA+AI-based power grid robot process automation construction method described in the first embodiment of the present invention;

[0065] Figure 4 It is a schematic diagram of the human-computer interaction process of the power grid robot process automation construction method based on RPA+AI described in the first embodiment of the present invention;

[0066] Figure 5 It is a schematic diagram of the background customization operation process in the simulation example of the power grid robot process automation construction method based on RPA+AI described in the second embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0068] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0069] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0070] Example 1

[0071] Reference Figure 1-Figure 4 , which is the first embodiment of the present invention, and provides a method for constructing a power grid robot process automation based on RPA+AI, including:

[0072] S1: Use web page data crawling and file data crawling to crawl the non-standardized scene data to be acquired;

[0073] Specifically, common non-standardized data include: chart data generated through web pages (line charts, bar charts, real-time comparison charts, etc.), on-site power grid equipment image data, nameplate images of power equipment, equipment monitoring information under multiple systems, specified data in power grid data texts, and other business data under unconventional conditions.

[0074] In the embodiment of the present application, web page data crawling includes:

[0075] Determine the page that needs to be accessed and the target element to be captured in the power grid business scenario. The RPA robot sends a request to the target page through the browser to obtain a response, thereby obtaining the HTML document of the access page; the RPA robot parses the obtained HTML document, loads and parses the web page style, obtains the node and style information of the target page element, and calculates the position and size of the element to be obtained or operated; through the web page style information, locates the page position where the target data is located, identifies and confirms the text data to be captured, locates the element position on the web page, and completes data capture by calling the browser plug-in.

[0076] For example, to determine the page that needs to be accessed for the power grid business scenario and the target element to be captured, the page that needs to be accessed is the Fujian Intelligent Control Cloud Platform (dcloud.fj.sgcc.com.cn) and the target data - daily electricity consumption of provincial and municipal coal-fired installed capacity levels - is captured. The RPA robot sends a request to the target page through the browser to obtain a response, thereby obtaining the HTML document of the Fujian Intelligent Control Cloud Platform.

[0077] The RPA robot parses the HTML document obtained from the Fujian Intelligent Control Cloud Platform, loads and parses the CSS style of the web page, obtains the node and style information of the target page element, and calculates the position and size of the element to be obtained or operated.

[0078] The target data is located on the page through the CSS style information of the web page, and then the text data to be captured is confirmed through OCR recognition, and the element position on the web page is located. Finally, the RPA robot completes data capture by calling the browser plug-in.

[0079] In the embodiment of the present application, file data capture includes:

[0080] Identify file types through RPA robots; call different tool libraries to assist in data extraction based on file types;

[0081] Specifically, for Excel or Word files, Apache POI tool class or OpenXML tool class is introduced; for PDF files, tool libraries such as PDFBox and iText are introduced; for non-text forms such as pictures, OCR recognition technology is used.

[0082] For example, it is necessary to filter the downloaded power generation plan document to obtain pumped storage type units and sum the data from 0:15 to 0:00 the next day. At this time, the RPA robot determines that the file type is an Excel file, calls the tool class, obtains the data in the Excel file, filters and sums the target data, and exports the summed data to generate a new document.

[0083] S2: Based on the captured non-standardized scenario data, the OCR file detection technology is used to identify the data type based on the pre-built power grid text data detection rules to determine the business model;

[0084] In an embodiment of the present application, identifying the data type based on the pre-constructed power grid text data detection rule includes:

[0085] Obtain the image text file of the power grid business executed by RPA;

[0086] Applying OCR recognition technology to decode and extract characters from the image text file;

[0087] Based on the decoded file content and extracted character sequences, a language model is applied for text recognition;

[0088] Data extraction is performed on the identified content.

[0089] Collect grid business text data, including grid specification documents, grid rules and regulations, and grid business data;

[0090] According to the actual power grid business application scenarios, some texts containing interference information, sensitive information, and key information features are artificially generated to form a text data set for algorithm training;

[0091] Preprocess the text data set to remove noise from the text and convert the text data into a unified format;

[0092] According to the specific needs of power grid business, the preprocessed text data set is divided into different categories and classification features are extracted;

[0093] Manually or semi-automatically annotate the extracted classification features to distinguish normal text from text containing bad, sensitive or critical information, and label them accordingly;

[0094] Build a text detection model based on the extracted features and labels;

[0095] Based on the text detection model, key discrimination rules or feature combinations are extracted to form a specific rule set for interference information filtering, sensitive information detection and key information extraction;

[0096] Integrate the rule set into the RPA system to detect newly generated text data in real time; at the same time, continuously monitor the performance of the system and adjust the rules or retrain the text detection model according to actual conditions.

[0097] For example, the collection of power grid business text data mainly includes power grid specification documents (such as safety operation manuals, maintenance guidelines, technical standards, etc.) and power grid rules and regulations (laws and regulations, company internal policies, etc.) and power grid business data (daily reports, weekly reports, accident plans, etc.);

[0098] According to the actual power grid business application scenarios, some texts containing interference information, sensitive information (requiring manual inspection or filling), key information and other features are artificially generated for algorithm training;

[0099] Preprocessing the text data set to remove noise in the text, such as extra spaces, non-text characters, repeated sentences or paragraphs, etc., and converting the text data into a unified format;

[0100] According to the specific needs of power grid business, the pre-processed text data is divided into different categories, such as technical documents, policy documents, safety guidelines, daily data, etc.;

[0101] Classification features are extracted from the preprocessed text data, such as keywords (wind power, hydropower, thermal power and other grid business-related words), phrases, sentence structures, and semantic features.

[0102] S3: Use the decision tree model to analyze the captured non-standardized scenario data and the determined business model, and determine the specific operation steps of the automation process based on the analysis results;

[0103] In the embodiment of the present application, based on the captured non-standardized scenario data and the determined business model, the repetitive tasks and data processing requirements in the power grid business are analyzed to build a decision tree model;

[0104] Based on the decision tree model, perform anomaly detection or fault prediction on the RPA execution status;

[0105] The data interaction channel is used to interact the business data and status information of the actual execution process of the RPA robot with the result information predicted and detected by the decision tree model, and the prediction mechanism of the decision tree model and the data processing mechanism of the RPA robot are coordinated;

[0106] Analyze the actual application problems of RPA based on the actual business execution, collect user feedback through the RPA robot background, and optimize the operation process and decision-making of the RPA robot based on the problems in the actual business process.

[0107] S4: Apply the human-computer interaction mechanism based on the specific operation steps of the automated process, and actively interact in the steps that require manual data supplementation or manual data verification. At the same time, the RPA background collects task execution status information and user feedback to form a closed-loop feedback and optimize decision-making.

[0108] In the embodiment of the present application, the specific operation steps based on the automation process using the human-computer interaction mechanism include:

[0109] Perceive the contextual information during the execution of the RPA robot;

[0110] Based on the context information, obtaining execution content of previous and subsequent operation steps;

[0111] Interactively judge the content to determine whether manual operation is required;

[0112] If interaction with the user is required, the RPA robot will automatically pop up a window or issue a voice prompt;

[0113] Add secondary judgment for special data types. If special data or security information is detected, the RPA robot will pop up a prompt window again, requiring the dispatcher to confirm the information for the second time.

[0114] The above is a schematic scheme of the RPA+AI-based power grid robot process automation construction method of this embodiment. It should be noted that the technical solution of the power grid robot process automation construction system based on RPA+AI and the technical solution of the power grid robot process automation construction method based on RPA+AI belong to the same concept. The details of the technical solution of the power grid robot process automation construction system based on RPA+AI in this embodiment that are not described in detail can be found in the description of the technical solution of the power grid robot process automation construction method based on RPA+AI.

[0115] In this embodiment, the power grid robot process automation construction system based on RPA+AI includes:

[0116] The data capture module is used to capture the non-standardized scene data to be acquired by using two methods: web page data capture and file data capture;

[0117] The detection and recognition module is used to identify data types and determine business models based on the captured non-standardized scene data and the pre-built power grid text data detection rules using OCR file detection technology;

[0118] The process establishment module is used to analyze the captured non-standardized scenario data and the determined business model using the decision tree model, and determine the specific operation steps of the automation process based on the analysis results;

[0119] The human-computer interaction module is used to apply the human-computer interaction mechanism based on the specific operation steps of the automated process, and actively interact in steps that require manual data supplementation or manual data verification. At the same time, the RPA background collects task execution status information and user feedback to form a closed-loop feedback and optimize decision-making.

[0120] This embodiment further provides a computing device, which is applicable to a method for constructing a power grid robot process automation based on RPA+AI, including:

[0121] Memory and processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the RPA+AI-based power grid robot process automation construction method proposed in the above embodiment.

[0122] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for constructing power grid robot process automation based on RPA+AI as proposed in the above embodiment is implemented.

[0123] The storage medium proposed in this embodiment and the RPA+AI-based power grid robot process automation construction method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0124] Example 2

[0125] Reference Figure 5 , which is an embodiment of the present invention, provides a method for constructing power grid robot process automation based on RPA+AI. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0126] Business goal: Generate the required information from the online emergency plan preparation function of the control cloud, and then use RPA to generate the corresponding list and input it into the Guobu Cloud joint fault plan preparation system.

[0127] Target page: Kokubu Cloud Disaster Plan Joint Preparation System

[0128] (http: / / faulthand.dcloud.gf.dc.sgcc.com.cn / pages / homePage / index.html#)

[0129] Target data: Fujian Province compiled major maintenance accident plan information for week XX of 202X.

[0130] Business steps:

[0131] 1. Kokubu Cloud Fault Plan Joint Compilation System;

[0132] 2. Click the New button, and the following pop-up window will pop up. Observe that the pop-up window contains various information;

[0133] 3. Select the correct plan and click the corresponding Excel table to obtain the plan information;

[0134] 4. In the new plan window, fill in the plan information;

[0135] 5. After filling in the form, click Ask the Dispatcher to Confirm (a pop-up window will appear). After the Dispatcher confirms that the form is correct;

[0136] 6. Automatically click to issue the compilation task.

[0137] Specific operation process:

[0138] (1) According to the above operation steps, the background sets the operation steps for the business scenario, such as Figure 5 As shown, it is the background customization operation process;

[0139] (2) Read the national emergency plan information;

[0140] (3) Read the risk analysis content of the risk warning sheet of the corresponding plan, fill in the content of the grid mode change (i.e. before XX trips) into the initial grid operation mode, and generate an Excel table.

[0141] (4) Open the RPA robot task interface and execute the task of uploading the national emergency plan.

[0142] (5) The RPA robot automatically logs into the Kokubu Cloud fault plan joint preparation system based on business processes.

[0143] (6) (First human-machine verification) After the RPA robot automatically completes the login, a prompt window pops up for the user to confirm the plan time. After the user confirms, the RPA machine automatically executes the subsequent plan selection process and calls the API interface provided by Kokubu Cloud to generate an Excel file containing the plan information.

[0144] (7) (Second human-machine verification) The RPA robot automatically opens the Excel file of emergency plan information and pops up a prompt window. After the user reviews the table information, he / she confirms the verification in the pop-up window. After the dispatcher completes the confirmation, the RPA robot extracts the emergency plan information in the Excel table and automatically fills it in.

[0145] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for constructing power grid robot process automation based on RPA+AI, characterized in that: include: Use web page data crawling and file data crawling to crawl the non-standardized scene data to be obtained; Based on the captured non-standardized scenario data, OCR file detection technology is used to identify data types based on pre-built power grid text data detection rules to determine business models; Use the decision tree model to analyze the captured non-standardized scenario data and the determined business model, and determine the specific operation steps of the automation process based on the analysis results; The human-computer interaction mechanism is applied based on the specific operating steps of the automated process, and active interaction is carried out in the steps that require manual data supplementation or manual data verification. At the same time, the RPA background collects task execution status information and user feedback to form a closed-loop feedback and optimize decision-making.

2. The method for constructing a power grid robot process automation based on RPA+AI according to claim 1, characterized in that: The web page data crawling includes: Determine the pages that need to be accessed and the target elements to be captured in the power grid business scenario; Use the RPA robot to issue an access request based on the target page to obtain the HTML document of the target page; Load the acquired HTML document and perform web page style parsing to obtain the element nodes and style information of the target page, and calculate the position and size of the element to be acquired or operated; Based on the calculated element position and size information, the RPA robot locates the element by calling the browser plug-in and grabs the located target element.

3. The method for constructing a power grid robot process automation based on RPA+AI as claimed in claim 2, characterized in that: The file data capture includes: Identify the file type of power grid business files; Different tool libraries are called to extract the file data content according to the identified file type.

4. The method for constructing a power grid robot process automation based on RPA+AI as claimed in claim 3, characterized in that: The method of using OCR file detection technology to identify data types based on pre-built power grid text data detection rules includes: Obtain the image text file of the power grid business executed by RPA; Applying OCR recognition technology to decode and extract characters from the image text file; Based on the decoded file content and extracted character sequences, a language model is applied for text recognition; Data extraction is performed on the identified content.

5. The method for constructing a power grid robot process automation based on RPA+AI as claimed in claim 4, characterized in that: The method of using OCR file detection technology to identify data types based on pre-built power grid text data detection rules also includes: Collect grid business text data, including grid specification documents, grid rules and regulations, and grid business data; According to the actual power grid business application scenarios, some texts containing interference information, sensitive information, and key information features are artificially generated to form a text data set for algorithm training; Preprocess the text data set to remove noise from the text and convert the text data into a unified format; According to the specific needs of power grid business, the preprocessed text data set is divided into different categories and classification features are extracted; Manually or semi-automatically annotate the extracted classification features to distinguish normal text from text containing bad, sensitive or critical information, and label them accordingly; Build a text detection model based on the extracted features and labels; Based on the text detection model, key discrimination rules or feature combinations are extracted to form a specific rule set for interference information filtering, sensitive information detection and key information extraction; Integrate the rule set into the RPA system to detect newly generated text data in real time; at the same time, continuously monitor the performance of the system and adjust the rules or retrain the text detection model according to actual conditions.

6. The method for constructing a power grid robot process automation based on RPA+AI as claimed in claim 5, characterized in that: The decision tree model is used to analyze the captured non-standardized scenario data and the determined business model, and the specific operation steps of the automation process are determined according to the analysis results, including: Based on the captured non-standardized scenario data and determined business models, the repetitive tasks and data processing requirements in the power grid business are analyzed to build a decision tree model; Based on the decision tree model, perform anomaly detection or fault prediction on the RPA execution status; The data interaction channel is used to interact the business data and status information of the actual execution process of the RPA robot with the result information predicted and detected by the decision tree model, and the prediction mechanism of the decision tree model and the data processing mechanism of the RPA robot are coordinated; Analyze the actual application problems of RPA based on the actual business execution, collect user feedback through the RPA robot background, and optimize the operation process and decision-making of the RPA robot based on the problems in the actual business process.

7. The method for constructing a power grid robot process automation based on RPA+AI as claimed in claim 6, characterized in that: The specific operation steps based on the automation process using the human-computer interaction mechanism include: Perceive the contextual information during the execution of the RPA robot; Based on the context information, obtaining execution content of previous and subsequent operation steps; Interactively judge the content to determine whether manual operation is required; If interaction with the user is required, the RPA robot will automatically pop up a window or issue a voice prompt; Add secondary judgment for special data types. If special data or security information is detected, the RPA robot will pop up a prompt window again, requiring the dispatcher to confirm the information for the second time.

8. A system using the RPA+AI-based power grid robot process automation construction method as described in any one of claims 1 to 7, characterized in that: include: The data capture module is used to capture the non-standardized scene data to be acquired by using two methods: web page data capture and file data capture; The detection and recognition module is used to identify data types and determine business models based on the captured non-standardized scene data and the pre-built power grid text data detection rules using OCR file detection technology; The process establishment module is used to analyze the captured non-standardized scenario data and the determined business model using the decision tree model, and determine the specific operation steps of the automation process based on the analysis results; The human-computer interaction module is used to apply the human-computer interaction mechanism based on the specific operation steps of the automated process, and actively interact in steps that require manual data supplementation or manual data verification. At the same time, the RPA background collects task execution status information and user feedback to form a closed-loop feedback and optimize decision-making.

9. A computing device comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the RPA+AI-based power grid robotic process automation construction method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for constructing a power grid robotic process automation based on RPA+AI as described in any one of claims 1 to 7.

Images