Method and device for processing electrical engineering data, computer device and storage medium

Abstract

The application relates to an electrical engineering data processing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring electrical engineering original data, wherein the electrical engineering original data comprises relevant parameters of electrical engineering components; processing the electrical engineering original data by using a data extraction model to obtain digitized data in the original data; and performing technical rule matching processing on the digitized data, and displaying the processed data. The data recognition efficiency of the electrical installation engineering related data can be improved.

Description

Technical Field

[0001] This application relates to the field of electrical installation engineering technology, and in particular to a method, apparatus, computer equipment, and storage medium for processing electrical engineering data. Background Technology

[0002] With the rapid development of science and technology, electrical engineering, which generates electrical and electronic systems, encompasses almost all engineering activities related to electronics and photonics. It is precisely the tremendous progress in electronic technology that has propelled the arrival of the information age based on computer networks, giving rise to a vast amount of digital information processing. In the field of electrical engineering, digital information processing includes data identification, data extraction, data conversion, and data loading of various data from electrical installation projects. Data identification involves extracting raw data from drawings and removing fault text. Data extraction is the process of retrieving identified data from various sources.

[0003] In traditional technology, electrical installation processes often rely on manual methods to identify and extract various data from electrical installation projects.

[0004] However, when traditional electrical installation engineering uses manual methods to identify and extract various data, it not only requires a lot of manpower and time, but also suffers from low accuracy and long processing time due to the large amount of data to be identified and extracted. In short, the current data identification efficiency for electrical installation engineering is low. Summary of the Invention

[0005] Based on this, this application provides a method, apparatus, computer equipment, and storage medium for processing electrical engineering data, which can improve the data identification efficiency of data related to electrical installation engineering.

[0006] Firstly, a method for processing electrical engineering data is provided, the method comprising:

[0007] Obtain raw data for electrical engineering, including relevant parameters of electrical engineering components;

[0008] The raw electrical engineering data is processed using a data extraction model to obtain digitized data from the raw data.

[0009] The digital asset data is processed using technical and economic rules, and the processed data is then displayed.

[0010] In one embodiment, the acquisition of raw electrical engineering data includes:

[0011] Optical character recognition (OCR) algorithms are used to identify two-dimensional data related to electrical engineering and obtain parameters related to components from the two-dimensional data.

[0012] Remove erroneous text from component-related parameters in the 2D data to obtain the original electrical engineering data.

[0013] In one embodiment, the removal of erroneous text from component-related parameters in the two-dimensional data includes:

[0014] The parameters related to the components in the two-dimensional data are input into the classification model, and the raw data of electrical engineering are obtained based on the output of the classification model. The classification model is used to divide the input text into correct text and incorrect text.

[0015] In one embodiment, the above-mentioned processing of raw electrical engineering data using a data extraction model includes:

[0016] The original electrical engineering data is classified according to the component attributes to obtain component classification data; the component classification data is coded, and the coded data is processed in an integrated manner to obtain digital data.

[0017] In one embodiment, the above-mentioned classification of raw electrical engineering data based on component attributes includes:

[0018] Obtain the plugin's description file; a plugin is a functional extension plugin of the framework to which a component belongs. The description file includes information about the plugin data package and the plugin class name; load the plugin data package based on the plugin data package information, instantiate the plugin data package based on the plugin class name, and classify the original electrical engineering data according to the classification attributes or classification algorithms in the plugin data package to obtain component classification data.

[0019] In one embodiment, the above-mentioned data integration processing of the encoded data includes:

[0020] The encoded data is processed in an integrated manner according to the framework of the integrated electrical engineering standards system.

[0021] In one embodiment, before processing the raw electrical engineering data using the data extraction model, the method further includes:

[0022] The data is split into multiple first data elements; the data type of the first data elements is the basic data type of the first language; each first data element is converted into a second data element, and the data type of the second data element is the basic data type of the second language; data corresponding to the second language is constructed based on all the second data elements.

[0023] Secondly, an electrical engineering data processing apparatus, the apparatus comprising:

[0024] The acquisition module is used to acquire raw data for electrical engineering, which includes relevant parameters of electrical engineering components.

[0025] The data processing module is used to process the raw electrical engineering data using a data extraction model to obtain digitized data from the raw data.

[0026] The matching module is used to perform technical and economic rule matching processing on digital asset data and display the processed data.

[0027] Thirdly, a computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, implements the steps of any of the methods described in the first aspect.

[0028] Fourthly, a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the methods described in the first aspect.

[0029] The aforementioned method, apparatus, computer equipment, and storage medium for processing electrical engineering data involve a terminal acquiring raw electrical engineering data, processing the raw data using a data extraction model to obtain digitized data from the raw data, and then performing technical rule matching processing on the digitized data to display the processed data. In this application, since the raw electrical engineering data includes relevant parameters of electrical engineering components, and the raw electrical engineering data is determined based on these parameters, the use of machine learning algorithms to replace manual data identification based on the raw electrical engineering data determined by the relevant parameters of the electrical engineering structure can support large-scale data identification and extraction. The use of machine learning algorithms can also improve the accuracy of data identification and shorten the identification cycle. Overall, this application can improve the efficiency of data identification for electrical installation engineering-related data. Attached Figure Description

[0030] Figure 1 An application environment diagram for the electrical engineering data processing method provided in the embodiments of this application;

[0031] Figure 2 A flowchart illustrating the method for processing electrical engineering data provided in this application embodiment;

[0032] Figure 3 A flowchart illustrating the method for processing electrical engineering data provided in this application embodiment;

[0033] Figure 4A flowchart illustrating the method for processing electrical engineering data provided in this application embodiment;

[0034] Figure 5 Another flowchart illustrating the method for processing electrical engineering data provided in the embodiments of this application;

[0035] Figure 6 Another flowchart illustrating the method for processing electrical engineering data provided in the embodiments of this application;

[0036] Figure 7 This is a schematic diagram of the structure of the electrical engineering data processing device provided in the embodiments of this application;

[0037] Figure 8 Another schematic diagram of the electrical engineering data processing apparatus provided in the embodiments of this application;

[0038] Figure 9 A schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0039] The electrical engineering data processing method, apparatus, computer equipment, and storage medium provided in this application aim to improve the data recognition rate of electrical installation engineering related data. The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below through embodiments and in conjunction with specific accompanying drawings. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0040] The electrical engineering data processing method provided in this embodiment can be applied to, for example, Figure 1 The application environment shown. (Reference) Figure 1 The application environment includes a scanning terminal 10 and a processing device 20. The scanning terminal 10 can communicate with the processing device 20. The scanning terminal 10 can scan two-dimensional drawings, charts, etc., and transmit the scan results to the processing device 20. For example, the scanning terminal 10 can be, but is not limited to, various fully automatic scanners, 3D scanners, mobile scanning apps, etc. The processing device 20 can use machine learning algorithms to analyze and process the scan results transmitted by the scanning terminal 10 to obtain digitized data. The processing device 20 can be, but is not limited to, various personal computers, laptops, etc., or it can be a server.

[0041] It should be noted that the scanning terminal 10 and the processing device 20 can be two independent devices or integrated into one unit; this embodiment does not impose any restrictions on this. Furthermore, the scanning terminal 10 and the processing device 20 can communicate via wired or wireless means; this embodiment does not impose any restrictions on this either.

[0042] Currently, data extraction in the electrical engineering field primarily relies on manual identification. Specifically, this involves manually entering the material lists output from the design, categorizing and organizing them based on experience, and then using calculation tools and manual input and settings to calculate and output the data extraction results for electrical installation projects. This method requires manual identification and participation throughout the entire process, resulting in low levels of automation and intelligence, tediousness, low efficiency, and a high probability of errors. Therefore, the current data identification efficiency for electrical installation engineering-related data remains low.

[0043] Based on this, the embodiments of this application provide a data processing method that can improve the data recognition efficiency of electrical installation engineering related data. Figure 2 This is a flowchart illustrating the electrical engineering data processing method provided in this embodiment, applicable to, for example... Figure 1 Processing device 20 in the system shown. For example... Figure 2 As shown, the method includes the following steps:

[0044] Step 201: Obtain the original electrical engineering data, which includes relevant parameters of the electrical engineering components.

[0045] This application aims to identify relevant data in electrical engineering based on machine learning algorithms, thereby achieving automated identification and acquisition of data. The processing device 20 can perform automated identification and acquisition of data; therefore, in step 201, the processing device 20 can acquire the original electrical engineering data for subsequent identification and acquisition of data based on the original electrical engineering data.

[0046] One possible implementation is that the raw data for electrical engineering can be some raw data from one or more electrical engineering construction phases. For example, electrical engineering can be a power distribution installation project, an electrical instrumentation installation project, or a lightning protection grounding installation project; this application embodiment does not limit this.

[0047] In one possible implementation, the raw data from the electrical engineering construction phase is used to describe the composition of the electrical engineering. For example, the components of the electrical engineering can be electrical engineering parts, and the aforementioned raw data can be related data of these parts. For instance, an electrical engineering part can be a transformer, a circuit breaker, or a motor; this application embodiment does not impose any limitations on this.

[0048] In one possible implementation, the raw data of the electrical engineering components are used to describe the properties of the electrical engineering components. For example, these may be the installation parameters of the components, the substation parameters of the components, the parameters of the power distribution network to which the components belong, and the usage specifications of the components. This application embodiment does not impose any limitations on these aspects.

[0049] In practice, the scanning terminal 10 scans two-dimensional data related to electrical engineering (e.g., charts, drawings, etc.), and the processing device 20 obtains the scanning results from the scanning terminal 10. The processing device 20 can also perform image and text recognition on the scanning results to obtain the original electrical engineering data in the two-dimensional data such as charts and drawings. For example, it can identify the relevant parameters of electrical engineering components.

[0050] Step 202: Use the data extraction model to process the original electrical engineering data to obtain the digitized data extracted from the original data.

[0051] In this embodiment, the automated identification and acquisition of data extraction information can be achieved based on a neural network model. For example, the processing device 20 can utilize a data extraction model to process the raw electrical engineering data to obtain digitized data extraction information from the raw data.

[0052] Specifically, the data extraction model is a model for extracting digitized data from raw electrical engineering data. The data extraction model can extract digitized data based on the attributes of electrical engineering components. For example, the digitized data for electrical engineering can be current or voltage, power or frequency, or pressure or humidity; this application does not impose any limitations on these aspects.

[0053] In one possible implementation, the processing device 20 acquires raw electrical engineering data from the scanning device terminal 10 and performs classification and regression on the raw electrical engineering data. Classifying the raw electrical engineering data may involve determining the categories of components within the raw electrical engineering data. The result of classifying the raw electrical engineering data may be that the components are divided into the following categories: installation components, transformer components, or power distribution network components; however, this embodiment does not impose such limitations.

[0054] Regression analysis of raw electrical engineering data can be used to determine the specific quantity of a certain component within the raw data. For example, the regression result of raw electrical engineering data could be the quantity and parameter values ​​of installed components, the quantity and parameter values ​​of transformer components, the quantity and parameter values ​​of network components, or the specific implementation method specified in the standard. This embodiment does not impose any specific limitations.

[0055] Step 203: Perform technical and economic rule matching processing on the digital asset data and display the processed data.

[0056] The data output by the data extraction model may conflict with the actual technical and economic rules. Therefore, in step 203, technical and economic rule matching processing can be performed on the data output by the data extraction model to obtain data that matches the technical and economic rules.

[0057] Specifically, technical and economic rules refer to technical and economic rules. Technical and economic rule matching processing involves transforming and validating the digitized data extracted from the data extraction model. For example, transformation refers to adding other metadata or using timestamps or geographic location data to enrich the data, and then storing the extracted data in a data warehouse. For example, validation refers to performing a reverse query on the data stored in the data warehouse to determine whether the data is correct.

[0058] After performing the aforementioned transformation and verification on the digitized data, the processed data needs to be displayed. For example, public disclosure refers to making the data publicly available online or in text format.

[0059] In the above-mentioned method for processing electrical engineering data, a scanning device acquires raw electrical engineering data, which includes relevant parameters of electrical engineering components. A processing device uses a data extraction model to process the raw electrical engineering data, obtaining digitized data from the raw data. This digitized data is then subjected to technical rule matching processing, and the processed data is displayed. It is evident that the method provided in this application can automatically identify and extract a large amount of raw electrical installation engineering data using machine learning algorithms, improving recognition accuracy and shortening the recognition cycle. This replaces the original method of manual data extraction, which required manual verification of the data, fully utilizing the advantages of machine learning algorithms for rapid and automatic data identification and extraction. Therefore, overall, this application can improve the data recognition efficiency of raw electrical installation engineering data, providing a foundation for removing erroneous data from the data.

[0060] Figure 2 In step 201 of the method shown, in a scenario where the scanning device 10 and the processing device 20 are integrated, the processing device 20 can utilize Optical Character Recognition (OCR) of two-dimensional data and obtain the aforementioned original electrical engineering data based on the recognition results. For example, the specific implementation of "obtaining original electrical engineering data" mentioned above includes... Figure 3 The steps shown are as follows:

[0061] Step 301: Use the Optical Character Recognition (OCR) algorithm to recognize the two-dimensional data related to electrical engineering and obtain the parameters related to the components in the two-dimensional data;

[0062] Specifically, optical character recognition (OCR) algorithms can recognize two-dimensional data. For example, two-dimensional data can be data related to electrical engineering, such as drawings or charts, and its forms include, but are not limited to: engineering construction drawings, engineering design drawings, charts of engineering-related data, and engineering-related parameter documents.

[0063] In one possible implementation, the two-dimensional data includes raw electrical engineering data. For example, the two-dimensional data may include parameters of electrical engineering components. Exemplary examples include the names of installation components, transformer components, and power distribution network components; however, this embodiment does not impose such limitations.

[0064] One possible implementation involves the processing device 20 using an Optical Character Recognition (OCR) algorithm to recognize characters printed on engineering drawings. This involves determining the character's shape by detecting dark and light patterns, and then translating the shape into text using a character recognition method. For example, for printed characters, an optical method is used to convert the text in the paper document into a black-and-white dot matrix image file, and then recognition software converts the text in the image into text format. The OCR-converted text may include parameters related to the component, thus the processing device 20 can obtain component-related parameters from two-dimensional data using OCR.

[0065] Step 302: Remove erroneous text from the parameters related to the components in the two-dimensional data to obtain the original electrical engineering data.

[0066] Specifically, the system detects whether abnormal text is included in the parameters related to components in the two-dimensional data. When the detection result of component-related text in the two-dimensional data is abnormal, then the text is erroneous. The presence of erroneous text will affect the accuracy of electrical engineering raw data recognition, so it needs to be removed. For example, erroneous text may be a mismatch between component category and component quantity in the electrical engineering raw data, which will affect the accuracy of electrical installation engineering raw data recognition. Therefore, deleting component-related erroneous text can improve the accuracy of electrical engineering raw data recognition.

[0067] One possible approach is to remove erroneous text related to components in two-dimensional data through data preprocessing. Data preprocessing refers to clearing erroneous data from the two-dimensional data before further processing of component-related data. For example, data preprocessing refers to data cleaning performed before classifying the acquired raw electrical engineering data; this embodiment of the application does not impose limitations on this. Data cleaning refers to filtering out erroneous data and then removing it; for example, data cleaning deletes incomplete, erroneous, and duplicate data.

[0068] The aforementioned method for processing electrical engineering data utilizes Optical Character Recognition (OCR) algorithms to identify two-dimensional data related to electrical engineering, obtain parameters related to components within the two-dimensional data, remove erroneous text from these parameters, and obtain the original electrical engineering data. In this embodiment, OCR is used to identify two-dimensional data on electrical engineering drawings or charts and remove erroneous text, replacing the original method of manually inputting two-dimensional data into tables and manually removing erroneous data. This fully leverages the advantages of machine learning algorithms in automatically removing erroneous data. Therefore, overall, this application can improve the removal rate of original erroneous data in electrical installation engineering, providing accurate data for the automated identification of data.

[0069] Figure 3 In step 301 of the method shown, the processing device 20 can use Optical Character Recognition (OCR) to obtain detected abnormal data of component-related text in the two-dimensional data and remove it. For example, the specific implementation of "detecting abnormal data and removing it" mentioned above includes: inputting the component-related parameters in the two-dimensional data into a classification model, obtaining the original electrical engineering data based on the output of the classification model; the classification model is used to classify the input text into correct text and incorrect text.

[0070] Specifically, the input to the classification model is the raw data from electrical engineering, and its output includes two categories: correct text and incorrect text. Therefore, the classification model can determine correct text from incorrect text. In specific implementation, a confusion matrix can be used to determine correct and incorrect text, and then the incorrect text can be removed. For example, taking a binary classification model, assuming there are only two classes, 0 and 1, there are four possible final discrimination results. The above four discrimination results are displayed on the confusion matrix, which is a two-row, two-column cross matrix. The rows are the true values, and the columns are the predicted values. The true values ​​are classified as true or false (TF), and the predicted values ​​are classified as positive or negative (PN). First, the positive or negative of the predicted value is determined, and then the true or false of the true value is determined. A predicted value of 1 is positive (P), and a predicted value of 0 is negative (N). If the predicted value matches the true value, it is true (T); if the predicted value does not match the true value, it is false (F). This embodiment of the application does not impose any limitations.

[0071] One possible approach is to use the Da-BiLSTM (Bidirectional Long Short-Term Memory) classification model to determine the correct and abnormal text related to the component. This application does not limit the scope of the embodiments.

[0072] The aforementioned method for processing electrical engineering data involves inputting component-related parameters from two-dimensional data into a classification model, and obtaining the original electrical engineering data based on the model's output. The classification model categorizes the input text into correct and incorrect text. In this embodiment, a confusion matrix from the classification model is used to determine correct and incorrect text, replacing the original method of manually removing incorrect data based on experience. This fully leverages the advantages of machine learning algorithms in automatically removing incorrect data. Therefore, overall, this application can improve the removal rate of incorrect text in the original data of electrical installation engineering, providing a data foundation for the automated identification of data.

[0073] Figure 2 In step 202 of the method shown, the raw electrical engineering data is processed using a data extraction model to obtain digitized data from the raw data. For example, the specific implementation of "obtaining digitized data using a data extraction model" mentioned above includes... Figure 4 The steps shown are as follows:

[0074] Step 401: Classify the original electrical engineering data according to the component attributes to obtain component classification data;

[0075] Specifically, component attributes refer to the parameters of the components that make up the original data of electrical engineering. For example, component attributes may include, but are not limited to, component name, component size, and component cost.

[0076] In practical implementation, machine learning models can be used to automate the identification and acquisition of data. Specifically, the data identification model can automate the identification and acquisition of data. Specifically, the data extraction model classifies and regresses the original electrical engineering data. Classification determines the categories, and regression determines the quantities. For example, to classify the original electrical engineering data, which consists of transformers, lighting equipment, fire-fighting equipment, electrical instruments, etc., the classification model needs to be able to determine which category these data belong to. To regress the original electrical engineering data, the digital data refers to determining the specific number, size, model, and specifications of the aforementioned components. This allows for changes to the number or parameters of components during electrical installation, enabling modifications during the design process and improving installation efficiency and cost rationalization. For example, the classification model needs to be able to determine the specific number, size, model, and specifications of these categories of components; however, this embodiment does not impose limitations on this.

[0077] In one possible implementation, the machine learning model used to implement step 401 can be a support vector machine, k-nearest neighbor, logistic regression, or a Naive Bayes machine learning classification model; this embodiment of the application does not impose any limitations on this. The machine learning model can also be a component data model.

[0078] Step 402: Encode the component classification data, and perform integrated data processing on the encoded data to obtain digital asset data.

[0079] Specifically, encoding refers to using codes to represent various sets of data, making them information that can be processed and analyzed by computers. Codes are symbols used to represent things. For example, the above codes can be represented by numbers, letters, special symbols, or combinations thereof. There are two commonly used encoding methods in digital systems: binary encoding and decimal encoding. This application does not limit these methods. For example, information encoding, based on information classification, assigns symbols with certain regularities that are easily recognized by computers and humans for processing.

[0080] One possible approach is for the data extraction model to encode component classification data using the ASCII algorithm. ASCII is an abbreviation for "American Standard for Information Interchange," also known as "US Standard." US Standard specifies a standardized encoding method using 128 numbers from 0 to 127 to represent information, including 33 control codes, one space code, and 94 symbolic codes. The symbolic codes include uppercase and lowercase English letters, Arabic numerals, punctuation marks, etc. The English computer text we read is transmitted and stored using symbolic codes. US Standard is a universal encoding used by most computers of all sizes internationally, and this application does not impose any limitations on it.

[0081] In one possible implementation, the machine learning model used to implement step 402 can be a conceptual data model, which is not limited in this embodiment of the application.

[0082] The above-mentioned method for processing electrical engineering data uses a data extraction model to process the original electrical engineering data, obtains digitized data from the original data, encodes the component classification data, and performs integrated data processing on the encoded data to obtain digitized data. This replaces the original method of manually classifying the original electrical engineering data based on experience and then manually inputting the data into a table.

[0083] Figure 4 In step 401 of the method shown, the original electrical engineering data can be classified according to the plugin's description file to obtain component classification data. For example, the specific implementation of "classifying the original electrical engineering data according to component attributes" mentioned above includes... Figure 5 The steps shown are as follows:

[0084] Step 501: Obtain the plugin's description file; a plugin is a functional extension plugin for the framework to which the component belongs. The description file includes information about the plugin data package and the plugin class name.

[0085] Specifically, a plugin refers to a program written according to a certain application programming interface specification. It can only run on the system platform specified by the program (it may support multiple platforms simultaneously) and cannot run independently of the specified platform. A plugin is a functional extension of the framework described above. The framework is used to construct a set of collaborative classes for a specific type of reusable software design, directly benefiting from code upgrades by others. This application's embodiments do not impose limitations on this.

[0086] Step 502: Load the plug-in data package according to the plug-in data package information, instantiate the plug-in data package according to the plug-in class name, classify the original electrical engineering data according to the classification attributes or classification algorithms in the plug-in data package, and obtain component classification data.

[0087] Specifically, the plug-in data packet information refers to the data unit used for plug-in information transmission, which is not limited in this embodiment. The plug-in class name refers to the process of creating a plug-in entity using an abstract conceptual class, while instantiation refers to the process of creating an object using a class—the process of specifying an abstract conceptual class as a concrete entity. For example, the abstract plug-in class name can be specified as a classification attribute or classification algorithm in the plug-in data packet to classify the original electrical engineering data and obtain component classification data; this is not limited in this embodiment.

[0088] This application provides a method to accurately classify raw data about electrical engineering components based on classification attributes or classification algorithms in the plug-in data package, thereby obtaining component classification data.

[0089] Figure 4 In step 402 of the method shown, the component classification data is encoded, and the encoded data undergoes integrated data processing to obtain the digitized data. For example, the specific implementation of "integrated data processing of the encoded data" mentioned above includes:

[0090] The encoded data is processed in an integrated manner according to the framework of the integrated electrical engineering standards system.

[0091] Specifically, the integrated system framework for electrical engineering standards is used to process coded data in an integrated manner. It serves as a framework for enterprises to develop and utilize information resources. The aforementioned integrated processing includes data element standards, information classification and coding standards, user view standards, conceptual database standards, and logical database standards. The embodiments in this application are not limited herein.

[0092] In one possible implementation, a data element standard is used to standardize elements in the data, which can be Chinese or English. This data element standard performs standardization processing on the encoded data. For example, the data element standard needs to comply with national and industry standards, but this application does not impose such limitations.

[0093] In one possible implementation, the information classification coding standard is used to standardize the classification coding of information, and can be code compiled by JAVA or Python. For example, the information classification coding standard can achieve code uniqueness, implementing one code for each component category and component parameters; however, this embodiment of the application does not impose any limitations.

[0094] One possible implementation is that the user view standard reflects the user's view of the data entity. For example, the user view standard can be an input form, an updated screen data format, or a query screen data format. This application embodiment does not impose any limitations on this.

[0095] One possible implementation is that the conceptual database reflects the end-user's perspective on data storage and is a comprehensive summary of user needs. For example, a conceptual database is typically expressed using a database name and a description of its content: a conceptual database identifier and a conceptual database name (information content description).

[0096] The logical database standard is designed from the perspective of system analysts and designers, representing a further decomposition and refinement of the conceptual database. For example, a logical database is represented in the following format: Logical Database Identifier, Logical Database Name (Primary Key, Attribute Table). The primary key is identified by corresponding attributes, and multiple attribute identifiers are connected by a plus sign. For instance, the primary key represents the organization code, and the attribute table represents the organization name, establishment date, and total number of personnel. This embodiment of the application does not impose limitations on this.

[0097] In this embodiment of the application, before automatically identifying and extracting the original electrical engineering data from the input model, the original electrical engineering data can be converted into a computer programming language so that the processing device 20 can better identify the original electrical engineering data. For example, refer to... Figure 6 Before processing the raw electrical engineering data using the data extraction model mentioned above, the methods also include:

[0098] Step 601: Divide the data into multiple first data elements; the data type of the first data element is a basic data type of the first language;

[0099] Specifically, the first language refers to the original data on drawings or charts described in Chinese, and the first data element refers to the original electrical engineering data composed of Chinese characters, letters, and Arabic numerals. This application does not impose any restrictions on these elements.

[0100] One possible implementation, exemplarily, is that the data element can be the size and cost of a single component; however, this embodiment of the application is not limited thereto. Exemplarily, the first language refers to the original data on electrical engineering drawings and charts expressed in human-readable Chinese.

[0101] Step 602: Convert each first data element into a second data element, where the data type of the second data element is a basic data type of the second language;

[0102] Specifically, the second language refers to the raw data on electrical engineering drawings and charts that computers can recognize and process, while the second data element refers to the representation of the raw electrical engineering data using codes. Converting the first data element into the second data element means converting human-readable text into characters that computers can recognize and process.

[0103] Step 603: Construct data corresponding to the second language based on all the second data elements.

[0104] Specifically, all second data elements are constructed into their corresponding data. "Construction" refers to compiling characters into code statements. For example, the second data elements can be either Python or Java; second-language data refers to code compiled using the aforementioned programming language to represent the original data of the electrical engineering components. It should be understood that although... Figure 2-6 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2-6 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0105] In one embodiment, such as Figure 7 As shown, an electrical engineering data processing device is provided, including: an acquisition module 701, a data processing module 702, and a matching module 703. Wherein:

[0106] The acquisition module 701 is used to acquire the original data of electrical engineering, which includes the relevant parameters of electrical engineering components.

[0107] Data processing module 702 is used to process the raw electrical engineering data using a data extraction model to obtain digitized data from the raw data.

[0108] The matching module 703 is used to perform technical and economic rule matching processing on the digital asset data and display the processed data.

[0109] In one embodiment, such as Figure 8 As shown, the acquisition module 701 includes: an identification unit 7011 and a removal unit 7012, wherein:

[0110] The recognition unit 7011 is used to recognize two-dimensional data related to electrical engineering using the optical character recognition algorithm (OCR) to obtain parameters related to components in the two-dimensional data.

[0111] The removal unit 7012 is used to remove erroneous text from the parameters related to components in the two-dimensional data to obtain the original electrical engineering data.

[0112] In one embodiment, the removal unit 7012 is specifically used to input the parameters related to the component in the two-dimensional data into the classification model, and obtain the original electrical engineering data according to the output of the classification model; the classification model is used to divide the input text of the classification model into correct text and incorrect text.

[0113] In one embodiment, such as Figure 8 As shown, the data processing module 702 includes: a classification unit and an encoding unit, wherein:

[0114] Classification unit 7021 is used to classify the original electrical engineering data according to the component attributes to obtain component classification data;

[0115] The coding unit 7022 is used to encode the component classification data and perform integrated data processing on the encoded data to obtain digital asset data.

[0116] In one embodiment, the classification unit 7021 is specifically used to: obtain the description file of the plug-in; the plug-in is a functional extension plug-in of the framework to which the component belongs, and the description file includes information of the plug-in data package and the plug-in class name; load the plug-in data package according to the plug-in data package information, instantiate the plug-in data package according to the plug-in class name, and classify the original electrical engineering data according to the classification attributes or classification algorithm in the plug-in data package to obtain component classification data.

[0117] In one embodiment, the encoding unit 7022 is specifically used to perform integrated processing on the encoded data according to the integrated framework of electrical engineering standards.

[0118] In one embodiment, such as Figure 8 As shown, the electrical engineering data processing device also includes a conversion module 703.

[0119] The conversion module 703 is used to split the data into multiple first data elements; the data type of the first data elements is a basic data type of a first language; each first data element is converted into a second data element, the data type of the second data element is a basic data type of a second language; and data corresponding to the second language is constructed based on all the second data elements. Specific limitations regarding the electrical engineering data processing device can be found in the limitations of the electrical engineering data processing method above, and will not be repeated here. Each module in the above-mentioned electrical engineering data device can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0120] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores digitized data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements an electrical engineering data processing method.

[0121] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0122] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0123] The process involves acquiring raw electrical engineering data, including relevant parameters of electrical engineering components; processing the raw electrical engineering data using a data extraction model to obtain digitized data; performing technical and economic rule matching on the digitized data; and displaying the processed data.

[0124] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0125] Optical character recognition (OCR) algorithms are used to identify two-dimensional data related to electrical engineering, and parameters related to components are obtained from the two-dimensional data. Erroneous text in the parameters related to components in the two-dimensional data is removed to obtain the original electrical engineering data.

[0126] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0127] The parameters related to the components in the two-dimensional data are input into the classification model, and the raw data of electrical engineering are obtained based on the output of the classification model. The classification model is used to divide the input text into correct text and incorrect text.

[0128] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0129] The original electrical engineering data is classified according to the component attributes to obtain component classification data; the component classification data is coded, and the coded data is processed in an integrated manner to obtain digital data.

[0130] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0131] Obtain the plugin's description file; a plugin is a functional extension plugin of the framework to which a component belongs. The description file includes information about the plugin data package and the plugin class name; load the plugin data package based on the plugin data package information, instantiate the plugin data package based on the plugin class name, classify the original electrical engineering data based on the classification attributes and / or classification algorithms in the plugin data package, and obtain component classification data.

[0132] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0133] The encoded data is processed in an integrated manner according to the framework of the integrated electrical engineering standards system.

[0134] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0135] The data is split into multiple first data elements; the data type of the first data elements is the basic data type of the first language; each first data element is converted into a second data element, and the data type of the second data element is the basic data type of the second language; data corresponding to the second language is constructed based on all the second data elements.

[0136] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0137] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for processing electrical engineering data, characterized in that, The method includes: Obtain raw electrical engineering data, which includes relevant parameters of electrical engineering components; Obtain the plugin's description file; the plugin is a functional extension plugin of the framework to which the component belongs, and the description file includes information about the plugin data package and the plugin class name; Load the plug-in data package according to the information in the plug-in data package, instantiate the plug-in data package according to the plug-in class name, classify the original electrical engineering data according to the classification attributes or classification algorithms in the plug-in data package, and obtain component classification data; The component classification data is encoded using a data extraction model, and the encoded data is then processed through integrated data processing to obtain digital data. The digital data includes at least one of the specific number, size, model, and specifications of the electrical engineering components. The data extraction model includes any one of the following: support vector machine, k-nearest neighbor, logistic regression, and Naive Bayes machine learning classification model. The digital asset submission data is subjected to technical and economic rule matching processing, and the processed data is displayed. The technical and economic rule matching processing is to transform and verify the digital asset submission data. The transformation includes adding other metadata or using timestamps or geographic location data in the digital asset submission data. The verification includes performing reverse queries on the digital asset submission data.

2. The method according to claim 1, characterized in that, The acquisition of raw electrical engineering data includes: Optical character recognition (OCR) algorithms are used to identify two-dimensional data related to electrical engineering, and parameters related to components in the two-dimensional data are obtained. Remove erroneous text from the component-related parameters in the two-dimensional data to obtain the original electrical engineering data.

3. The method according to claim 2, characterized in that, The removal of erroneous text from the component-related parameters in the two-dimensional data includes: The parameters related to the components in the two-dimensional data are input into the classification model, and the original electrical engineering data are obtained based on the output of the classification model; the classification model is used to divide the input text into correct text and incorrect text.

4. The method according to claim 3, characterized in that, The classification model is a data bidirectional long short-term memory (Da-BiLSTM) classification model.

5. The method according to claim 1, characterized in that, The data integration processing of the encoded data includes: The encoded data is processed in an integrated manner according to the framework of the integrated electrical engineering standards system.

6. The method according to claim 1, characterized in that, Before obtaining the plugin's description file, the method further includes: The data is split into multiple first data elements; the data type of the first data elements is a basic data type of a first language; Each of the first data elements is converted into a second data element, wherein the data type of the second data element is a basic data type of the second language; Construct data corresponding to the second language based on all the second data elements.

7. A device for processing electrical engineering data, characterized in that, The device includes: The acquisition module is used to acquire raw electrical engineering data, which includes relevant parameters of electrical engineering components. A data processing module is used to obtain the description file of a plugin; the plugin is a functional extension plugin of the framework to which the component belongs, and the description file includes information about the plugin data package and the plugin class name; the module loads the plugin data package according to the information of the plugin data package, instantiates the plugin data package according to the plugin class name, classifies the original electrical engineering data according to the classification attributes or classification algorithms in the plugin data package to obtain component classification data; the module encodes the component classification data using a data extraction model, and performs integrated data processing on the encoded data to obtain digital information data; the digital information data includes at least one of the following: the specific number, size, model, and specifications of the electrical engineering components; The matching module is used to perform technical and economic rule matching processing on the digital asset data and display the processed data. The technical and economic rule matching processing is to transform and verify the digital asset data. The transformation includes adding other metadata or using timestamps or geographic location data in the digital asset data. The verification includes performing reverse queries on the digital asset data.

8. The apparatus according to claim 7, characterized in that, The acquisition module includes: The recognition unit is used to recognize two-dimensional data related to electrical engineering using optical character recognition (OCR) algorithms to obtain parameters related to components in the two-dimensional data. The removal unit is used to remove erroneous text from the parameters related to the components in the two-dimensional data to obtain the original electrical engineering data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images