CN113887274A - Method and device for processing electrical engineering data, computer equipment and storage medium - Google Patents
Method and device for processing electrical engineering data, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113887274A CN113887274A CN202110954027.4A CN202110954027A CN113887274A CN 113887274 A CN113887274 A CN 113887274A CN 202110954027 A CN202110954027 A CN 202110954027A CN 113887274 A CN113887274 A CN 113887274A
- Authority
- CN
- China
- Prior art keywords
- data
- electrical engineering
- processing
- plug
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004870 electrical engineering Methods 0.000 title claims abstract description 181
- 238000012545 processing Methods 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000013075 data extraction Methods 0.000 claims abstract description 30
- 238000013145 classification model Methods 0.000 claims description 32
- 238000012015 optical character recognition Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 230000010354 integration Effects 0.000 claims description 15
- 238000007635 classification algorithm Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000010616 electrical installation Methods 0.000 abstract description 21
- 230000008569 process Effects 0.000 description 15
- 238000003672 processing method Methods 0.000 description 14
- 238000010801 machine learning Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 230000002159 abnormal effect Effects 0.000 description 8
- 238000009434 installation Methods 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 6
- 238000009826 distribution Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a method and a device for processing electrical engineering data, computer equipment and a storage medium. The method comprises the following steps: acquiring electrical engineering raw data, wherein the electrical engineering raw data comprises relevant parameters of electrical engineering components; processing the electrical engineering original data by using a data extraction model to obtain digital contribution data in the original data; and performing technical rule matching processing on the digital contribution data, and displaying the processed data. The data identification efficiency of the relevant data of the electrical installation engineering can be improved.
Description
Technical Field
The present application relates to the field of electrical installation engineering technologies, and in particular, to a method and an apparatus for processing electrical engineering data, a computer device, and a storage medium.
Background
With the rapid development of scientific technology, electrical engineering for producing electrical and electronic systems covers almost all electronic, photonic-related engineering activities. The arrival of the information era based on computer networks is just promoted by the great progress of electronic technology, and a great deal of information digital processing business is derived in the information era. In the field of electrical engineering, the digital processing of information includes data identification, data extraction, data conversion and data loading of various data of electrical installation engineering. The data identification is to extract original data on a drawing and remove a fault text. Data extraction is the process of retrieving identified data relating to various sources.
In the traditional technology, various data of electrical installation engineering are mostly identified and extracted in a manual mode in the electrical installation process.
However, when the conventional electrical installation project adopts a manual method to identify and extract various data of the electrical installation project, not only a large amount of manpower and time are required to be consumed, but also the amount of data to be identified and extracted is large, and the problems of low identification accuracy, long identification period and the like exist in the prior art for processing the relevant data of the electrical installation project, and in a word, the data identification efficiency of the relevant data of the electrical installation project is low at present.
Disclosure of Invention
Based on the above, the application provides a processing method and device of electrical engineering data, a computer device and a storage medium, which can improve the data identification efficiency of the electrical installation engineering related data.
In a first aspect, a method for processing electrical engineering data is provided, and the method includes:
acquiring electrical engineering raw data, wherein the data comprises relevant parameters of electrical engineering components;
processing the original data of the electrical engineering by using a data extraction model to obtain digital contribution data in the original data;
and carrying out technical rule matching processing on the digital contribution data, and displaying the processed data.
In one embodiment, the acquiring raw electrical engineering data includes:
identifying two-dimensional data related to electrical engineering by using an Optical Character Recognition algorithm (Optical Character Recognition) to obtain parameters related to components in the two-dimensional data;
and removing error texts in parameters related to the components in the two-dimensional data to obtain the original data of the electrical engineering.
In one embodiment, the removing the erroneous text in the parameter related to the member in the two-dimensional data includes:
inputting parameters related to the components in the two-dimensional data into a classification model, and obtaining an electrical engineering original number according to the output of the classification model; the classification model is used for dividing the input text of the classification model into correct text and error text.
In one embodiment, the processing the electrical engineering raw data by using the data extraction model includes:
classifying the electrical engineering original data according to the component attributes to obtain component classification data; and coding the component classification data, and carrying out data integration processing on the coded data to obtain digital contribution data.
In one embodiment, the classifying the electrical engineering raw data according to the component attributes includes:
acquiring a description file of the plug-in; the plug-in is a function extension plug-in of a framework to which the component belongs, and the description file comprises information of a plug-in data packet and a plug-in class name; and loading the plug-in data packet according to the plug-in data packet information, instantiating the plug-in data packet according to the plug-in class name, and classifying the electrical engineering original data according to the classification attribute or classification algorithm in the plug-in data packet to obtain component classification data.
In one embodiment, the performing data integration processing on the encoded data includes:
and carrying out integrated processing on the coded data according to an electrical engineering standard integrated system framework.
In one embodiment, before the processing the electrical engineering raw data by using the data extraction model, the method further includes:
splitting the funding data into a plurality of first data elements; the data type of the first data element is a basic data type of a first language; converting each first data element into a second data element, wherein the data type of the second data element is a basic data type of a second language; and constructing data corresponding to the second language according to all the second data elements.
In a second aspect, an apparatus for processing electrical engineering data, the apparatus comprising:
the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for acquiring electrical engineering raw data, and the electrical engineering raw data comprises relevant parameters of electrical engineering components;
the data processing module is used for processing the original data of the electrical engineering by using the data extraction model to obtain digital contribution data in the original data;
and the matching module is used for carrying out skill rule matching processing on the digital contribution data and displaying the processed data.
In a third aspect, a computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods of the first aspect when executing the computer program.
In a fourth aspect, a computer-readable storage medium has stored thereon a computer program which, when executed by a processor, carries out the steps of the method of any of the first aspects described above.
According to the method and the device for processing the electrical engineering data, the terminal obtains the electrical engineering original data, the data extraction model is used for processing the electrical engineering original data to obtain the digital submission data in the original data, the digital submission data is subjected to skill rule matching processing, and the processed data is displayed. In the application, because the electrical engineering raw data comprise the relevant parameters of the electrical engineering component, and the electrical engineering raw data are determined according to the relevant parameters of the electrical engineering component, the machine learning algorithm is used for replacing manual work to identify the contribution data according to the electrical engineering raw data determined according to the relevant parameters established in the electrical engineering, so that a large amount of data identification and extraction can be supported, the identification accuracy of the contribution data can be improved by adopting the machine learning algorithm, and the identification period can be shortened. Overall, the data identification efficiency of the relevant data of the electrical installation engineering can be improved by adopting the method and the device.
Drawings
Fig. 1 is an application environment diagram of a processing method of electrical engineering data according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a processing method of electrical engineering data according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of a processing method of electrical engineering data according to an embodiment of the present disclosure;
fig. 4 is a schematic flowchart of a processing method of electrical engineering data according to an embodiment of the present disclosure;
fig. 5 is another schematic flow chart of a processing method of electrical engineering data according to an embodiment of the present disclosure;
fig. 6 is another schematic flow chart of a processing method of electrical engineering data according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a device for processing electrical engineering data according to an embodiment of the present disclosure;
fig. 8 is another schematic structural diagram of a device for processing electrical engineering data according to an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The application provides a processing method and device of electrical engineering data, computer equipment and a storage medium, and aims to improve the data identification rate of electrical installation engineering related data. The following detailed description will specifically describe the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems by embodiments and with reference to the specific drawings. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
The method for processing electrical engineering data provided by this embodiment may be applied to the application environment shown in fig. 1. Referring to fig. 1, the application environment includes a scanning terminal 10 and a processing device 20. The scanning terminal 10 may communicate with a processing device 20. The scanning terminal 10 may scan a two-dimensional drawing, a diagram, or the like, and transmit the scanning result to the processing device 20. For example, the scanning terminal 10 may be, but is not limited to, various fully automatic scanners, 3D scanners, cell phone scanning APPs, and so on. The processing device 20 may analyze and process the scanning result transmitted by the scanning terminal 10 by using a machine learning algorithm to obtain digitized funding data. The processing device 20 may be, but is not limited to, various personal computers, notebook computers, etc., and may also be a server.
It should be noted that the scanning terminal 10 and the processing device 20 may be two independent devices, or may be integrated into one body, and the embodiment of the present application does not limit this. In addition, the scanning terminal 10 and the processing device 20 may communicate with each other in a wired or wireless manner, which is not limited in the embodiment of the present application.
At present, manual identification and funding data are mainly adopted in the field of electrical engineering. The method is characterized in that a material table for design output is manually input, calculation and output of the data result of electric installation engineering investment improvement are completed in a mode of classifying and arranging according to experience, calculating tools, manual input and setting, manual identification and participation are needed in the whole process of the mode, the automation and intelligence degree is low, the complexity is high, the efficiency is low, and the error probability is high. Therefore, the problem that the data identification efficiency of the related data of the electrical installation engineering is low exists at present.
Based on this, the embodiment of the application provides a data processing method, which can improve the data identification efficiency of the relevant data of the electrical installation engineering. Fig. 2 is a schematic flow chart of a processing method of electrical engineering data provided in this embodiment, and is suitable for the processing device 20 in the system shown in fig. 1. As shown in fig. 2, the method comprises the steps of:
The embodiment of the application aims to identify relevant data of electrical engineering based on a machine learning algorithm, and realize automatic identification and acquisition of contribution data. The processing device 20 may perform an automated identification and acquisition of the funding data, so that in step 201 the processing device 20 may acquire the electrical engineering raw data for a subsequent identification and acquisition of the funding data based on the electrical engineering raw data.
In one possible implementation, the electrical engineering raw data may be some raw data of one or more electrical engineering construction phases. For example, the electrical engineering may be a transformation and distribution installation engineering, an electrical instrument installation engineering, and a lightning protection and grounding installation engineering, which is not limited in the embodiments of the present application.
In one possible implementation, the raw data of the electrical engineering construction phase is used to describe the composition of the electrical engineering. For example, the electrical engineering component may be an electrical engineering component, and the electrical engineering raw data may be data related to the electrical engineering component. For example, the electrical engineering component may be a transformer, a circuit breaker, or a motor, which is not limited in this embodiment of the present application.
In a possible implementation manner, the raw data of the electrical engineering composition is used to describe the attributes of the electrical engineering component, for example, the installation parameters of the component, the power transformation parameters of the component, the parameters of the power distribution network to which the component belongs, and the usage specification of the component, and the embodiments of the present application are not limited herein.
In a specific implementation, the scanning terminal 10 scans two-dimensional data (e.g., charts, drawings, etc.) related to electrical engineering, and the processing device 20 obtains the scanning result from the scanning terminal 10. The processing device 20 may also perform image-text recognition on the scanning result, and obtain the electrical engineering raw data in the two-dimensional data such as the chart and the drawing, for example, may identify the relevant parameters of the electrical engineering component.
In the embodiment of the application, automatic identification and acquisition of the contribution data can be realized based on the neural network model. For example, the processing device 20 may process the electrical engineering raw data using a data extraction model to obtain digitized contribution data in the raw data.
Specifically, the data extraction model is a model for extracting digital contribution data from electrical engineering raw data. The data extraction model may extract the digitized contribution data based on attributes of the electrical engineering component. For example, the electrical engineering digital mention data may be current or voltage, power or frequency, and may also be pressure or humidity, and the embodiments of the present application are not limited herein.
In a possible implementation manner, the processing device 20 obtains the raw data of the electrical engineering from the scanning device terminal 10, and classifies and regresses the raw data of the electrical engineering. The classification of the electrical engineering raw data can be to determine the category of a component in the electrical engineering raw data; the classification of the electrical engineering raw data may result in the classification of the components into the following categories: the power distribution network component can be a mounting component, a transformer component or a power distribution network component, and the embodiments of the present application are not limited herein.
The regression of the raw electrical engineering data may be to determine what the specific number of a certain component in the raw electrical engineering data is. For example, the regression result of the raw data of the electrical engineering may be the number of installation components and the parameter value, the number of transformer components and the parameter value, the number of network components, the parameter specific value, or the implementation of the usage specification, and the embodiment is not particularly limited herein.
And 203, performing rule matching processing on the digital investment data, and displaying the processed data.
The data output by the data extraction model may conflict with the actual skills rule, and therefore, the data output by the data extraction model may be subjected to skill rule matching processing in step 203 to obtain the contribution data matched with the skill rule.
Specifically, the rules of skill refer to the rules of technical economy. The technical rule matching processing is to convert and verify the digital contribution data extracted by the data extraction model. Illustratively, transformation refers to adding other metadata or enriching the data using timestamps or geographic location data, storing the extracted data in a data warehouse. Illustratively, the verification refers to performing a reverse query on the data stored in the data warehouse to determine whether the data is correct.
After the above conversion and verification are performed on the digital funding data, the processed data needs to be displayed. Illustratively, publicity refers to publicizing data in the form of a network or text to the public.
In the method for processing the electrical engineering data, scanning equipment acquires electrical engineering raw data, the electrical engineering raw data comprise relevant parameters of electrical engineering components, processing equipment processes the electrical engineering raw data by using a data extraction model to acquire digitized contribution data in the raw data, and processes the digitized contribution data by technical rule matching to display the processed data. Therefore, in the method provided by the embodiment of the application, a large amount of original data of the electrical installation project can be automatically identified and extracted by adopting the machine learning algorithm, the identification accuracy is improved, the identification period is shortened, the original manual data extraction is replaced, the data extraction needs to be manually corrected, and the advantage of the quick and automatic identification and extraction of the data by adopting the machine learning algorithm is fully utilized. Therefore, on the whole, the data identification efficiency of the original data of the electrical installation project can be improved, and a foundation is provided for eliminating error data in the funding data.
In step 201 of the method shown in fig. 2, in a scenario where the scanning device 10 and the processing device 20 are integrated, the processing device 20 may utilize Optical Character Recognition (OCR) two-dimensional data, and obtain the above-mentioned electrical engineering raw data based on the Recognition result. Exemplary, the specific implementation of "acquiring raw data of electrical engineering" referred to above includes the steps shown in fig. 3:
301, recognizing two-dimensional data related to electrical engineering by using an optical character recognition algorithm (OCR) to obtain parameters related to components in the two-dimensional data;
specifically, the optical character recognition algorithm OCR may recognize two-dimensional data, which may be, for example, drawing or diagram data related to electrical engineering, and may be in the form of, but not limited to: engineering construction drawings, engineering design drawings, charts of engineering related data and engineering related parameter documents.
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. By way of example, the two-dimensional data may be a name of an installation component, a name of a transformer component, and a name of a distribution network component, and embodiments of the present application are not limited herein.
In one possible implementation, the processing device 20 uses an optical character recognition algorithm OCR to recognize characters printed on the engineering drawings, determine their shapes by detecting dark and light patterns, and then translate the shapes into text using character recognition methods. Illustratively, for the print characters, characters in a paper document are optically converted into an image file of a black and white dot matrix, and the characters in the image are converted into a text format through recognition software. Where the OCR-translated text may include parameters related to the building blocks, processing device 20 may obtain the parameters related to the building blocks in the two-dimensional data using OCR.
And step 302, removing error texts in parameters related to the components in the two-dimensional data to obtain the original data of the electrical engineering.
Specifically, whether parameters related to the component in the two-dimensional data include abnormal texts is detected, when the detection result of the texts related to the component in the two-dimensional data is abnormal, the texts are error texts, and the identification accuracy of the original data of the electrical engineering is affected by the existence of the error texts, so that the texts need to be removed. For example, the error text may be the non-correspondence between the component type and the component number in the raw electrical engineering data, which may affect the identification accuracy of the raw electrical installation data, so that the error text related to the component is deleted, which may improve the identification accuracy of the raw electrical engineering data.
In a possible implementation manner, error texts related to the building blocks in the two-dimensional data can be eliminated through data preprocessing. The data preprocessing refers to clearing the error data before the data related to the component in the two-dimensional data is processed next. For example, the data preprocessing refers to data cleaning before classifying the acquired raw data of the electrical engineering, and the embodiment of the application is not limited herein. Data cleaning refers to screening error data, and removing the error data after screening, and exemplarily, the data cleaning is to delete incomplete data, error data, and repeated data.
According to the processing method of the electrical engineering data, the optical character recognition algorithm OCR is used for recognizing the two-dimensional data related to the electrical engineering to obtain parameters related to the component in the two-dimensional data, the error text in the parameters related to the component in the two-dimensional data is removed, and the original data of the electrical engineering is obtained. In the embodiment of the application, the OCR is adopted to identify the two-dimensional data on the electrical engineering drawing or diagram, the error text is removed, the original manual mode that the two-dimensional data is input into the form is replaced, the error data is removed in the manual mode, and the advantage of automatic removal of the error data of the machine learning algorithm is fully utilized. Therefore, on the whole, the method and the device can improve the rejection rate of the original error data of the electrical installation project and provide accurate data for automatic identification of the funding data.
In step 301 of the method shown in fig. 3, processing device 20 may obtain the detected abnormal data of the text related to the building block in the two-dimensional data by using Optical Character Recognition (OCR), and reject the detected abnormal data. Exemplary, the foregoing specific implementations of "detecting abnormal data and removing the abnormal data" include: inputting parameters related to the components in the two-dimensional data into a classification model, and obtaining an electrical engineering original number according to the output of the classification model; the classification model is used for dividing the input text of the classification model into correct text and error text.
Specifically, the input of the classification model is the original data of the electrical engineering, and the output of the classification model comprises two types, namely correct text and wrong text. Therefore, the judgment of the correct text and the abnormal text can be realized based on the classification model. In a specific implementation, the confusion matrix can be adopted to judge the correct text and the error text, and then the error text is eliminated. For example, taking a binary model as an example, assuming that there are only two classes of 0 and 1, the final discrimination result has four cases. The above four types of determination results are displayed on a confusion matrix, the confusion matrix is a two-row and two-column cross matrix, the behavior true value is listed as a predicted value, the true value is True (TF), the predicted value is divided into yin and yang (PN), firstly, the yin and yang of the predicted value is determined, then, the true and false of the true value is determined, the predicted value is 1, the predicted value is positive (P), the predicted value is 0, the predicted value is negative (N), if the predicted value is consistent with the true value, the predicted value is true (T), and if the predicted value is inconsistent with the true value, the predicted value is false (F), the embodiment of the present application is not limited herein.
In one possible implementation manner, the Da-BiLSTM (data bidirectional long short term memory) classification model may be used to determine correct texts and abnormal texts of texts associated with the building blocks, and the embodiments of the present application are not limited herein.
The processing method of the electrical engineering data inputs parameters related to the components in the two-dimensional data into the classification model, and obtains the electrical engineering original number according to the output of the classification model; the classification model is used for dividing the input text of the classification model into correct text and error text. In the embodiment of the application, the confusion matrix in the classification model is adopted to judge the correct text and the error text, so that the original manual mode of removing the error data according to experience is replaced, and the advantage of automatically removing the error data by a machine learning algorithm is fully utilized. Therefore, on the whole, the method and the device can improve the rejection rate of the error texts in the original data in the electrical installation engineering, and provide a data basis for the automatic identification of the funding data.
In step 202 of the method shown in fig. 2, the raw data of the electrical engineering is processed by using the data extraction model to obtain the digitized contribution data in the raw data. Exemplary, the specific implementation of the aforementioned "obtaining the datamation funding data using the data extraction model" includes the steps shown in fig. 4:
specifically, the component property refers to a parameter of a component constituting the raw data of the electrical engineering, and may be, for example and without limitation, a component name, a component size, and a component manufacturing cost.
In specific implementation, a machine learning model can be used for realizing automatic identification and acquisition of the contribution data, wherein the data identification model can realize automatic identification and acquisition of the contribution data. Specifically, the data extraction model is used for classifying and regressing the electrical engineering raw data, classifying and determining the category, and regressing and determining the quantity. For example, to classify raw data of electrical engineering, the raw data of electrical engineering is composed of transformers, lighting equipment, fire fighting equipment, electrical instruments and the like, and a classification model needs to be able to judge what category the data belong to. The original data of the electrical engineering is regressed, the original data of the electrical engineering is related to the categories, and the digitalized improvement data refers to the determination of the specific number, size, model, specification and the like of the components, so that when the number or parameters of the components need to be changed in the electrical installation engineering, the components can be designed and changed at the same time, and the installation efficiency and the cost of the electrical installation engineering are improved and rationalized. For example, the classification model needs to be able to determine the specific number, size, model, specification, etc. of the members of the classes, and the embodiments of the present application are not limited herein.
In a possible implementation manner, the machine learning model for implementing step 401 may be a support vector machine, k-nearest, Logistic regression, naive bayes machine learning classification model, and the embodiment of the present application is not limited herein. Wherein the machine learning model may also be a component datamation model.
Specifically, the code is information that represents each set of data by a code and is processed and analyzed by a computer, and the code is a symbol that represents an object. Illustratively, the codes may be represented by numbers, letters, special symbols, or a combination thereof. There are two types of codes commonly used in digital systems, one is binary code, and the other is decimal code, and the embodiments of the present application are not limited herein. Illustratively, information encoding is to assign a certain regularity to an encoding object on the basis of information classification, and the encoding object is easy to recognize and process by a computer and a person.
In one possible implementation, the data extraction model may encode the component classification data using an ASCII algorithm. The ASCII is an acronym for "american standard code for information interchange," which may be referred to as "american standard". The american standard specifies a canonical code that represents information by 128 digits from 0 to 127, including 33 control codes, a space code, and 94 character codes. The image code includes English capital and small letter, Arabic number, punctuation mark, etc. English computer texts which are read by people at ordinary times are transmitted and stored in a mode of image codes. The American standard is a common code for most international large-sized computers, and the embodiment of the application is not limited herein.
In one possible implementation, the machine learning model used to implement step 402 may be a data model, and the embodiments of the present application are not limited herein.
According to the method for processing the electrical engineering data, the electrical engineering original data are processed by using the data extraction model to obtain the digital financing data in the original data, the component classification data are encoded, the encoded data are subjected to data integration processing to obtain the digital financing data, the electrical engineering original data are classified by adopting a manual mode according to experience in the original substitute material, and then the data are manually input into the form.
In step 401 of the method shown in fig. 4, classification of the raw data of the electrical engineering may be implemented according to the description file of the plug-in to obtain component classification data. Exemplary, the specific implementation of the aforementioned "classifying the electrical engineering raw data according to component properties" includes the steps shown in fig. 5:
501, obtaining a description file of a plug-in; the plug-in is a function extension plug-in of a framework to which the component belongs, and the description file comprises information of a plug-in data packet and a plug-in class name;
specifically, a plug-in refers to a program written in an application program interface conforming to a certain specification, which can only run under a system platform (possibly supporting multiple platforms simultaneously) specified by the program, and cannot run independently from a specified platform. The framework is a function extension plug-in of the framework, and the framework is used for forming a group of mutually cooperative classes of a specific software reusable design and directly enjoying the benefits brought by upgrading codes of others.
502, loading a plug-in data packet according to the plug-in data packet information, instantiating the plug-in data packet according to the plug-in class name, and classifying the electrical engineering original data according to the classification attribute or classification algorithm in the plug-in data packet to obtain component classification data.
Specifically, the plug-in packet information refers to a data unit for plug-in information transmission, and this embodiment is not limited herein. The plug-in class name refers to a process of creating a plug-in entity by using an abstract concept class, and the instantiation refers to a process of creating an object by using a class and a process of embodying an abstract concept class to the class entity. For example, the abstract plug-in class name is embodied into a classification attribute or a classification algorithm in a plug-in data packet to classify the raw data of the electrical engineering to obtain component classification data, which is not limited herein.
The embodiment of the application provides a method for accurately classifying original data of electrical engineering components according to classification attributes or classification algorithms in plug-in data packets to obtain component classification data.
In step 402 of the method shown in fig. 4, the component classification data is encoded, and the encoded data is subjected to data integration processing to obtain the digital contribution data. For example, the foregoing specific implementation of "data integration processing on encoded data" includes:
and carrying out integrated processing on the coded data according to an electrical engineering standard integrated system framework.
Specifically, the electrical engineering standard integration system framework is used for performing integration processing on coded data, and is a framework for information resource development and utilization by enterprises, where the integration processing includes a data element standard, an information classification coding standard, a user view standard, a concept database standard, and a logic database standard, and embodiments of the present application are not limited herein.
In one possible implementation, the data element standard is used to normalize an element in data, which may be chinese or english, and the data element standard performs normalization processing on the encoded data. For example, the data element standard needs to comply with national and industry standards, and the embodiments of the present application are not limited thereto.
In one possible implementation, the information classification coding standard is used to specify the information classification coding, and may be a code compiled by JAVA or Python. For example, the information classification coding standard may implement code normalization, and implement an object-to-code for the component type and the component parameter, which is not limited herein.
In one possible implementation manner, the user view standard reflects a user's opinion on the data entity, and for example, the user view standard may be an input form, an updated screen data format, or a queried screen data format, which is not limited herein.
In one possible implementation, the concept database reflects the end-user's opinion of the data store, which is a comprehensive generalization of the user's needs. Illustratively, a concept database is generally expressed by a description of the database name and its contents: concept database identification, concept database name (information content description).
The logical database criteria is used in the system analysis designer's view to further decompose and refine the concept database. Illustratively, the logical database is represented in the following format: logical database identifier, logical database name (primary key, attribute table), primary key referring to using corresponding attribute identifier, multiple attribute identifiers are connected by plus sign, such as: the primary key represents a mechanism code, the attribute table represents a mechanism name, an establishment date, and a total number of persons, and the embodiment of the present application is not limited herein.
In the embodiment of the application, before the electrical engineering raw data is input into the model for automatic identification and extraction, the electrical engineering raw data can be converted into a computer programming language, so that the processing device 20 can better identify the electrical engineering raw data. Exemplarily, referring to fig. 6, before the processing of the electrical engineering raw data by the data extraction model mentioned above, the method further includes:
specifically, the first language refers to original data on a drawing or a chart described in chinese, and the first data element refers to original data of electrical engineering, which is composed of chinese characters, letters, and arabic numerals, which is not limited herein.
In one possible implementation, the data elements may be, for example, the size and cost of a single component, and the embodiments of the present application are not limited thereto. For example, the first language refers to raw data on electrical engineering drawings and diagrams represented in human-readable chinese.
specifically, the second language refers to raw data on electrical engineering drawings and charts which can be recognized and processed by a computer, and the second data element refers to that the raw data of the electrical engineering is represented by codes. Converting a first data element to a second data element refers to converting human readable text to computer recognizable and processable characters.
Specifically, all the second data elements are constructed into the corresponding data, and the construction refers to compiling characters into code statements. Illustratively, the second data element may be any one of Python or JAVA language, and the second language data refers to raw data compiled in the above programming language so as to be able to express the electrical engineering with respect to the component. It should be understood that although the various steps in the flow charts of fig. 2-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-6 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 7, there is provided an electrical engineering data processing apparatus including: an obtaining module 701, a data processing module 702, and a matching module 703. Wherein:
the acquisition module 701 is used for acquiring electrical engineering raw data, wherein the electrical engineering raw data comprises relevant parameters of electrical engineering components;
the data processing module 702 is configured to process the electrical engineering raw data by using a data extraction model to obtain digitized contribution data in the raw data;
and the matching module 703 is configured to perform rule matching processing on the digitized contribution data, and display the processed data.
In one embodiment, as shown in fig. 8, the obtaining module 701 includes: identifying unit 7011, removing unit 7012, wherein:
the identification unit 7011 is configured to identify the two-dimensional data related to the electrical engineering by using an optical character recognition algorithm OCR, and obtain a parameter related to a component in the two-dimensional data;
the removing unit 7012 is configured to remove an error text in the parameter related to the component in the two-dimensional data, and obtain the electrical engineering raw data.
In one embodiment, the removing unit 7012 is specifically configured to input parameters related to the component in the two-dimensional data into the classification model, and obtain the electrical engineering raw number according to an output of the classification model; the classification model is used for dividing the input text of the classification model into correct text and error text.
In one embodiment, as shown in FIG. 8, the data processing module 702 includes: a classification unit and an encoding unit, wherein:
a classification unit 7021, configured to classify the electrical engineering raw data according to component attributes to obtain component classification data;
and the encoding unit 7022 is configured to encode the component classification data, and perform data integration processing on the encoded data to obtain digitized contribution data.
In an embodiment, the classifying unit 7021 is specifically configured to obtain a description file of the plug-in; the plug-in is a function extension plug-in of a framework to which the component belongs, and the description file comprises information of a plug-in data packet and a plug-in class name; and loading the plug-in data packet according to the plug-in data packet information, instantiating the plug-in data packet according to the plug-in class name, and classifying the electrical engineering original data according to the classification attribute or classification algorithm in the plug-in data packet to obtain component classification data.
In an embodiment, the encoding unit 7022 is specifically configured to perform integration processing on the encoded data according to an electrical engineering standard integration framework.
In one embodiment, as shown in fig. 8, the electrical engineering data processing apparatus further includes a conversion module 703.
A conversion module 703, configured to split the funding data into a plurality of first data elements; the data type of the first data element is a basic data type of a first language; converting each first data element into a second data element, wherein the data type of the second data element is a basic data type of a second language; and constructing data corresponding to the second language according to all the second data elements. For specific limitations of the electrical engineering data processing apparatus, reference may be made to the above limitations of the electrical engineering data processing method, which are not described herein again. The various modules in the electrical engineering data apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the digital contribution data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an electrical engineering data processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring electrical engineering raw data, wherein the electrical engineering raw data comprises relevant parameters of electrical engineering components; processing the original data of the electrical engineering by using a data extraction model to obtain digital contribution data in the original data; and carrying out technical rule matching processing on the digital contribution data, and displaying the processed data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
recognizing two-dimensional data related to electrical engineering by using an optical character recognition algorithm (OCR) to obtain parameters related to components in the two-dimensional data; and removing error texts in parameters related to the components in the two-dimensional data to obtain the original data of the electrical engineering.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
inputting parameters related to the components in the two-dimensional data into a classification model, and obtaining an electrical engineering original number according to the output of the classification model; the classification model is used for dividing the input text of the classification model into correct text and error text.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
classifying the electrical engineering original data according to the component attributes to obtain component classification data; and coding the component classification data, and carrying out data integration processing on the coded data to obtain digital contribution data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a description file of the plug-in; the plug-in is a function extension plug-in of a framework to which the component belongs, and the description file comprises information of a plug-in data packet and a plug-in class name; and loading the plug-in data packet according to the plug-in data packet information, instantiating the plug-in data packet according to the plug-in class name, and classifying the electrical engineering original data according to the classification attribute and/or classification algorithm in the plug-in data packet to obtain component classification data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and carrying out integrated processing on the coded data according to an electrical engineering standard integrated system framework.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
splitting the funding data into a plurality of first data elements; the data type of the first data element is a basic data type of a first language; converting each first data element into a second data element, wherein the data type of the second data element is a basic data type of a second language; and constructing data corresponding to the second language according to all the second data elements.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for processing electrical engineering data, the method comprising:
acquiring electrical engineering raw data, wherein the electrical engineering raw data comprises relevant parameters of electrical engineering components;
processing the electrical engineering original data by using a data extraction model to obtain digital contribution data in the original data;
and performing technical rule matching processing on the digital contribution data, and displaying the processed data.
2. The method of claim 1, wherein the obtaining raw electrical engineering data comprises:
recognizing two-dimensional data related to electrical engineering by using an optical character recognition algorithm (OCR) to obtain parameters related to components in the two-dimensional data;
and removing error texts in parameters related to the components in the two-dimensional data to obtain the electrical engineering raw data.
3. The method of claim 2, wherein removing erroneous text in the component-related parameters in the two-dimensional data comprises:
inputting parameters related to components in the two-dimensional data into a classification model, and obtaining the original number of the electrical engineering according to the output of the classification model; the classification model is used for classifying the input text of the classification model into correct text and wrong text.
4. The method of claim 1, wherein the processing the electrical engineering raw data using a data extraction model comprises:
classifying the electrical engineering original data according to component attributes to obtain component classification data;
and coding the component classification data, and carrying out data integration processing on the coded data to obtain the digital contribution data.
5. The method of claim 4, wherein the classifying the electrical engineering raw data according to component attributes comprises:
acquiring a description file of the plug-in; the plug-in is a function extension plug-in of a framework to which the member belongs, and the description file comprises information of a plug-in data packet and a plug-in class name;
loading a plug-in data packet according to the plug-in data packet information, instantiating the plug-in data packet according to the plug-in class name, and classifying the electrical engineering original data according to the classification attribute or classification algorithm in the plug-in data packet to obtain component classification data.
6. The method according to claim 4, wherein the performing data integration processing on the encoded data comprises:
and carrying out integrated processing on the coded data according to an electrical engineering standard integrated system framework.
7. The method of claim 1, wherein prior to the processing the electrical engineering raw data with the data extraction model, the method further comprises:
splitting the funding data into a plurality of first data elements; the data type of the first data element is a basic data type of a first language;
converting each first data element into a second data element, wherein the data type of the second data element is a basic data type of a second language;
and constructing data corresponding to the second language according to all the second data elements.
8. An apparatus for processing electrical engineering data, the apparatus comprising:
the system comprises an acquisition module, a processing module and a control module, wherein the acquisition module is used for acquiring electrical engineering raw data which comprises relevant parameters of electrical engineering components;
the data processing module is used for processing the electrical engineering original data by using a data extraction model to obtain digital contribution data in the original data;
and the matching module is used for carrying out skill rule matching processing on the digital resource improving data and displaying the processed data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110954027.4A CN113887274A (en) | 2021-08-19 | 2021-08-19 | Method and device for processing electrical engineering data, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110954027.4A CN113887274A (en) | 2021-08-19 | 2021-08-19 | Method and device for processing electrical engineering data, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113887274A true CN113887274A (en) | 2022-01-04 |
Family
ID=79010806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110954027.4A Pending CN113887274A (en) | 2021-08-19 | 2021-08-19 | Method and device for processing electrical engineering data, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887274A (en) |
-
2021
- 2021-08-19 CN CN202110954027.4A patent/CN113887274A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284372B (en) | User operation behavior analysis method, electronic device and computer readable storage medium | |
| CN112818398B (en) | Data processing method and big data processing equipment for big data privacy protection | |
| CN107145516B (en) | Text clustering method and system | |
| CN108763380B (en) | Trademark identification retrieval method and device, computer equipment and storage medium | |
| CN112396049A (en) | Text error correction method and device, computer equipment and storage medium | |
| JP2019502979A (en) | Automatic interpretation of structured multi-field file layouts | |
| CN110866116A (en) | Policy document processing method and device, storage medium and electronic equipment | |
| CN112861648A (en) | Character recognition method and device, electronic equipment and storage medium | |
| CN110704880B (en) | Correlation method of engineering drawings | |
| RU2640322C2 (en) | Methods and systems of effective automatic recognition of symbols | |
| CN111582169A (en) | Image recognition data error correction method, device, computer equipment and storage medium | |
| CN113935880A (en) | Policy recommendation method, device, equipment and storage medium | |
| CN111104422B (en) | Training method, device, equipment and storage medium of data recommendation model | |
| CN114842982B (en) | Knowledge expression method, device and system for medical information system | |
| CN113887274A (en) | Method and device for processing electrical engineering data, computer equipment and storage medium | |
| CN115984886A (en) | Table information extraction method, device, equipment and storage medium | |
| CN115718807A (en) | Personnel relationship analysis method, device, equipment and storage medium | |
| CN115482075A (en) | Financial data anomaly analysis method and device, electronic equipment and storage medium | |
| CN114925125A (en) | Data processing method, device and system, electronic equipment and storage medium | |
| CN114943306A (en) | Intention classification method, device, equipment and storage medium | |
| CN114706886A (en) | Evaluation method and device, computer equipment and storage medium | |
| CN115034177A (en) | Presentation file conversion method, device, equipment and storage medium | |
| RU2582064C1 (en) | Methods and systems for effective automatic recognition of symbols using forest solutions | |
| CN114969467A (en) | Data analysis and classification method and device, computer equipment and storage medium | |
| CN113657279A (en) | Bill image layout analysis method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |