Electrical drawing data processing method and device, equipment, medium and product

Abstract

The embodiment of the invention provides an electrical drawing data processing method and device, equipment, a medium and a product, and is applied to the technical field of data processing. The method comprises the steps of obtaining to-be-processed electrical drawing data; the to-be-processed electrical drawing data comprises multiple pieces of drawing data; classifying the to-be-processed electrical drawing data through a pre-trained drawing data classification model to obtain a data category corresponding to each piece of drawing data in the to-be-processed electrical drawing data; the data category comprises image data, text data, table data, vector data and time sequence data; determining a storage channel of each piece of drawing data according to the data category corresponding to each piece of drawing data; and storing the drawing data into a drawing database based on the determined storage channel. The technical effect of improving the data management efficiency is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to an electrical drawing data processing method and device, equipment, medium and product. BACKGROUND

[0002] In the field of electrical engineering, electrical drawings are important basis for engineering design and construction. With the increase of project scale and complexity, the number and content of electrical drawings are increasingly numerous. In actual engineering, how to efficiently and accurately classify and manage the basic data of electrical drawings has become an important work.

[0003] In the prior art, the data management method for electrical drawings mainly includes: obtaining image data corresponding to the electrical drawings, generating an electronic drawing corresponding to each electrical drawing; obtaining a device code corresponding to each electronic drawing, establishing a mapping relationship between the device code and the electronic drawing, and generating a data storage path based on the mapping relationship to obtain a query identifier carrying the storage path; and performing data query and other operations on the electronic drawing and the device code by using the query identifier, so as to realize data management of the electrical drawings.

[0004] Since the existing technology mainly uses coding mapping to manage drawing data, there is a lack of data management in the subdivided field, which leads to the technical problem of low data management efficiency in the existing technology. SUMMARY

[0005] The electrical drawing data processing method, device, equipment, medium and product provided by the embodiments of the present application can improve the data management efficiency.

[0006] In a first aspect, the embodiments of the present application provide an electrical drawing data processing method, which includes:

[0007] Obtaining to-be-processed electrical drawing data; the to-be-processed electrical drawing data includes a plurality of drawing data;

[0008] Classifying the to-be-processed electrical drawing data by using a pre-trained drawing data classification model to obtain a data category corresponding to each drawing data in the to-be-processed electrical drawing data; the data category includes: image data, text data, table data, vector data and time series data;

[0009] Determining a storage channel of each drawing data according to the data category corresponding to each drawing data;

[0010] Storing the drawing data into a drawing database based on the determined storage channel.

[0011] In a possible implementation, the to-be-processed electrical drawing data is obtained, which includes:

[0012] Obtaining original electrical drawing data;

[0013] Preprocessing the original electrical drawing data to obtain to-be-processed electrical drawing data; wherein the preprocessing includes data screening, data verification, data unified standardization, data arrangement and integration, data conversion and mapping, and data source recording.

[0014] In a possible implementation, the method further includes:

[0015] Obtaining a data processing request;

[0016] According to the identity information in the data processing request, determining the permission information of the user;

[0017] Based on the permission information, determining the corresponding data processing application process;

[0018] Processing the data processing request according to the data processing application process.

[0019] In a possible implementation, processing the data processing request according to the data processing application process includes:

[0020] Judging whether the data processing request meets the data processing application process;

[0021] If it meets, executing the data processing request;

[0022] If it does not meet, sending warning information to the user to prompt the user to reinitiate the data processing request based on the data processing application process.

[0023] In a possible implementation, the method further includes:

[0024] Recording the processing process of the data processing request and generating a processing log.

[0025] In a possible implementation, after recording the processing process of the data processing request and generating a processing log, the method further includes:

[0026] Updating the drawing data classification model based on the processing log at a preset update period;

[0027] Wherein, the way to update the drawing data classification model includes at least any one of the following: the data volume increment of the drawing data in the drawing database reaches the data volume increment setting value, the running time of the drawing data classification model reaches the setting period, the cumulative amount of the processing log reaches the log setting value, and the accuracy of the drawing data classification model is lower than the preset accuracy threshold.

[0028] In a possible implementation, before obtaining the to-be-processed electrical drawing data, the method further includes:

[0029] Obtaining a data storage request;

[0030] obtaining user identity information in response to the data storage request;

[0031] verifying the user identity information to obtain a verification result;

[0032] Correspondingly, the electrical drawing data to be processed is obtained, including:

[0033] When the verification result is a verification pass, the electrical drawing data to be processed is obtained.

[0034] In a second aspect, an electrical drawing data processing apparatus is provided, including:

[0035] The obtaining module is configured to obtain electrical drawing data to be processed, wherein the electrical drawing data to be processed includes a plurality of drawing data.

[0036] The first processing module is configured to classify the electrical drawing data to be processed by using a pre-trained drawing data classification model to obtain a data category corresponding to each drawing data in the electrical drawing data to be processed, wherein the data category includes image data, text data, table data, vector data, and time series data.

[0037] The second processing module is configured to determine a storage channel of each drawing data according to the data category corresponding to each drawing data.

[0038] The third processing module is configured to store the drawing data into a drawing database based on the determined storage channel.

[0039] In a possible implementation, the apparatus further includes a fourth processing module configured to:

[0040] obtain a data processing request;

[0041] determine the user's permission information according to the identity information in the data processing request;

[0042] determine a corresponding data processing application process based on the permission information;

[0043] process the data processing request according to the data processing application process.

[0044] In a possible implementation, the fourth processing module is further configured to:

[0045] determine whether the data processing request conforms to the data processing application process;

[0046] if yes, execute the data processing request;

[0047] if no, send alert information to the user to prompt the user to reinitiate the data processing request based on the data processing application process.

[0048] In a possible implementation, the fourth processing module is further configured to:

[0049] record a processing procedure of the data processing request, and generate a processing log.

[0050] In a possible implementation, the fourth processing module is further configured to:

[0051] update the drawing data classification model based on the processing log in a preset update period;

[0052] The manner of updating the drawing data classification model at least includes any one of the following: a data amount increase amplitude of the drawing data in the drawing database reaches a data amount increase amplitude setting value, a running time of the drawing data classification model reaches a setting period, a cumulative amount of the processing log reaches a log setting value, and an accuracy of the drawing data classification model is lower than a preset accuracy threshold.

[0053] In a possible implementation, the apparatus further includes a fifth processing module configured to:

[0054] obtain a data storage request;

[0055] obtain user identity information in response to the data storage request;

[0056] verify the user identity information to obtain a verification result;

[0057] Correspondingly, the drawing data to be processed is obtained, including:

[0058] When the verification result is a verification pass, the drawing data to be processed is obtained.

[0059] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0060] The memory stores computer execution instructions;

[0061] The processor executes the computer execution instructions stored in the memory, so that the processor executes the first aspect and various possible implementation manners in the first aspect.

[0062] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions. When the computer execution instructions are executed by a processor, the computer execution instructions are used to implement the first aspect and various possible implementation manners in the first aspect.

[0063] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the computer program implements the first aspect and various possible implementation manners in the first aspect.

[0064] The electrical drawing data processing method, device, equipment, medium and product provided by the embodiment of the present application. The method obtains the to-be-processed electrical drawing data, classifies the multiple drawing data in the to-be-processed electrical drawing data by using the pre-trained drawing data classification model, determines the data category corresponding to each drawing data; the data category includes image data, text data, table data and time series data; the storage channel of each drawing data is determined according to the data category corresponding to the drawing data, so that each drawing data is stored in the database based on the storage channel. Compared with the prior art, the drawing data classification model trained by the present application is used to determine the drawing data category, and the mapping relationship between the category and the storage channel is used to determine the storage channel corresponding to each drawing data in the to-be-processed electrical drawing data, so that the multi-channel data storage is realized; the subsequent data access and calling can be realized quickly according to different data channels, so as to improve the data management efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0065] The drawings incorporated into the specification and forming a part thereof, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the present application.

[0066] Figure 1 Flowchart of the electrical drawing data processing method provided by the present application Figure 1 ;

[0067] Figure 2 Flowchart of the electrical drawing data processing method provided by the present application Figure 2 ;

[0068] Figure 3 Structure diagram of the electrical drawing data processing system provided by the present application;

[0069] Figure 4 Structure diagram of the electrical drawing data processing device provided by the present application;

[0070] Figure 5 Structure diagram of the electronic equipment provided by the present application.

[0071] Through the above drawings, the specific embodiments of the present application have been shown, and will be described in more detail in the following. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0072] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The following description is made with reference to the accompanying drawings in which like reference numerals designate identical or similar elements in the several figures. The implementations described in the following exemplary embodiments are not meant to represent all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the appended claims.

[0073] Firstly, the terms involved in the present application are explained:

[0074] Portable Document Format (PDF): refers to a document format for presenting documents, including the presentation of text, images, and vector graphics.

[0075] Drawing Exchange Format (dxf): refers to a data file format that allows data exchange between different drawing design programs, used to store two-dimensional and three-dimensional graphics data.

[0076] Template Drawing (dwt): used to save the style, layout and preset settings of the drawing file, which can be used as the basis for creating new drawings through dwt files to ensure that new files follow the same standards and formats.

[0077] Drawing (dwg): refers to a proprietary file format mainly used to store two-dimensional and three-dimensional drawing information.

[0078] In the prior art, the data management method for electrical drawings mainly includes: establishing a mapping relationship between the device code corresponding to the electrical drawing and the data of the electrical drawing, storing the mapping relationship, device code and electrical drawing data into a database, and determining the data storage path and query identifier according to the mapping relationship, thereby realizing electrical drawing data access and calling based on the storage path.

[0079] However, since the prior art mainly manages data for electrical drawings, in actual processing, electrical drawing data contains multiple data types, and if electrical drawing data needs to be managed, different types of data need to be processed; since the prior art focuses on the processing of text data, it lacks management of other types of data, thus resulting in the technical problem of low data management efficiency in the prior art.

[0080] To solve the above technical problems, the present application proposes the following technical concept: obtaining to-be-processed electrical drawing data, classifying the electrical drawing data by using a pre-trained drawing data classification model to obtain a data category corresponding to each drawing data, determining a storage channel of each drawing data according to the data category, and storing drawing data of different categories by using the storage channel. Compared with the prior art, the present application stores drawing data by using a classification storage method, and can quickly access and obtain data according to different types when calling and processing data, thereby achieving the technical effect of improving data management efficiency.

[0081] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described again in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0082] Figure 1 Flowchart of the electrical drawing data processing method provided by the present application Figure 1 As shown in the method, Figure 1 includes the following steps.

[0083] S101, obtaining to-be-processed electrical drawing data.

[0084] In this step, the to-be-processed electrical drawing data includes a plurality of drawing data.

[0085] Optionally, one possible implementation manner of obtaining to-be-processed electrical drawing data is as follows:

[0086] S1011, obtaining original electrical drawing data.

[0087] In this step, the original electrical drawing data includes but is not limited to design drawing data of electrical equipment or electrical system, element attribute data, element connection data, text annotation data, technical description information, and device information.

[0088] For example, the way of obtaining original electrical drawing data can be as follows:

[0089] Obtaining original design drawing data based on design source files of electrical equipment or electrical system; obtaining design drawing data and version history through a product life cycle management system; obtaining picture data and text data by scanning paper drawings; obtaining original electrical drawing data by analyzing PDF files; and obtaining original electrical drawing data by database calling.

[0090] S1012, preprocessing the original electrical drawing data to obtain to-be-processed electrical drawing data.

[0091] In this step, the preprocessing includes data screening, data verification, data uniform standardization, data arrangement and integration, data conversion and mapping, and data source recording. Preprocessing refers to converting raw electrical drawing data from different sources into a standard format, extracting key information from the drawing data, and converting it into a data format that can be used for classification. Through data screening, data verification, data uniform standardization, data arrangement and integration, data conversion and mapping, and data source recording, the quality of the data is ensured, and the subsequent data classification management is facilitated.

[0092] For example, the process of preprocessing can be:

[0093] a1, data screening: eliminate invalid data, retain core elements.

[0094] Specifically, delete the blank layers, decorative elements and low confidence information in the image data; eliminate invalid data in the text data, delete duplicate data, and supplement blank data and missing values.

[0095] a2, data verification: ensure the consistency of data logic.

[0096] Specifically, check the completeness of the line topology related to the equipment, the compliance of the line components, the rationality of the parameter range, and the text conflict in the text data.

[0097] For example: the link topology diagram of the electronic components of the electrical equipment needs to comply with the electrical principle, the components need to comply with the requirements, and the range of the related electrical parameters in the line needs to comply with the requirements. The identification information of the equipment cannot be repeated.

[0098] a3, data uniform standardization: eliminate the differences of multi-source data.

[0099] Specifically, unify the data units, such as the units of voltage data and current data; unify the naming conventions, such as using a unified naming format for equipment identification; unify the coordinate system, such as positioning the coordinate system of different source drawing data in the left title bar of the drawing, and using the same map scale for the drawing; unify the mapping relationship of the symbol library, such as matching and mapping the symbols of electronic equipment and electronic components from different sources with the symbols in the same standard library.

[0100] a4, data integration: the purpose is to associate scattered data elements.

[0101] For example: according to the project identification in the original electrical drawing data, the subsystems or sub-devices scattered in multiple drawings are aggregated into the same system; the symbol information, attribute information and device related connection line information corresponding to each electronic device are combined into a device object.

[0102] a5, data conversion and mapping: aims to generate classification data that machines can read.

[0103] Specifically: conversion is performed on vector diagrams, for example, devices in an electrical system can be nodes, and the connection relationship of the devices can be edges, thereby realizing the mapping of the electrical system and the drawing data.

[0104] Labeling is performed on different electrical devices, for example, a classification label is set for a sensor type device, and a classification label is set for a circuit breaker type device.

[0105] Establishing the blood relationship between data, tracking the flow of data, and determining the data blood relationship in the original electrical drawing data.

[0106] a6, data source recording: associating the original electrical drawing data and its corresponding data source, and labeling the data source in each piece of data, as well as the acquisition time of the data and the processing steps, thereby obtaining the to-be-processed electrical drawing data.

[0107] Optionally, before obtaining the to-be-processed electrical drawing data, identity information verification is also needed, and one possible implementation manner of the identity information verification is:

[0108] A1, obtaining a data storage request.

[0109] In this step, the manner of obtaining the data storage request includes but is not limited to:

[0110] The user clicks the button of uploading drawing data on the webpage to trigger data storage and send a data storage request; the data storage request of the user is obtained through message queue listening.

[0111] A2, obtaining user identity information in response to the data storage request.

[0112] In this step, the manner of obtaining the user identity information can be: extracting the user identity information from the data storage request; or querying the session information according to the data storage request, and extracting the user identity information from the session record; or based on the data storage request, initiating an identity verification prompt to the user, and obtaining the user identity information uploaded by the user based on the identity verification prompt.

[0113] A3, verifying the user identity information to obtain a verification result.

[0114] In this step, the manner of verifying the user identity information includes but is not limited to: account password verification, biometric identification, certificate verification, and multi-factor verification combining the above verification manners.

[0115] Exemplarily, the account password verification-based process can be as follows:

[0116] b1. Obtain account information and password information based on user identity information.

[0117] b2. Perform matching in a user database based on the account information to obtain original password information stored in the database.

[0118] b3. Calculate a hash value of the original password information and a hash value of the password information submitted by the user.

[0119] b4. When the two hash values are consistent, determine that the user identity information is legal, and when the two hash values are inconsistent, determine that the user identity information is illegal or the password is incorrect.

[0120] A4. When the verification result is a verification pass, obtain the to-be-processed electrical drawing data.

[0121] In this step, the purpose of obtaining the to-be-processed electrical drawing data after the verification pass is to safely load the original drawing data.

[0122] Exemplarily, the manner of obtaining the to-be-processed electrical drawing data is as follows: extracting the to-be-processed electrical drawing data from a data storage request of the user; or extracting drawing address information from the data storage request, and obtaining the to-be-processed electrical drawing data based on the drawing address information.

[0123] S102. Classify the to-be-processed electrical drawing data by using a pre-trained drawing data classification model to obtain a data category corresponding to each drawing data in the to-be-processed electrical drawing data.

[0124] In this step, the data category includes image data, text data, table data, vector data, and time series data.

[0125] Optionally, the pre-trained drawing data classification model is trained by using a deep learning algorithm, and one possible implementation manner of the model training is as follows:

[0126] S1021. Collect historical data related to electrical drawings, and convert the historical data into a format suitable for neural network input by using data preprocessing to obtain sample training data.

[0127] S1022. Train an initial neural network model based on the sample training data to obtain a to-be-determined drawing data classification model.

[0128] In this step, the initial neural network model is composed of a convolution layer, a full connection layer, and an output layer, wherein, in the calculation of the convolution layer; assuming that the input sample training data is a(0), the first layer is a convolution layer, and the linear combination value of the positions of k features of the layer is calculated as shown in formula 1:

[0129]

[0130] wherein, denotes the activation value of the previous layer, denotes the weight of the convolution kernel of the lth layer, m and n denote the spatial position, c denotes the input channel, and k denotes the output channel; denotes the bias vector of the lth layer; denotes the linear combination value of the lth layer.

[0131] After obtaining the linear combination value, the activation value is calculated based on the activation function, as shown in Equation 2:

[0132]

[0133] wherein, denotes the activation value of the lth layer, denotes the activation function. The purpose of activation is to enhance the expression ability of features and retain positive activation.

[0134] After processing by multiple convolution layers and pooling layers, the data is flattened into a one-dimensional vector and input into the fully connected layer. Assuming that the current processing is the lth fully connected layer, the input is the activation value of the previous layer, and the fully connected layer is as shown in Equation 3:

[0135]

[0136] wherein, a l-1 denotes the activation value of the previous layer, W l denotes the weight matrix of the lth fully connected layer, b l denotes the bias vector of the lth fully connected layer; Z l denotes the linear combination value of the lth layer.

[0137] Based on the linear combination value, the activation value is calculated, and the calculated activation value can represent the classification probability of the data, as shown in Equation 4:

[0138]

[0139] wherein, Z l denotes the linear combination value of the lth layer, a l denotes the activation value of the lth fully connected layer, i.e., the class probability vector; denotes the activation function of the fully connected layer.

[0140] The third layer is the output layer, which is used for normalization processing or maximum value extraction on the class probability vector to obtain the classification result of the input sample training data.

[0141] S1023, loss value calculation is performed based on the to-be-determined drawing data classification model. When the loss value is lower than a preset value, or the number of iterations reaches a preset upper limit value, or the performance of the model tends to be stable, the model training can be stopped, and the to-be-determined drawing data classification model is determined as the target drawing data classification model.

[0142] In this step, after the loss value is calculated, if it is still needed to enter the next round of iteration training, gradient optimization calculation based on the loss value is needed, as shown in formula 5:

[0143]

[0144] wherein, W l refers to a weight matrix, b l refers to a bias vector, refers to a loss value, refers to a learning rate; refers to the gradient of the loss value to the weight, refers to the gradient of the loss value to the bias vector.

[0145] In the model training process, a dynamic optimization method is also used to continuously adjust the training strategy, for example, adjusting the learning rate, training batch size and data enhancement method in the training. The dynamic optimization is shown in formula 6:

[0146]

[0147] wherein, s refers to the current state, for example, model confidence, system resources and input data complexity; a refers to the selectable optimization action, R refers to the reward value calculated according to the processing speed and accuracy, V refers to the value function, i.e., the optimal strategy calculated; γ is a discount factor, which is a weight for balancing the current reward value and the future reward value; P refers to the future reward value.

[0148] It should be noted that the data classification can also be realized by a pre-set classification rule, and the classification rule can be customized and modified by the management personnel.

[0149] S103, according to the data category corresponding to each drawing data, the storage channel of each drawing data is determined.

[0150] In this step, the drawing data of different categories includes but is not limited to:

[0151] The image data specifically includes primary diagrams, secondary diagrams, device layout diagrams, and wiring connection diagrams of the system; the text data specifically includes text of drawing descriptions, device parameter descriptions, and device operation manual texts; the table data specifically includes device list data, connection table data, and material list data; the vector data specifically includes dwg drawing files, dxf files, dwt files, and graphics data; and the time series data specifically includes device construction progress plan data, device maintenance data, and device repair record data.

[0152] For example, the image data can be stored in an object storage or by using a distributed file system; the primary diagram in the image data refers to a topology diagram of a main circuit, and the secondary diagram refers to a topology diagram of a control protection circuit. The text data can be stored in a time series database or a vector database; the table data can be stored in a relational database or a graph database; the vector data can be stored in a spatial database; and the time series data can be stored in a time series database.

[0153] In S104, the drawing data is stored in the drawing database based on the determined storage channel.

[0154] In this step, the storage channel includes a database type used and a storage path of the database; the drawing data is stored in the drawing database, and it is determined whether the storage is successful; if it is determined that the storage is successful, a storage identifier is generated; if the storage fails, a data storage request is reinitiated to the drawing database until the storage is successful.

[0155] Optionally, after the drawing data is stored in the corresponding drawing database, the drawing data can also be recorded in the meta-database, and the identifier of each data item, the data category, the storage location, the project to which the data belongs, and the data storage time are stored.

[0156] For example, when the image data is stored, if the current image data is image data that needs to be accessed frequently, the image data can be stored in a memory database to facilitate frequent access; if the image data is data that needs to be stored for a long time, the image data can be stored in a cold storage system.

[0157] The electrical drawing data processing method provided in this application involves acquiring electrical drawing data to be processed, using a pre-trained drawing data classification model to classify multiple drawing data within the data, and determining the data category corresponding to each drawing data. Data categories include image data, text data, tabular data, and time-series data. Based on the data category, the storage channel for each drawing data is determined, and each drawing data is stored in a database based on the storage channel. Compared to existing technologies, this application utilizes a pre-trained drawing data classification model to determine the drawing data category. Based on the mapping relationship between categories and storage channels, the storage channel corresponding to each drawing data in the electrical drawing data to be processed is determined, thereby achieving multi-channel data storage. This facilitates rapid data access and retrieval based on different data channels during subsequent data access and retrieval, thus improving data management efficiency.

[0158] Figure 2 Flowchart of the electrical drawing data processing method provided in this application Figure 2 ,like Figure 3 As shown, the method includes:

[0159] S201, Obtain data processing request.

[0160] In this step, a data processing request refers to a request to further process the data in the drawing database, including but not limited to: data storage, data deletion, data modification, and data retrieval.

[0161] S202. Determine the user's permission information based on the identity information in the data processing request.

[0162] In this step, the user's permission information is the permission information assigned to the user during registration. The permission information is related to the user's identity: the super administrator has the highest privileges and can access and manage all data and functions; the administrator has full system privileges and can manage users and assign permissions; the advanced user has medium privileges and can access and operate more data and functions; the ordinary user has basic privileges and can only access and operate limited data; the visitor has only limited access permissions.

[0163] For example, the method to determine a user's permission information can be: obtaining the identity information in the data processing request, determining the user's identity type based on the identity information, and determining the user's permission information based on the mapping relationship between the identity type and the permission information.

[0164] S203. Based on the permission information, determine the corresponding data processing application process.

[0165] In this step, the data processing procedure refers to identity verification and permission verification based on the identity information and the permission information of the user. This step can also be implemented in the stage of determining the permission information of the user. After it is determined that the identity verification and the permission verification are both passed, data screening and filtering need to be performed based on the permission level represented by the permission information, so as to ensure that the user can only process data within the permission range. After the data screening, the data processing request of the user is executed based on the screened data.

[0166] S204. Processing the data processing request according to the data processing application procedure.

[0167] Optionally, one possible implementation manner of processing the data processing request is as follows:

[0168] S2041. Determining whether the data processing request conforms to the data processing application procedure.

[0169] In this step, verifying whether the data processing request conforms to the data processing application procedure based on the data processing request refers to verifying the legality of the identity information of the user, specifically verifying whether the user belongs to a registered legal user; verifying the legality of the permission information of the user, specifically verifying whether the permission information of the user conforms to the user type of the user; verifying whether the data processing request is within the allowed range of the permission information, specifically verifying whether the data access, data calling, data modification and other data processing requests submitted by the user are within the permission range of the user; and verifying the legality of the procedure of the data processing request submitted by the user, specifically verifying whether the operation procedure of the user is consistent with the data processing application procedure.

[0170] S2042. If the data processing request conforms to the data processing application procedure, executing the data processing request.

[0171] In this step, when it is determined that the data processing request of the user conforms to the data processing application procedure, the drawing data screened according to the permission information of the user is used to execute the data processing request.

[0172] For example, when the data processing request indicates that data modification is needed, the target data to be modified is located based on the data processing request, the data processing request is executed to modify the target data, and the modified target data is updated to the drawing database.

[0173] S2043. If the data processing request does not conform to the data processing application procedure, sending alert information to the user to prompt the user to reinitiate the data processing request based on the data processing application procedure.

[0174] In this step, when it is determined that the data processing request of the user does not conform to the data processing application process, the user needs to be sent warning information. If the user sends a data processing request according to the data processing application process after receiving the warning information, the data processing request is executed normally. If the data processing requests sent by the user do not conform to the data processing application process for multiple times, the data processing request initiated by the user can be limited by limiting the request frequency, limiting the request times, and limiting the request time, so as to avoid the reception of high-frequency error requests in a short period of time.

[0175] S205, record the processing process of the data processing request, and generate a processing log.

[0176] In this step, the data processing process recorded in the request log includes but is not limited to: data source information, processing step record, data quality index, resource consumption information, processing exception and error, and processing final output information.

[0177] The data source information includes: data source identification, data acquisition time, and version information corresponding to the data; the processing step record includes: parameters of each processing operation, operation start and end time, and operation execution state; the data quality index refers to: data statistical information before and after processing, data distribution change, or data abnormal value information; the processing exception and error include: error type, error step, and error corresponding processing mode; the output information includes: storage location of processed data, whether data mode is changed, and whether data quality index is qualified.

[0178] S206, in a preset update period, update the drawing data classification model based on the processing log.

[0179] In this step, the way to update the drawing data classification model includes at least any one of the following: the data volume increment of the drawing data in the drawing database reaches the data volume increment setting value, the running time of the drawing data classification model reaches the setting period, the cumulative amount of the processing log reaches the log setting value, and the accuracy of the drawing data classification model is lower than the preset accuracy threshold.

[0180] For example, when updating the drawing data classification model, the gradient descent algorithm can be iteratively optimized. The optimization process can be:

[0181] S1061, initialize the parameter vector, initialize the first-order momentum gradient mean, and initialize the second-order momentum gradient square mean; set the hyperparameters, including the learning rate, the first-order momentum decay rate, the second-order momentum decay rate, and the constant term.

[0182] In this step, the first-order momentum and the second-order momentum can be initialized to 0 in the initialization process, as shown in formula 7:

[0183]

[0184] wherein m0 refers to the first-order momentum and v0 refers to the second-order momentum.

[0185] S1062, a prediction output of the current drawing data classification model is calculated through forward propagation, and a loss function value is calculated based on the prediction output and a real data label.

[0186] S1063, a gradient value of the loss function value with respect to a parameter vector is calculated through back propagation, and a gradient vector is obtained.

[0187] S1064, the first-order momentum and the second-order momentum are updated based on the gradient vector.

[0188] In this step, the way of updating the first-order momentum and the second-order momentum is shown in formula 8:

[0189]

[0190] wherein m t refers to the updated first-order momentum, v t refers to the updated second-order momentum, β1 refers to the first-order momentum decay rate, β2 refers to the second-order momentum decay rate; ▽θL(θ) refers to the gradient vector, L(θ) refers to the loss function value; and θ refers to the parameter vector.

[0191] S1065, the updated first-order momentum and the updated second-order momentum are corrected for deviation, and the corrected first-order momentum and the corrected second-order momentum are obtained.

[0192] In this step, the way of deviation correction is shown in formula 9:

[0193]

[0194] wherein , respectively refer to the t-th power of the first-order momentum decay rate and the second-order momentum decay rate, and the correction factor will gradually approach 1 as the number of iterations increases; and respectively refer to the corrected first-order momentum and the corrected second-order momentum; m t and v t respectively refer to the updated first-order momentum and the updated second-order momentum.

[0195] S1066, the parameter vector is updated based on the corrected first-order momentum and the corrected second-order momentum.

[0196] In this step, the way of updating the parameter vector is shown in formula 10:

[0197]

[0198] in, This refers to the updated parameter vector. and These refer to the corrected first-order momentum and second-order momentum, respectively; α refers to the learning rate. This refers to the constant term.

[0199] S1067. Based on the hyperparameters and the updated parameter vector, update the current drawing data classification model.

[0200] Figure 3 A schematic diagram of the electrical drawing data processing system provided in this application is shown below. Figure 4 As shown, the system includes:

[0201] The data receiving module 301 is used to receive the user's identity information, verify identity based on password verification and face matching, and obtain the original drawing data after successful verification.

[0202] The data preprocessing module 302 is used to preprocess the original drawing data, convert the original drawing data from different sources into the format required by the system, extract key information from the drawings, and convert it into a data format that can be used for classification. Through a series of operations such as data filtering, data verification, data standardization, data integration, data conversion and mapping, and data source recording, high-quality preprocessed data is obtained.

[0203] The data recognition and classification module 303 is used to classify preprocessed data based on a pre-trained drawing data classification model to obtain the data categories of the preprocessed data. Specifically, the data classification includes image data, text data, tabular data, vector data, and time series data. Deep learning algorithms are used to gradually improve the system's efficiency in data classification.

[0204] The multi-channel storage module 304 is used to determine the corresponding data storage channel according to different data categories and to realize data storage based on the data storage channel. Among them, image data, text data, tabular data, vector data, and time series data are stored in their respective system locations through corresponding data storage channels, avoiding data confusion caused by unified storage on a single channel, which could lead to data errors and unusable data, and ensuring data validity.

[0205] The management permission allocation module 305 is used to divide the system's management into corresponding management layers and determine the corresponding permission information for different types of users through permission allocation. Permission allocation can effectively ensure system security and data integrity, and improve system manageability and efficiency.

[0206] The hierarchical retrieval module 306 is used to define the flow of data request and retrieval, and ensure that the user obtains data according to the permission information. At the same time, the user's data retrieval request and operation behavior are recorded, which is convenient for subsequent audit and analysis. By defining the access permission level, data classification and grading, optimizing the data retrieval process and implementing security measures, the system can efficiently and safely provide the required data for different users.

[0207] The optimization analysis module 307 is used to periodically optimize and improve the data receiving input, data processing, data classification, data storage, management permission allocation and data retrieval of the system according to the records and feedback of the system data; at the same time, the optimization of the drawing data classification model can be carried out according to the log record information of the data processing process.

[0208] Figure 4 The structural schematic diagram of the electrical drawing data processing device provided in the present application is shown in Figure 5 The electrical drawing data processing device provided in the present embodiment comprises:

[0209] The acquisition module 401 is used to acquire the electrical drawing data to be processed; the electrical drawing data to be processed comprises a plurality of drawing data.

[0210] The first processing module 402 is used to classify the electrical drawing data to be processed by using the pre-trained drawing data classification model, so as to obtain the data category corresponding to each drawing data in the electrical drawing data to be processed; the data category comprises image data, text data, table data, vector data and time series data.

[0211] The second processing module 403 is used to determine the storage channel of each drawing data according to the data category corresponding to each drawing data.

[0212] The third processing module 404 is used to store the drawing data into the drawing database based on the determined storage channel.

[0213] In a possible implementation, the device further comprises a fourth processing module 405, which is used to:

[0214] Acquire a data processing request.

[0215] Determine the permission information of the user according to the personal information in the data processing request.

[0216] Determine the corresponding data processing application flow based on the permission information.

[0217] Process the data processing request according to the data processing application flow.

[0218] In a possible implementation, the fourth processing module 405 is further used to:

[0219] determine whether the data processing request meets the data processing application procedure.

[0220] if yes, execute the data processing request.

[0221] if no, send alert information to the user to prompt the user to re-initiate the data processing request based on the data processing application procedure.

[0222] In a possible implementation, the fourth processing module 405 is further configured to:

[0223] record the processing procedure of the data processing request and generate a processing log.

[0224] In a possible implementation, the fourth processing module 405 is further configured to:

[0225] update the drawing data classification model based on the processing log at a preset update period.

[0226] The manner of updating the drawing data classification model at least includes any one of the following: the data volume increment of the drawing data in the drawing database reaches a data volume increment setting value, the running time of the drawing data classification model reaches a setting period, the cumulative amount of the processing log reaches a log setting value, and the accuracy of the drawing data classification model is lower than a preset accuracy threshold.

[0227] In a possible implementation, the apparatus further includes a fifth processing module 406 configured to:

[0228] obtain a data storage request.

[0229] obtain user identity information in response to the data storage request.

[0230] verify the user identity information to obtain a verification result.

[0231] correspondingly, obtain the to-be-processed electrical drawing data, including.

[0232] obtain the to-be-processed electrical drawing data when the verification result is passed.

[0233] The apparatus provided in this embodiment can execute the method provided in the method embodiment, and has similar implementation principles and technical effects, which will not be described here in detail.

[0234] Figure 5 The apparatus provided in this embodiment is a structural schematic diagram of an electronic device. As shown in ​ The apparatus provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the apparatus further includes a communication component 503. The processor 501, the memory 502, and the communication component 503 are connected through a bus 504.

[0235] In the implementation process, the at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that the at least one processor 501 executes the above-mentioned electrical drawing data processing method or method.

[0236] The specific implementation process of the processor 501 can refer to the method embodiments described above, which have similar implementation principles and technical effects, and will not be described here in detail.

[0237] In the above embodiments, it should be understood that the processor can be a central processing unit (English: Central Processing Unit, for short: CPU), and can also be other general-purpose processors, digital signal processors (English: Digital Signal Processor, for short: DSP), application specific integrated circuits (English: Application Specific Integrated Circuit, for short: ASIC), etc. The general-purpose processor can be a microprocessor, or the processor can be any conventional processor, etc. The steps of the method disclosed in combination with the application can be directly embodied as hardware processor execution, or executed by hardware and software modules in the processor.

[0238] The memory can include a random access memory (Random Access Memory, RAM), and can also include a non-volatile memory (Non-volatile Memory, NVM), for example, at least one disk memory.

[0239] The bus can be an industry standard architecture (Industry Standard Architecture, ISA) bus, a peripheral component interconnect (Peripheral Component, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present application does not limit only one bus or one type of bus.

[0240] The present application also provides a computer program product, comprising a computer program, which is executed by the processor to realize the above-mentioned method.

[0241] The present application also provides a computer readable storage medium, which stores computer-executable instructions, and when the processor executes the computer-executable instructions, the above-mentioned method is realized.

[0242] The above-mentioned readable storage medium can be realized by any type of volatile or nonvolatile storage devices or their combinations, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0243] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the device.

[0244] The division of units is only a logical functional division, and in actual implementation, there can be another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0245] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0246] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0247] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0248] Those of ordinary skill in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction-related hardware. The aforementioned program can be stored in a computer readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed, and the aforementioned storage medium includes a ROM, a RAM, a magnetic disk or an optical disk, and various media that can store program codes.

[0249] Finally, it should be noted that those of ordinary skill in the art, after considering the specification and practicing the application disclosed herein, will easily think of other embodiments of the present application. The present application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or conventional technical means in the art that are not disclosed in the present application, and is not limited to the precise structures described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present application is only limited by the appended claims.

Claims

1. A method for processing electrical drawing data, characterized in that, include: Obtain the electrical drawing data to be processed; The electrical drawing data to be processed includes multiple drawing data; The electrical drawing data to be processed is classified using a pre-trained drawing data classification model to obtain the data category corresponding to each drawing data in the electrical drawing data to be processed; the data categories include: image data, text data, tabular data, vector data, and time series data; The storage channel for each drawing data is determined based on the data category corresponding to each drawing data. Based on the determined storage channel, the drawing data is stored in the drawing database.

2. The method according to claim 1, characterized in that, The acquisition of electrical drawing data to be processed includes: Obtain the original electrical drawing data; The original electrical drawing data is preprocessed to obtain the electrical drawing data to be processed; wherein, the preprocessing includes data filtering, data verification, data standardization, data organization and integration, data conversion and mapping, and data source recording.

3. The method according to claim 1, characterized in that, The method further includes: Get data processing request; Based on the identity information in the data processing request, determine the user's permission information; Based on the aforementioned permission information, the corresponding data processing request process is determined; The data processing request is processed according to the data processing application process.

4. The method according to claim 3, characterized in that, The step of processing the data processing request according to the data processing request process includes: Determine whether the data processing request conforms to the data processing application process; If the conditions are met, the data processing request will be executed; If the request does not meet the requirements, a warning message will be sent to the user to prompt the user to re-initiate the data processing request based on the data processing application process.

5. The method according to claim 4, characterized in that, The method further includes: Record the processing of the data processing request and generate a processing log.

6. The method according to claim 5, characterized in that, After recording the processing of the data processing request and generating a processing log, the method further includes: The drawing data classification model is updated based on the processing log at a preset update cycle; The method of updating the drawing data classification model includes at least one of the following: the increase in the amount of drawing data in the drawing database reaches a set value; the running time of the drawing data classification model reaches a set period; the accumulated amount of the processing log reaches a set value; and the accuracy of the drawing data classification model is lower than a preset accuracy threshold.

7. The method according to claim 1, characterized in that, Before acquiring the electrical drawing data to be processed, the method further includes: Get data storage request; In response to the data storage request, obtain user identity information; The user's identity information is verified to obtain the verification result; Accordingly, acquiring the electrical drawing data to be processed includes: When the verification result is successful, the electrical drawing data to be processed is obtained.

8. An electrical drawing data processing device, characterized in that, include: The acquisition module is used to acquire electrical drawing data to be processed; The electrical drawing data to be processed includes multiple drawing data; The first processing module is used to classify the electrical drawing data to be processed using a pre-trained drawing data classification model to obtain the data category corresponding to each drawing data in the electrical drawing data to be processed; the data category includes: image data, text data, tabular data, vector data, and time series data; The second processing module is used to determine the storage channel for each drawing data according to the data category corresponding to each drawing data. The third processing module is used to store the drawing data into the drawing database based on the determined storage channel.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images