Power equipment nameplate information extraction method and related device

Abstract

The invention belongs to the technical field of power systems, and discloses a power equipment nameplate information extraction method and a related device, and the method comprises the steps: extracting nameplate text contents of a power equipment nameplate in rows; traversing a pre-established unconventional nameplate template library by utilizing the nameplate text content, wherein the unconventional nameplate template library comprises a plurality of unconventional nameplate templates marked with different supplier name-equipment name tags; when the nameplate text content contains content matched with the supplier name-equipment name tag, calling an unconventional nameplate template corresponding to the matched tag, and filling the called unconventional nameplate template with the nameplate text content to obtain power equipment nameplate information; when the nameplate text content does not contain the content matched with the supplier name-equipment name label, the nameplate text content is the power equipment nameplate information. The invention aims to effectively extract the structured information from various complex nameplates.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power systems, and in particular relates to a method for extracting nameplate information of electric power equipment and a related device. Background Art

[0002] With the booming power industry, the number of power equipment is growing rapidly. The efficient management and maintenance of these equipment is not only the key to ensuring the stable operation of the power grid, but also an important factor in improving the quality and efficiency of power supply. The equipment nameplate, as an indispensable information identification of power equipment, carries a series of key data such as the equipment model, specification parameters, production date, etc. These data play a vital role in the full life cycle management, troubleshooting and preventive maintenance of the equipment.

[0003] The traditional way of reading equipment nameplate information relies on manual operation, which is not only inefficient but also prone to errors. Especially when faced with a large number of equipment, the difficulty and cost of manual management increase significantly. In recent years, with the rapid development of information technology, optical character recognition (OCR) technology has been widely used in the field of nameplate recognition and information extraction due to its high efficiency and accuracy. OCR technology can automatically recognize and extract text information from images, greatly improving the efficiency and accuracy of information processing and bringing convenience to power equipment management. Although OCR technology has made progress in the field of nameplate recognition, it still faces many challenges in practical applications. Since equipment nameplates from different manufacturers often have different structural characteristics, especially when the text structure of the nameplate is complex or irregular, the accuracy of its recognition cannot meet industry needs. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a method for extracting nameplate information of electric equipment and a related device, the purpose of which is to effectively extract structured information from various complex nameplates.

[0005] In order to solve the above technical problems, the present invention is implemented by the following technical solutions: According to a first aspect of the present invention, a method for extracting nameplate information of electric equipment is provided, comprising: Extract the nameplate text content of the power equipment nameplate by line; Using the nameplate text content, traversing a pre-established unconventional nameplate template library, the unconventional nameplate template library includes a plurality of unconventional nameplate templates marked with different supplier name-equipment name labels; When the nameplate text content contains content that matches the supplier name-equipment name tag, calling the unconventional nameplate template corresponding to the matching tag, and using the nameplate text content to fill the called unconventional nameplate template to obtain the power equipment nameplate information; When the nameplate text content does not contain content that matches the supplier name-equipment name label, the nameplate text content is the electric equipment nameplate information.

[0006] In a possible implementation manner of the first aspect, extracting nameplate text content of the electric power equipment nameplate row by row includes: Get the nameplate image of the power equipment; Using an OCR algorithm to traverse the electric power equipment nameplate image line by line to extract the nameplate text content; After traversing the last text block of each line, a line break traversal is performed until the electric equipment nameplate image is traversed.

[0007] In a possible implementation of the first aspect, when the OCR algorithm is used to traverse the electric power equipment nameplate image row by row to extract the nameplate text content, it also includes: When traversing the same line, if the character interval between adjacent text blocks exceeds the preset character interval, a separator is added between adjacent text blocks.

[0008] In a possible implementation of the first aspect, the unconventional nameplate template is constructed based on the actual power equipment nameplate corresponding to the supplier name-equipment name, and the unconventional nameplate template includes a fixed text block and a text filling area that has a unique positional relationship with the fixed text block.

[0009] In a possible implementation manner of the first aspect, the unconventional nameplate template that is called by filling the nameplate text content is specifically: comparing the nameplate text content with the fixed text block in the unconventional nameplate template; According to the comparison result, the information in the nameplate text content is filled into the text filling area.

[0010] In a possible implementation manner of the first aspect, the unconventional nameplate is a nameplate of the electric power equipment on which text is not arranged in a regular row pattern.

[0011] According to a first aspect of the present invention, there is provided a device for extracting nameplate information of electric equipment, comprising: An extraction module, used for extracting the nameplate text content of the power equipment nameplate by line; A traversal module, used to traverse a pre-established unconventional nameplate template library using the nameplate text content, wherein the unconventional nameplate template library includes a plurality of unconventional nameplate templates marked with different supplier name-equipment name labels; A calling and filling module is used to call the unconventional nameplate template corresponding to the matching tag when the nameplate text content contains content matching the supplier name-equipment name tag, and fill the called unconventional nameplate template with the nameplate text content to obtain the electric power equipment nameplate information; A determination module is used to determine that, when the nameplate text content does not contain content that matches the supplier name-equipment name label, the nameplate text content is the electric equipment nameplate information.

[0012] In a possible implementation manner of the second aspect, the extraction module is specifically configured to: Get the nameplate image of the power equipment; Using an OCR algorithm to traverse the electric power equipment nameplate image line by line to extract the nameplate text content; After traversing the last text block of each line, a line break traversal is performed until the electric equipment nameplate image is traversed.

[0013] In a possible implementation of the second aspect, when the OCR algorithm is used to traverse the electric power equipment nameplate image line by line to extract the nameplate text content, it also includes: When traversing the same line, if the character interval between adjacent text blocks exceeds the preset character interval, a separator is added between adjacent text blocks.

[0014] In a possible implementation of the second aspect, the unconventional nameplate template is constructed based on the actual power equipment nameplate corresponding to the supplier name-equipment name, and the unconventional nameplate template includes a fixed text block and a text filling area that has a unique positional relationship with the fixed text block.

[0015] In a possible implementation manner of the second aspect, the unconventional nameplate template that is called by filling the nameplate text content is specifically: comparing the nameplate text content with the fixed text block in the unconventional nameplate template; According to the comparison result, the information in the nameplate text content is filled into the text filling area.

[0016] According to a third aspect of the present invention, there is provided a device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for extracting nameplate information of electric equipment when executing the computer program.

[0017] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the method for extracting nameplate information of electric equipment.

[0018] Compared with the prior art, the present invention has at least the following beneficial effects: The present invention provides a method for extracting nameplate information of electric equipment. First, the nameplate text content of the nameplate of the electric equipment is extracted row by row, and then the nameplate text content is used to traverse a pre-established unconventional nameplate template library. When the nameplate text content contains content that matches the supplier name-equipment name tag, the unconventional nameplate template corresponding to the matching tag is called, and the called unconventional nameplate template is filled with the nameplate text content to obtain the nameplate information of the electric equipment; when the nameplate text content does not contain content that matches the supplier name-equipment name tag, the nameplate text content is the nameplate information of the electric equipment. It can be seen that the present invention can quickly obtain the nameplate information of the electric equipment by extracting the nameplate text content by row and matching the template, and through the pre-established unconventional nameplate template library, it can accurately extract information for nameplates with different structural characteristics, avoiding the recognition errors that may occur in traditional OCR technology when facing complex or irregular nameplates, and can effectively extract structured information from various complex nameplates, thereby improving the accuracy of information extraction.

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the specific implementation modes of the present invention, the drawings required for use in the description of the specific implementation modes will be briefly introduced below. Obviously, the drawings described below are some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 This is a flow chart of a method for extracting nameplate information of electric equipment according to an embodiment of the present invention; Figure 2 The present invention is a block diagram of a device for extracting nameplate information of electric equipment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] like Figure 1As shown, an embodiment of the present invention provides a method for extracting nameplate information of electric equipment. In order to overcome the problem of insufficient recognition accuracy of existing OCR technology when processing complex or irregular nameplate text structures, this method introduces an unconventional nameplate template library to achieve efficient and accurate extraction of nameplate information of various types of electric equipment. The following are the specific implementation steps of the method for extracting nameplate information of electric equipment in this embodiment: Step 1: Extract the nameplate text content of the power equipment nameplate by row.

[0024] Specifically, first, use a high-definition image acquisition device (such as a digital camera or a smartphone camera) to take a picture of the nameplate of the power equipment to ensure that the image is clear and unblurred. Then, preprocess the image through image processing technology (such as grayscale, binarization, denoising, etc.) to improve the accuracy of character recognition. Then, use the text line detection algorithm in OCR technology to scan the preprocessed image line by line to identify and extract the text content of each line. The output of this step is a string array containing multiple lines of text content, and each line of text corresponds to a line of information on the nameplate.

[0025] Step 2: Use the nameplate text content to traverse a pre-established unconventional nameplate template library, wherein the unconventional nameplate template library includes a variety of unconventional nameplate templates marked with different supplier name-equipment name labels.

[0026] That is, the unconventional nameplate template library contains a variety of power equipment nameplate templates with specific structural characteristics provided by different suppliers. Each unconventional nameplate template is marked with a unique supplier name-equipment name tag to identify the supplier and equipment type to which the unconventional nameplate template belongs.

[0027] It should be noted that when establishing a template library, it is necessary to collect a large number of power equipment nameplate samples from different suppliers, manually annotate each sample, extract its text structure and key information points, and then build the corresponding unconventional nameplate template based on these information points.

[0028] After extracting the nameplate text content, the system starts to traverse the unconventional nameplate template library. For each unconventional nameplate template in the library, the system checks whether the nameplate text content contains the supplier name-device name label corresponding to the unconventional nameplate template. Exemplarily, this operation can be implemented by a string matching algorithm (such as KMP algorithm, Boyer-Moore algorithm, etc.) to improve matching efficiency.

[0029] It should be understood that the unconventional nameplate template library in this embodiment can be updated at any time. With the emergence of new suppliers and new equipment, users can manually add new unconventional nameplate templates to the template library to ensure that all types of power equipment nameplates can be identified.

[0030] Step 3: When the nameplate text contains content that matches the supplier name-equipment name tag, call the unconventional nameplate template corresponding to the matching tag, and use the nameplate text content to fill in the called unconventional nameplate template to obtain the power equipment nameplate information.

[0031] That is to say, this step calls the matching unconventional nameplate template and fills in the information. When the nameplate text content contains content that matches the supplier name-equipment name label of an unconventional nameplate template, the system considers that an unconventional nameplate template matching the current nameplate has been found. Next, the system parses and reorganizes the nameplate text content according to the text structure and key information points of the unconventional nameplate template. Specifically, the system extracts the corresponding information from the nameplate text content according to the field order and format defined in the unconventional nameplate template, and fills it into the corresponding position of the unconventional nameplate template. The output of this operation is a structured power equipment nameplate information object, which, for example, contains key data such as the equipment model, specification parameters, and production date.

[0032] Step 4: When the nameplate text does not contain content that matches the supplier name-equipment name label, the nameplate text content is the power equipment nameplate information.

[0033] That is to say, if the nameplate text content does not contain content that matches the supplier name-equipment name tag of any template, it means that the current nameplate is a regular nameplate (i.e., a nameplate in which the power equipment nameplate text is arranged regularly in rows). In this case, the nameplate text content of the power equipment nameplate extracted by row in step 1 is basically structured, and the system will directly output the original nameplate text content as the power equipment nameplate information.

[0034] In one achievable manner, extracting the nameplate text content of the electric power equipment nameplate row by row may specifically include: a. Obtain the nameplate image of the power equipment.

[0035] Exemplarily, this is accomplished by using a high-resolution digital camera, a smart phone, or other image acquisition device. When capturing images, it should be ensured that the images are clear, well-lit, and at the correct angle, so that the subsequent OCR algorithm can accurately recognize the text information on the nameplate. It should also be noted that in order to improve recognition accuracy, the nameplate can also be cleaned before shooting to remove dirt or obstructions that may affect recognition.

[0036] b. Using the OCR algorithm, traverse the electric power equipment nameplate image line by line to extract the nameplate text content.

[0037] That is to say, after obtaining the nameplate image of the power equipment, the OCR algorithm is used to process the nameplate image of the power equipment. The OCR algorithm can convert the text in the nameplate image of the power equipment into editable text and can accurately recognize text in various fonts, sizes and arrangements.

[0038] Specifically, the OCR algorithm will first pre-process the nameplate image of the power equipment, including grayscale, binarization, and denoising, to improve the accuracy of text recognition. Then, the OCR algorithm will traverse the image line by line from left to right and from top to bottom to extract text information. In each line, the OCR algorithm will identify continuous text blocks (i.e., text areas) and extract the text in these text blocks to form a complete line of text content.

[0039] c. After traversing the last text block of each line, perform line break traversal until traversing the entire electric equipment nameplate image.

[0040] Specifically, when the OCR algorithm traverses the last text block of the current line, it will automatically wrap and continue to extract the text of the next line. This step will be repeated until the entire power equipment nameplate image has been traversed.

[0041] Preferably, when the OCR algorithm is used to traverse the electric power equipment nameplate image line by line to extract the nameplate text content, it also includes: when traversing the same line, if the character spacing between adjacent text blocks exceeds the preset character spacing, a separator is added between adjacent text blocks.

[0042] That is to say, in the process of extracting the nameplate text content by line traversal using the OCR algorithm, the character spacing between adjacent text blocks may be different due to factors such as the arrangement of the text on the nameplate, the font size, and the shooting angle. In order to ensure that the extracted text blocks are better structured and facilitate subsequent information processing and analysis, this embodiment adds a processing step for the character spacing between adjacent text blocks when traversing the same line.

[0043] Specifically, when the OCR algorithm traverses a line, it detects the character spacing between adjacent text blocks. If the character spacing between adjacent text blocks exceeds the preset character spacing threshold (the threshold can be adjusted according to actual conditions to ensure that the separation between different text blocks can be accurately identified), the OCR algorithm will automatically add separators (such as spaces, commas, line breaks, etc., and the specific separators can be determined according to actual needs) between adjacent text blocks.

[0044] In this embodiment, by adding separators, adjacent text blocks can be effectively distinguished to avoid confusion or errors in subsequent information processing and parsing. At the same time, the extracted text content is more structured, which is convenient for subsequent field matching, information extraction and data analysis.

[0045] It should be noted that the selection of the preset character spacing threshold is critical to the effect of this step. If the threshold is set too high, it may lead to inaccurate separation between adjacent text blocks, or even incorrectly separate the content that originally belonged to the same text block; if the threshold is set too low, some actual separations between text blocks may be ignored, resulting in confusion or errors in the extracted text content. Therefore, in actual applications, it is necessary to reasonably adjust and optimize the character spacing threshold according to the specific situation of the nameplate and the recognition effect of the OCR algorithm.

[0046] In one achievable manner, the unconventional nameplate template is constructed based on an actual electric equipment nameplate corresponding to a supplier name-equipment name, and the unconventional nameplate template includes a fixed text block and a text filling area that has a unique positional relationship with the fixed text block.

[0047] Specifically, the unconventional nameplate template is constructed based on the actual power equipment nameplate corresponding to the supplier name-equipment name. For each specific supplier and equipment combination, this embodiment will construct a corresponding unconventional nameplate template based on the actual layout and format of its nameplate.

[0048] Exemplarily, the process of constructing an unconventional nameplate template can be specifically as follows: collect a large number of power equipment nameplate samples from different suppliers and different equipment. The samples should cover various possible nameplate layouts and formats to ensure that the constructed template can cover all possible situations. For each collected power equipment nameplate sample, analyze and identify the fixed text blocks on the power equipment nameplate (such as voltage, product code, total weight, rated voltage, etc. fonts). Based on the structural analysis of the nameplate, an unconventional nameplate template is designed, which includes all fixed text blocks on the nameplate, and a text fill area that has a unique positional relationship with the fixed text blocks. There is a unique positional relationship between the text fill area and the fixed text block to ensure that the extracted text content can be accurately matched with the corresponding area in the template in the subsequent information extraction process.

[0049] Preferably, the unconventional nameplate template called by filling the nameplate text content is specifically: comparing the nameplate text content with the fixed text block in the unconventional nameplate template; and filling the information in the nameplate text content into the text filling area according to the comparison result.

[0050] Specifically, after constructing the unconventional nameplate template and successfully extracting the text content of the power equipment nameplate, the next step is to fill these text contents into the called unconventional nameplate template. First, the extracted nameplate text content needs to be compared with the fixed text block in the unconventional nameplate template. During the comparison process, string matching algorithms, such as the KMP algorithm, the Boyer-Moore algorithm, etc., can be used to efficiently match the text content. After the extracted text content matches the fixed text block, the information in the text content needs to be filled into the text filling area in the unconventional nameplate template.

[0051] During the filling process, it is necessary to ensure that each field in the extracted text content can accurately match the corresponding text filling area in the template. After completing the information filling, the structured power equipment nameplate information can be generated. This information can include key data such as the equipment model, specification parameters, production date, serial number, etc.

[0052] When using the nameplate text content to fill in the unconventional nameplate template, the accurate and efficient extraction and structured storage of the power equipment nameplate information is achieved through the process of comparison and filling, which not only improves the accuracy of information extraction, but also provides reliable support for the management and maintenance of power equipment.

[0053] In this embodiment, the unconventional nameplate is a nameplate whose text is not arranged in a row pattern. This type of nameplate brings difficulties to the traditional OCR information extraction method based on row traversal due to the irregularity of the text arrangement. The present invention proposes a method for extracting nameplate information of power equipment, which realizes accurate and efficient extraction and structured storage of nameplate information when facing unconventional nameplates.

[0054] In another embodiment of the present invention, a device for extracting nameplate information of electric equipment is provided, which is used to implement the aforementioned method for extracting nameplate information of electric equipment, and specifically includes the following modules: The extraction module is used to extract the nameplate text content of the power equipment nameplate by line.

[0055] In one embodiment, extracting the nameplate text content of the power equipment nameplate by line specifically includes: obtaining a nameplate image of the power equipment; using an OCR algorithm to traverse the nameplate image of the power equipment by line to extract the nameplate text content; when traversing the last text block of each line, performing a line break traversal until the nameplate image of the power equipment is traversed.

[0056] Preferably, when traversing the same line, if the character interval between adjacent text blocks exceeds a preset character interval, a separator is added between adjacent text blocks.

[0057] The traversal module is used to traverse a pre-established unconventional nameplate template library using the nameplate text content, wherein the unconventional nameplate template library includes a variety of unconventional nameplate templates marked with different supplier name-equipment name labels.

[0058] A calling filling module is used to call the unconventional nameplate template corresponding to the matching tag when the nameplate text content contains content that matches the supplier name-equipment name tag, and use the nameplate text content to fill the called unconventional nameplate template to obtain the power equipment nameplate information.

[0059] In one embodiment, the nameplate text content is compared with the fixed text block in the unconventional nameplate template; based on the comparison result, the information in the nameplate text content is filled into the text filling area.

[0060] A determination module is used to determine that, when the nameplate text content does not contain content that matches the supplier name-equipment name label, the nameplate text content is the electric equipment nameplate information.

[0061] All relevant contents of each step involved in the aforementioned embodiment of a method for extracting nameplate information of electric equipment can be referred to the functional description of a functional module corresponding to a device for extracting nameplate information of electric equipment in an embodiment of the present invention, and will not be repeated here. The division of modules in the embodiment of the present invention is schematic, and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention can be integrated into a processor, or it can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules.

[0062] The above-mentioned method for extracting nameplate information of power equipment can be applied in the equipment verification work of the power industry. When a power company carries out a project, it will receive various types of power equipment provided by the equipment company. Using the method for extracting nameplate information of power equipment proposed in the present invention, the staff can quickly determine whether the equipment meets the requirements. The specific working steps are as follows: The staff uses a mobile phone to take a picture of the nameplate of the power equipment to ensure that the image quality is clear, and then sends the nameplate image to the server. The program running on the computer will read the message on the server regularly. If the nameplate picture is updated, the nameplate picture will be downloaded and processed and compared through the processing module and the information comparison module, and then the result will be sent to the server. The mobile terminal obtains the result on the server through the subscription service.

[0063] Exemplarily, a system for extracting nameplate information of electric equipment is provided, and a system for extracting nameplate information of electric equipment is described in combination with a specific nameplate image: the system for extracting nameplate information of electric equipment mainly includes an image acquisition module, a database module, a processing module, and an information comparison module. The image acquisition module is deployed on the mobile terminal, and the database module, the processing module, and the information comparison module are all deployed on the PC terminal. The database module on the PC terminal needs to save the data of the nameplate of electric equipment related to a project to the database in advance. The mobile terminal uses a smart phone to take an image of the nameplate of the electric equipment, and then uploads it to the server through the network. The PC terminal is connected to the server through an application, obtains the nameplate image transmitted by the mobile terminal, and then obtains the parameter information on the nameplate of the electric equipment through the processing module (that is, the above-mentioned method for extracting nameplate information of electric equipment, in which the above-mentioned device for extracting nameplate information of electric equipment is deployed), and compares the extracted parameters with the equipment standard parameters in the database through the information comparison module to determine whether the equipment actually delivered is consistent with the equipment on the material list.

[0064] In another embodiment of the present invention, a computer device is provided, the computer device comprising a processor and a memory, the memory being used to store a computer program, the computer program comprising program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in a computer storage medium to implement a corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a method for extracting nameplate information of an electric power device.

[0065] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for extracting nameplate information of an electric equipment in the above embodiment.

[0066] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0067] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0068] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0070] In the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0071] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for extracting nameplate information of electric power equipment, characterized in that: include: Extract the nameplate text content of the power equipment nameplate by line; Using the nameplate text content, traversing a pre-established unconventional nameplate template library, the unconventional nameplate template library includes a plurality of unconventional nameplate templates marked with different supplier name-equipment name labels; When the nameplate text content contains content that matches the supplier name-equipment name tag, calling the unconventional nameplate template corresponding to the matching tag, and using the nameplate text content to fill the called unconventional nameplate template to obtain the power equipment nameplate information; When the nameplate text content does not contain content that matches the supplier name-equipment name label, the nameplate text content is the electric equipment nameplate information.

2. A method for extracting nameplate information of electric power equipment according to claim 1, characterized in that: The extracting of nameplate text content of the electric power equipment nameplate by row includes: Get the nameplate image of the power equipment; Using an OCR algorithm to traverse the electric power equipment nameplate image line by line to extract the nameplate text content; After traversing the last text block of each line, a line break traversal is performed until the electric equipment nameplate image is traversed.

3. A method for extracting nameplate information of electric power equipment according to claim 2, characterized in that: When the OCR algorithm is used to traverse the electric power equipment nameplate image line by line to extract the nameplate text content, it also includes: When traversing the same line, if the character interval between adjacent text blocks exceeds the preset character interval, a separator is added between adjacent text blocks.

4. A method for extracting nameplate information of electric power equipment according to claim 1, characterized in that: The unconventional nameplate template is constructed based on an actual electric equipment nameplate corresponding to a supplier name-equipment name, and the unconventional nameplate template includes a fixed text block and a text filling area that has a unique positional relationship with the fixed text block.

5. A method for extracting nameplate information of electric power equipment according to claim 4, characterized in that: The non-conventional nameplate template filled and called by the nameplate text content is specifically: comparing the nameplate text content with the fixed text block in the unconventional nameplate template; According to the comparison result, the information in the nameplate text content is filled into the text filling area.

6. A method for extracting nameplate information of electric power equipment according to claim 1, characterized in that: The unconventional nameplate is a nameplate on which the text of the electric equipment nameplate is not arranged in a regular row pattern.

7. A device for extracting nameplate information of electric power equipment, characterized in that: include: An extraction module, used for extracting the nameplate text content of the power equipment nameplate by line; A traversal module, used to traverse a pre-established unconventional nameplate template library using the nameplate text content, wherein the unconventional nameplate template library includes a plurality of unconventional nameplate templates marked with different supplier name-equipment name labels; A calling and filling module is used to call the unconventional nameplate template corresponding to the matching tag when the nameplate text content contains content matching the supplier name-equipment name tag, and fill the called unconventional nameplate template with the nameplate text content to obtain the electric power equipment nameplate information; A determination module is used to determine that, when the nameplate text content does not contain content that matches the supplier name-equipment name label, the nameplate text content is the electric equipment nameplate information.

8. The device for extracting nameplate information of electric power equipment according to claim 7, characterized in that: The extraction module is specifically used for: Get the nameplate image of the power equipment; Using an OCR algorithm to traverse the electric power equipment nameplate image line by line to extract the nameplate text content; After traversing the last text block of each line, a line break traversal is performed until the electric equipment nameplate image is traversed.

9. A device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for extracting nameplate information of electric equipment as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for extracting nameplate information of electric equipment as described in any one of claims 1 to 6 are implemented.

Images