An OSM model-based power standard system missing item supplement method and system and a machine readable storage medium

Abstract

The embodiment of the application provides a power standard system missing item supplement method and system based on an OSM model and a machine readable storage medium, and belongs to the technical field of electric power. The power standard system missing item supplement method comprises the following steps: acquiring power system related technical standards, and identifying and marking missing items of the related technical standards through an ontology description language in an OSM model; determining at least one power field related technical document related to the missing items according to semantic understanding of the missing items; preprocessing the technical document and the missing items to obtain required technical documents and missing items; classifying the content of the technical document to obtain multiple themes; performing semantic analysis on the missing items; and preliminarily matching the content of the technical document with the missing items according to the classified themes of the technical document and the themes of the missing items. The power standard system missing item supplement method can improve the filling accuracy of the missing items of the standard system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power, in particular to an electric power standard system missing item supplement method and system based on an OSM model and a machine readable storage medium. BACKGROUND

[0002] Currently, the main function of the standard system planning tool is to guide the revision of standard texts and standard systems according to existing standards and standard system information (including standard system structure, standard detail table and technical clause library after disassembly), combined with the matching of business and standard clauses. However, the comparison and filling of missing items in the existing technology still have the problem of insufficient accuracy. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide an electric power standard system missing item supplement method and system based on an OSM model and a machine readable storage medium, which can improve the accuracy of filling the missing items of the standard system.

[0004] In order to achieve the above-mentioned purpose, on the one hand, the embodiments of the present application provide an electric power standard system missing item supplement method based on an OSM model, which comprises:

[0005] Obtain electric power system related technical standards, and identify and mark the missing items of the related technical standards through the ontology description language in the OSM model;

[0006] According to the semantic understanding of the missing items, at least one electric power field related technical document related to the missing items is determined;

[0007] The technical documents and missing items are preprocessed to obtain technical documents and missing items meeting the requirements;

[0008] The content of the technical documents is classified to obtain a plurality of topics;

[0009] The missing items are subjected to semantic analysis to obtain the topics of the missing items;

[0010] According to the topics of the classified technical documents and the topics of the missing items, the content of the technical documents is preliminarily matched with the missing items;

[0011] According to the preliminary matching result, the topics of the technical documents are screened, and the content of the screened topics of the technical documents is further matched with the missing items to obtain a fine matching result;

[0012] According to the fine matching result, the content of the matched technical documents is supplemented into the missing items.

[0013] Optionally, the technical document and the missing item are preprocessed to obtain a required technical document and missing item, including:

[0014] Obtaining the missing item and the technical document;

[0015] The missing item and the technical document are segmented, stop words are removed, word stems are extracted, and word forms are restored.

[0016] Optionally, the technical document and the missing item are preprocessed to obtain a required technical document and missing item, including:

[0017] The technical document is contextually analyzed using a semantic analysis model to obtain the true meaning of the words in the technical document;

[0018] The processed technical document is input into a translation machine for translation in units of words, obtaining a multilingual word set corresponding to the words in the processed text;

[0019] The obtained multilingual text set is arranged and output according to the grammar of the language, so that the output text conforms to the grammar of the corresponding language, obtaining a multilingual text that conforms to the semantics.

[0020] Optionally, the content of the technical document is classified to obtain a plurality of topics, including:

[0021] Obtaining a dataset containing text and corresponding labels as a training set;

[0022] Bringing the training set into a CNN model to train the CNN model;

[0023] Converting the content of the technical document to obtain a word vector sequence;

[0024] Sending the word vector sequence into the trained CNN model to obtain the classification result of the content of the technical document, and corresponding the classification result to different topics.

[0025] Optionally, according to the topic of the technical document after classification and the topic of the missing item, the content of the technical document is preliminarily matched with the missing item, including: according to the semantic understanding of the topic of the missing item, finding a topic of the technical document that is the same as the semantic representation of the topic of the missing item.

[0026] Optionally, according to the result of preliminary matching, the topic of the technical document is screened, and the content of the screened topic of the technical document is further matched with the missing item to obtain a fine matching result, including:

[0027] Obtaining a topic of the technical document that is the same as the semantic representation of the topic of the missing item;

[0028] obtain the content of the topic, and perform a duplicate detection process on the text content of the topic to remove duplicate content;

[0029] perform feature conversion on the text content after deduplication and the missing items to obtain a feature vector in a unified format;

[0030] perform similarity matching on the text content and the missing items according to the feature vector, and select text content with a similarity greater than a preset threshold as a matching result.

[0031] Optionally, the power standard system includes multiple links from clean energy power generation, smart grid, energy storage technology to end user services.

[0032] In another aspect, the present application also provides a power standard system missing item supplement system based on an OSM model, which includes:

[0033] a data acquisition module that acquires power system related technical standards and identifies and marks missing items of the standards through an ontology description language in the OSM model;

[0034] a missing supplement module that is used to acquire power system related technical standards and perform a power standard system missing item supplement method based on an OSM model as described above.

[0035] In still another aspect, the present application also provides a machine readable storage medium having instructions stored thereon for causing a machine to perform a power standard system missing item supplement method based on an OSM model as described above.

[0036] Through the technical solution, the power standard system missing item supplement method and system based on the OSM model and the machine readable storage medium provided by the application obtain the power system related technical standards, and the missing items of the related technical standards can be identified and marked by the ontology description language in the OSM model, then at least one power field related technical document related to the missing item can be determined according to the semantic understanding of the missing item. After the technical document is obtained, the technical document and the missing item can be preprocessed, so that the technical document and the missing item meeting the requirements can be obtained, then the content of the technical document can be classified, so that multiple topics can be obtained. The missing item can be subjected to semantic analysis, so that the topic of the missing item can be obtained. According to the topic of the technical document after classification and the topic of the missing item, the content of the technical document can be preliminarily matched with the missing item. According to the preliminary matching result, the topic of the technical document can be screened, and the topic content of the technical document that does not conform to the topic of the missing item can be removed, then the content of the screened topic of the technical document and the missing item can be further matched, so that a fine matching result can be obtained. According to the fine matching result, the content of the matched technical document can be supplemented into the missing item. The power standard system missing item supplement method can improve the accuracy of the standard system missing item filling.

[0037] Other features and advantages of the embodiments of the present application will be described in detail in the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0038] The accompanying drawings are included to provide a further understanding of the embodiments of the application, and constitute a part of the specification, and are used to explain the embodiments of the application together with the following detailed description, but do not constitute a limitation of the embodiments of the application. In the drawings:

[0039] Figure 1 is a flowchart of a power standard system missing item supplement method based on an OSM model according to an embodiment of the present application;

[0040] Figure 2 is a first flowchart of preprocessing of a power standard system missing item supplement method based on an OSM model according to an embodiment of the present application;

[0041] Figure 3 is a second flowchart of preprocessing of a power standard system missing item supplement method based on an OSM model according to an embodiment of the present application;

[0042] Figure 4 is a flowchart of classifying the content of a technical document of a power standard system missing item supplement method based on an OSM model according to an embodiment of the present application;

[0043] Figure 5 is a flowchart of obtaining fine matching based on an OSM model-based power standard system missing item supplement method according to an embodiment of the present application. DETAILED DESCRIPTION

[0044] The specific embodiments of the embodiments of the present application are described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to illustrate and explain the embodiments of the present application, and are not intended to limit the embodiments of the present application.

[0045] Figure 1 is a flowchart of an OSM model-based power standard system missing item supplement method according to an embodiment of the present application. In the present application, the flowchart can include:

[0046] In step S1, power system related technical standards are obtained, and missing items of the related technical standards are identified and marked by an ontology description language in the OSM model.

[0047] In step S2, at least one power field related technical document related to the missing item is determined according to semantic understanding of the missing item.

[0048] In step S3, the technical document and the missing item are preprocessed to obtain a required technical document and a missing item.

[0049] In step S4, the content of the technical document is classified to obtain a plurality of topics.

[0050] In step S5, the missing item is subjected to semantic analysis to obtain a topic of the missing item.

[0051] In step S6, the content of the technical document is preliminarily matched with the missing item according to the classified topics of the technical document and the topic of the missing item.

[0052] In step S7, the topics of the technical document are screened according to the preliminary matching result, and the content of the screened topics of the technical document is further matched with the missing item to obtain a fine matching result.

[0053] In step S8, the content of the matched technical document is supplemented into the missing item according to the fine matching result.

[0054] In the present application, when supplementing the missing items, the relevant technical standards of the power system can be acquired first, and the missing items of the relevant technical standards can be identified and marked by the ontology description language in the OSM model. According to the implied understanding of the missing items, at least one power field related technical document related to the missing items can be determined. The technical document and the missing items can be preprocessed, so that the required technical document and the missing items can be obtained. The content of the technical document is classified to obtain multiple types of topics, and then the missing items are semantically analyzed to obtain the topics of the missing items. According to the classified topics of the technical document and the topics of the missing items, the content of the technical document can be preliminarily matched with the missing items. After the preliminary matching of the missing items, the topics of the technical document can be screened according to the preliminary matching results, and the content of the screened topics of the technical document can be further matched with the missing items, so that the fine matching results can be obtained. According to the fine matching results, the content of the matched technical document can be supplemented into the missing items. The power standard system missing item supplement method can improve the accuracy of standard system missing item filling.

[0055] In one embodiment of the present application, as shown in Figure 2 the first flow of preprocessing can include:

[0056] In step S9, the missing items and the technical document are acquired.

[0057] In step S10, the missing items and the technical document are segmented, stop words are removed, word stems are extracted, and word forms are restored.

[0058] For the acquired technical document and the missing items, unnecessary punctuation marks and special characters such as “,” and “.” can be removed, and then segmentation, word stem extraction and word form restoration processing can be performed to facilitate subsequent processing of the technical document and the missing items.

[0059] In one embodiment of the present application, as shown in Figure 3 the second flow of preprocessing can include:

[0060] In step S11, the technical document is contextually semantically analyzed using a semantic analysis model to acquire the true meaning of the words in the technical document.

[0061] In step S12, the processed technical document is input into a translation machine for translation in units of words to obtain a multilingual word set corresponding to the words in the processed text.

[0062] In step S13, the obtained multilingual text set is arranged and output according to the grammar of the language, so that the output text conforms to the grammar of the corresponding language, and a multilingual text conforming to the semantics is obtained.

[0063] In the present application, after processing such as word segmentation on technical documents and missing items, the technical documents can be subjected to contextual semantic analysis using a semantic analysis model, so that the true meaning of the words in the technical documents can be obtained. Then the processed technical documents can be input into a translation machine for translation in word units, so that a multilingual word set corresponding to the words in the processed text can be obtained. After obtaining the multilingual word set, the obtained multilingual text set can be arranged and output according to the grammar of the language, so that the output text can conform to the grammar of the corresponding language, and thus a required multilingual text can be obtained.

[0064] In an embodiment of the present application, as shown in Figure 4 The process of classifying the content of the technical document can include:

[0065] In step S14, a data set containing text and corresponding labels is obtained as a training set.

[0066] In step S15, the training set is input into the CNN model to train the CNN model.

[0067] In step S16, the content of the technical document is converted to obtain a word vector sequence.

[0068] In step S17, the word vector sequence is input into the trained CNN model to obtain the classification result of the content of the technical document, and the classification result is corresponded to different topics.

[0069] In the present application, when classifying the content of the technical document, a data set containing text and corresponding labels can be obtained as a training set, and then the CNN model can be trained through the training set so that the CNN model can classify the input text. After training, the content of the technical document can be converted to obtain a word vector sequence, and then the word vector sequence can be input into the trained CNN model to obtain the classification result of the content of the technical document, and then the classification result can be corresponded to different topics.

[0070] In an embodiment of the present application, according to the topic of the technical document after classification and the topic of the missing item, the content of the technical document is preliminarily matched with the missing item, including: according to the semantic understanding of the topic of the missing item, finding the topic of the technical document which has the same semantic representation as the topic of the missing item. After obtaining the preliminary match, the content of the topic which does not match the topic of the missing item in the technical document can be discarded.

[0071] In an embodiment of the present application, as shown in Figure 5 The process of obtaining the fine match can include:

[0072] In step S18, the topic of the technical document identical to the topic semantic representation of the missing item is obtained.

[0073] In step S19, the content of the topic is obtained, and the duplicate content of the text content of the topic is removed.

[0074] In step S20, the de-duplicated text content and the missing item are feature-converted to obtain a feature vector in a unified format.

[0075] In step S21, the text content is similarity-matched with the missing item according to the feature vector, and the text content with a similarity greater than a preset threshold is selected as a matching result.

[0076] In the present application, when fine matching is performed, the topic of the technical document identical to the topic semantic representation of the missing item can be obtained, and then the content of the topic can be obtained, and the duplicate content of the topic can be removed. After de-duplication, the de-duplicated text content and the missing item can be feature-converted to obtain a feature vector in a unified format. According to the feature vector of the text content and the feature vector of the missing item, the text content can be similarity-matched with the missing item, and then the text content with a similarity greater than a preset threshold can be selected as a matching result.

[0077] In one embodiment of the present application, the power standard system can include multiple links from clean energy power generation, smart grid, energy storage technology to end user services.

[0078] On the other hand, the present application also provides an OSM model-based power standard system missing item supplement system, which comprises:

[0079] A data acquisition module acquires power system related technical standards and identifies and marks missing items of the standards through an ontology description language in the OSM model.

[0080] A missing supplement module is used to acquire power system related technical standards and execute an OSM model-based power standard system missing item supplement method as described above.

[0081] In one aspect, the present application also provides a machine readable storage medium having instructions stored thereon for causing a machine to execute an OSM model-based power standard system missing item supplement method as described above.

[0082] By the technical scheme, the power standard system missing item supplement method and system based on the OSM model and the machine readable storage medium provided by the application obtain the power system related technical standards, and the missing items of the related technical standards can be identified and marked by the ontology description language in the OSM model, then at least one power field related technical document related to the missing item can be determined according to the semantic understanding of the missing item. After the technical document is obtained, the technical document and the missing item can be preprocessed, so that the technical document and the missing item meeting the requirements can be obtained, then the content of the technical document can be classified, so that multiple topics can be obtained. The semantic analysis can be performed on the missing item, so that the topic of the missing item can be obtained. According to the topic of the technical document after the classification and the topic of the missing item, the content of the technical document can be preliminarily matched with the missing item. According to the preliminary matching result, the topic of the technical document can be screened, and the topic content of the technical document that does not conform to the topic of the missing item is removed, then the content of the screened topic of the technical document and the missing item can be further matched, so that a fine matching result can be obtained. According to the fine matching result, the content of the matched technical document can be supplemented into the missing item. The power standard system missing item supplement method can improve the accuracy of the standard system missing item filling.

[0083] Those skilled in the art will appreciate that embodiments of the application can be supplied as a method, a system, or a computer program product. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can be embodied in the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage media, etc.) having computer usable program code embodied therein.

[0084] The application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams 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 produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in a flow or multiple flows and / or blocks.

[0085] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0087] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0088] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), flash memory, or other memory technologies, about which the processor can execute instructions. The memory is an example of computer readable media.

[0089] Computer readable media includes permanent and non-permanent, moveable and non- moveable media that can store information by any method or technology. The information can be computer readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile discs (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0090] It should also be noted that the terms "comprising", "comprises" or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0091] The above embodiments are only used to illustrate the present application, but not to limit it. Instead of the above, various modifications and changes can be made to the application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall fall into the scope of the claims of the application.

Claims

1. A method for supplementing missing items in a power standard system based on an OSM model, characterized in that, The power standard system missing item supplement method comprises: Obtaining power system related technical standards, and identifying and marking missing items of the related technical standards through an ontology description language in an OSM model; According to the semantic understanding of the missing items, at least one power field related technical document related to the missing items is determined; The technical document and the missing item are preprocessed to obtain a required technical document and a missing item; The content of the technical document is classified to obtain a plurality of topics; The missing item is subjected to semantic analysis to obtain the topic of the missing item; According to the classified topics of the technical document and the topic of the missing item, the content of the technical document is preliminarily matched with the missing item; According to the preliminary matching result, the topics of the technical document are screened, and the content of the screened topics of the technical document is further matched with the missing item to obtain a fine matching result, comprising: Obtaining the topics of the technical document with the same semantic representation as the topic of the missing item; Obtaining the content of the topic and performing duplicate detection processing on the text content of the topic to remove duplicate content; The de-duplicated text content and the missing item are subjected to feature conversion to obtain a feature vector in a unified format; According to the feature vector, the text content is matched with the missing item in terms of similarity, and the text content with a similarity greater than a preset threshold is selected as a matching result; According to the fine matching result, the content of the matched technical document is supplemented into the missing item.

2. The method of claim 1, wherein the method is based on an OSM model. The preprocessing of the technical document and the missing item to obtain a required technical document and a missing item comprises: Obtaining the missing item and the technical document; The missing item and the technical document are subjected to word segmentation, stop word removal, stem extraction, and morphological reduction.

3. The method of claim 2, wherein the OSM model-based power standard system missing item supplement method is characterized by, The preprocessing of the technical document and the missing item to obtain a required technical document and a missing item comprises: Using a semantic analysis model to perform context semantic analysis on the technical document to obtain the true meaning of the words in the technical document; The processed technical document is input into a translation machine for translation in units of words to obtain a multilingual word set corresponding to the words in the processed text; The obtained multilingual text set is arranged and output according to the grammar of the language, so that the output text conforms to the grammar of the corresponding language, and a multilingual text conforming to the semantics is obtained.

4. The method of claim 3, wherein the method is based on an OSM model. The classification of the content of the technical document to obtain a plurality of topics comprises: Obtaining a data set containing text and corresponding labels as a training set; The training set is input into a CNN model to train the CNN model; The content of the technical document is converted to obtain a word vector sequence; The word vector sequence is input into the trained CNN model to obtain the classification result of the content of the technical document, and the classification result is corresponded to different topics.

5. The method of claim 4, wherein the OSM model-based power standard system missing item supplement method is characterized by, According to the classified topics of the technical document and the topic of the missing item, the content of the technical document is preliminarily matched with the missing item, comprising: according to the semantic understanding of the topic of the missing item, finding the topic of the technical document with the same semantic representation as the topic of the missing item.

6. The method of claim 1, wherein the method is based on an OSM model. The power standard system includes multiple links from clean energy power generation, smart grid, energy storage technology to end user services.

7. An OSM model-based power standard system missing item supplement system, characterized by, The system comprises: A data acquisition module acquires power system related technical standards and identifies and marks missing items in the standards through an ontology description language in the OSM model; A missing supplement module is configured to acquire power system related technical standards and perform the missing item supplement method of the power standard system based on the OSM model according to any one of claims 1-6.

8. A machine-readable storage medium having stored thereon instructions, the instructions being executable by a machine to cause the machine to: The instruction is configured to cause the machine to perform the missing item supplement method of the power standard system based on the OSM model according to any one of claims 1-6.

Images