CN113282752B - Object classification method and system based on semantic mapping - Google Patents
Object classification method and system based on semantic mapping Download PDFInfo
- Publication number
- CN113282752B CN113282752B CN202110642057.1A CN202110642057A CN113282752B CN 113282752 B CN113282752 B CN 113282752B CN 202110642057 A CN202110642057 A CN 202110642057A CN 113282752 B CN113282752 B CN 113282752B
- Authority
- CN
- China
- Prior art keywords
- mapping
- relation
- result
- file
- instruction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
Abstract
The invention discloses a thing classification method and a system based on semantic mapping, which are characterized in that a first image is obtained according to a first acquisition instruction, a first image format is converted according to a first document conversion instruction, and a second file is obtained; carrying out document disassembly evaluation on the second file according to the first document disassembly evaluation instruction to obtain a first document disassembly scheme; obtaining a third file; extracting keywords from the third file according to the first keyword extraction instruction to obtain a first keyword extraction result; constructing a first mapping retrieval classification relation between the keywords and the third file; obtaining a first semantic aggregation result; constructing a second mapping retrieval classification relation of the semantics and a third file according to the first semantic aggregation result, and obtaining a third mapping retrieval classification relation; and classifying the files based on the mapping relation for the first file according to the third mapping retrieval classification relation. Solves the technical problem that the classification arrangement of files is not scientific and accurate enough when the classification arrangement of files is carried out in the prior art.
Description
Technical Field
The invention relates to the field of file classification, in particular to a transaction classification method and system based on semantic mapping.
Background
The file classification is a process of hierarchically distinguishing files according to different points of file sources, time, contents and form characteristics according to a certain standard. The value of the file can be scientifically identified only after classification and arrangement, and the storage period of the file is determined; only if files are sorted, the scientific storage and scientific plan of the files are conditionally realized.
However, in the process of implementing the technical scheme of the invention in the embodiment of the application, the inventor of the application finds that at least the following technical problems exist in the above technology:
in the prior art, the technical problem that the classification arrangement of files is not scientific and accurate enough exists when the classification arrangement of files is carried out.
Disclosure of Invention
By providing the object classification method and the object classification system based on the semantic mapping, the technical problem that classification and arrangement of files are not scientific and accurate enough in the prior art when the files are classified and arranged is solved, and the technical effect that intelligent and accurate classification and arrangement of files are carried out based on the semantic mapping is achieved.
In view of the above problems, it is proposed that an embodiment of the present application provides a method and a system for classifying things based on semantic mapping.
The application provides a thing classification method based on semantic mapping, which is applied to a mapping classification system, wherein the system is in communication connection with a first image acquisition device, the system comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, the processor executes the program to realize the following steps of the method, and the method comprises the following steps: acquiring a first acquisition instruction, and acquiring a first image through the first image acquisition device according to the first acquisition instruction, wherein the first image is an image of a first file; obtaining a first document conversion instruction, and converting the first image format according to the first document conversion instruction to obtain a second file; obtaining a first document disassembly evaluation instruction, and carrying out document disassembly evaluation on the second file according to the first document disassembly evaluation instruction to obtain a first document disassembly scheme; according to the first document disassembly scheme, document disassembly is carried out on the second file, and a third file is obtained; obtaining a first keyword extraction instruction, and extracting keywords from the third file according to the first keyword extraction instruction to obtain a first keyword extraction result; constructing a first mapping retrieval classification relation between the keywords and the third file according to the first keyword extraction result; acquiring a first semantic aggregation instruction, and performing semantic aggregation analysis on the third file according to the first semantic aggregation instruction to acquire a first semantic aggregation result; constructing a second mapping retrieval classification relation between the semantics and the third archive according to the first semantic aggregation result, wherein the mapping grade of the second mapping retrieval classification relation is higher than that of the first mapping retrieval classification relation; inputting the second mapping retrieval classification relation and the first mapping retrieval classification relation into a mapping result analysis model to obtain a third mapping retrieval classification relation; and classifying the files of the first file based on the mapping relation according to the third mapping retrieval classification relation.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
the first file is acquired through the first acquisition instruction, a first image is obtained, the first image is converted into a second file according to the first document conversion instruction, the second file is disassembled to obtain a third file, the third file is extracted according to the first keyword extraction instruction, a first keyword extraction result is obtained, a first mapping search classification relation between keywords and the third file is constructed according to the first keyword extraction result, a second mapping search classification relation between semantics and the third file is constructed according to the semantic aggregation result, the second mapping search classification relation and the first mapping search classification relation are input into a mapping result analysis model to obtain a third mapping search classification relation, the first file is disassembled according to the third mapping search classification relation, the mapping search classification result is constructed according to the semantic disassembly and semantic analysis of the file, and the subsequent file classification result obtained according to the mapping result is more accurate, and therefore a more intelligent technology effect is obtained.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Fig. 1 is a flow chart of a transaction classification method based on semantic mapping according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Reference numerals illustrate: electronic device 10, processor 11, memory 12, input means 13, output means 14.
Detailed Description
By providing the object classification method and the object classification system based on the semantic mapping, the technical problem that classification and arrangement of files are not scientific and accurate enough in the prior art when the files are classified and arranged is solved, and the technical effect that intelligent and accurate classification and arrangement of files are carried out based on the semantic mapping is achieved. Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can appreciate, with the development of technology and the appearance of new scenes, the technical solutions provided in the embodiments of the present application are applicable to similar technical problems.
The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which the embodiments of the application described herein have been described for objects of the same nature. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Summary of the application
The file classification is a process of hierarchically distinguishing files according to different points of file sources, time, contents and form characteristics according to a certain standard. The value of the file can be scientifically identified only after classification and arrangement, and the storage period of the file is determined; only if files are sorted, the scientific storage and scientific plan of the files are conditionally realized. In the prior art, the technical problem that the classification arrangement of files is not scientific and accurate enough exists when the classification arrangement of files is carried out.
Aiming at the technical problems, the technical scheme provided by the application has the following overall thought:
the embodiment of the application provides a thing classification method based on semantic mapping, which is applied to a mapping classification system, wherein the system is in communication connection with a first image acquisition device, and the method comprises the following steps: acquiring a first acquisition instruction, and acquiring a first image through the first image acquisition device according to the first acquisition instruction, wherein the first image is an image of a first file; obtaining a first document conversion instruction, and converting the first image format according to the first document conversion instruction to obtain a second file; obtaining a first document disassembly evaluation instruction, and carrying out document disassembly evaluation on the second file according to the first document disassembly evaluation instruction to obtain a first document disassembly scheme; according to the first document disassembly scheme, document disassembly is carried out on the second file, and a third file is obtained; obtaining a first keyword extraction instruction, and extracting keywords from the third file according to the first keyword extraction instruction to obtain a first keyword extraction result; constructing a first mapping retrieval classification relation between the keywords and the third file according to the first keyword extraction result; acquiring a first semantic aggregation instruction, and performing semantic aggregation analysis on the third file according to the first semantic aggregation instruction to acquire a first semantic aggregation result; constructing a second mapping retrieval classification relation between the semantics and the third archive according to the first semantic aggregation result, wherein the mapping grade of the second mapping retrieval classification relation is higher than that of the first mapping retrieval classification relation; inputting the second mapping retrieval classification relation and the first mapping retrieval classification relation into a mapping result analysis model to obtain a third mapping retrieval classification relation; and classifying the files of the first file based on the mapping relation according to the third mapping retrieval classification relation.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a semantic mapping-based object classification method, where the method is applied to a mapping classification system, the system is communicatively connected to a first image capturing device, and the method includes:
step S100: acquiring a first acquisition instruction, and acquiring a first image through the first image acquisition device according to the first acquisition instruction, wherein the first image is an image of a first file;
step S200: obtaining a first document conversion instruction, and converting the first image format according to the first document conversion instruction to obtain a second file;
specifically, the mapping classification system is a system for classifying files based on a mapping relation, the system classifies files according to the constructed file mapping relation, the first image acquisition device is a device for acquiring file images, the mapping classification system is in communication connection with the first image acquisition device, the first image acquisition device is controlled to acquire images of the first files through the first acquisition instruction, a first image acquisition result is obtained, the first image acquisition result comprises a first image, a first document conversion instruction is obtained, the first image is subjected to image format recognition according to the first document conversion instruction, the format and target format of the first image are obtained, the first image is subjected to document conversion according to the first document conversion instruction, and a second file is obtained, wherein the second file can be in an electronic format plain text.
Step S300: obtaining a first document disassembly evaluation instruction, and carrying out document disassembly evaluation on the second file according to the first document disassembly evaluation instruction to obtain a first document disassembly scheme;
step S400: according to the first document disassembly scheme, document disassembly is carried out on the second file, and a third file is obtained;
specifically, the first document disassembly evaluation instruction is a part-of-speech and sentence-based disassembly evaluation instruction for the second document, and the first document disassembly evaluation instruction at least comprises performing natural language analysis (NLP) on each sentence of a text, including word segmentation, part-of-speech tagging, word aggregation, phrase identification, named entity identification, event identification and the like. The method supports data through a semantic big dictionary, and further obtains more accurate classification and disassembly results. And according to the evaluation disassembly scheme, performing file disassembly on the second file to obtain a third file.
Step S500: obtaining a first keyword extraction instruction, and extracting keywords from the third file according to the first keyword extraction instruction to obtain a first keyword extraction result;
specifically, the keyword extraction process is to extract keywords from the third file according to the disassembled result after the file is disassembled, so as to obtain a first keyword extraction result, wherein the first keyword extraction result is a process of summarizing and extracting keywords according to part-of-speech tagging, word aggregation, phrase recognition and the like, and the first keyword extraction result is obtained according to the above processes.
Step S600: constructing a first mapping retrieval classification relation between the keywords and the third file according to the first keyword extraction result;
specifically, according to the obtained first keyword extraction result, obtaining the extraction position of the keyword, and mapping the position relationship between the extraction position of the keyword and the keyword extraction result, namely, each keyword extraction result has a position mapping relationship corresponding to the keyword extraction result. And constructing a mapping relation between the keywords and the positions corresponding to the third file according to the keyword extraction result and the keyword extraction position.
Step S700: acquiring a first semantic aggregation instruction, and performing semantic aggregation analysis on the third file according to the first semantic aggregation instruction to acquire a first semantic aggregation result;
specifically, the semantic aggregation refers to firstly carrying out semantic recognition based on segmentation on the file subjected to document disassembly, the semantic recognition is obtained through semantic analysis by a semantic analysis module, the semantic recognition at least comprises explicit semantic analysis and implicit semantic analysis, the explicit semantic analysis refers to an analysis mode of carrying out semantic analysis with simple combination of semantics according to word combination literal meaning, the implicit semantic analysis refers to an analysis mode of carrying out deep mining on the combined vocabulary, further analyzing whether the combined vocabulary has the semantics which are not flowing on the surface, carrying out semantic aggregation on the explicit semantic analysis result and the implicit semantic analysis result according to the semantic analysis module, obtaining a first semantic aggregation result, further, the aggregation result also comprises inputting the file which is not subjected to document disassembly into the semantic analysis module, carrying out semantic analysis on the file which is not subjected to document disassembly, and carrying out semantic aggregation according to the analysis result and the analysis result of semantic disassembly, so as to obtain the first aggregation result.
Step S800: constructing a second mapping retrieval classification relation between the semantics and the third archive according to the first semantic aggregation result, wherein the mapping grade of the second mapping retrieval classification relation is higher than that of the first mapping retrieval classification relation;
step S900: inputting the second mapping retrieval classification relation and the first mapping retrieval classification relation into a mapping result analysis model to obtain a third mapping retrieval classification relation;
specifically, a mapping relation between paragraphs and semantic aggregation results in the semantic analysis is constructed according to the first semantic aggregation results, namely the second mapping search classification relation, and the level of the mapping relation in the second mapping search classification relation is higher than that of the first mapping search classification relation. The second mapping search classification relation and the first mapping search classification relation are input into a mapping result analysis model, a third mapping search classification relation is obtained, the obtaining process of the third mapping search classification relation is a process of integrating mapping relations between the first mapping search classification relation and the second mapping search classification relation, the integrating result can comprise sorting a plurality of groups of mapping relations which occur at the same position, namely sorting the priority of the search classification according to the level of the mapping relation, further, the sorting process also comprises a judging process of the plurality of groups of mapping relations, for example, when the same position occurs opposite to the mapping relation, the mapping relation with lower mapping grade is subjected to opinion retaining processing, namely only the mapping relation with higher mapping grade is realized. And obtaining the third mapping retrieval classification relation according to the mapping result analysis model.
Step S1000: and classifying the files of the first file based on the mapping relation according to the third mapping retrieval classification relation.
Specifically, according to the mapping relation in the third mapping search classification relation, the search term at the corresponding position of the first archive is obtained, and according to the description mapping relation of different positions, the search indexes of different positions of the archive are constructed, so that a user can be helped to classify the same archive more accurately, the classification result obtained according to the mapping result is more accurate, and the technical effect of obtaining the file classification result more intelligently and accurately is achieved.
Further, the embodiment of the application further includes:
step S1110: obtaining a first semantic deep analysis instruction;
step S1120: performing deep semantic analysis on the third file according to the first semantic deep analysis instruction to obtain a first deep analysis result;
step S1130: extracting a position keyword according to the first deep analysis result, and constructing a fourth mapping retrieval classification relation according to the position keyword and the third file, wherein the mapping grade of the fourth mapping retrieval classification relation is higher than that of the third mapping retrieval classification relation;
Step S1140: inputting the third mapping retrieval classification relation and the fourth mapping retrieval classification relation into a mapping result analysis model to obtain a fifth mapping retrieval classification relation;
step S1150: and classifying the files of the first file based on the mapping relation according to the fifth mapping retrieval classification relation.
Specifically, the first semantic deep analysis instruction is an instruction for further semantic analysis of the third file, in order to further ensure the accuracy of the mapping relation and improve the accuracy of the mapping relation, further analysis is needed for the mapping relation, further semantic analysis is performed on the third file based on internet big data related network hotwords according to the first semantic deep analysis instruction, namely the creation time of the first file is obtained, words occurring after the creation of the first file are filtered according to the creation time, dominant semantic analysis and recessive semantic analysis based on disassembled documents and un-disassembled documents are performed on the third file according to the information of the occurrence time, the deep analysis result is obtained according to the analysis result, keyword extraction based on a context is performed on the position of the analysis result based on the deep analysis result, the position keyword is a central concept according to the semantic result, the position keyword is obtained according to the determination result of different position central concepts, a fourth mapping relation is constructed according to the position keyword and the third file, and the mapping relation is classified according to the fourth mapping relation is classified according to the mapping grade; and inputting the third mapping search classification relation and the fourth mapping search classification relation into a mapping result analysis model to obtain a fifth mapping search classification relation, classifying the files based on the mapping relation for the first file according to the fifth mapping search classification relation, and tamping a foundation for obtaining a more accurate classification result by refining the mapping key words.
Further, the step S1120 in this embodiment of the present application further includes:
step S1121: obtaining a first logical relationship expression word set;
step S1122: constructing a first semantic knowledge database according to the first logical relation expression word set, wherein the first semantic knowledge database is a database for carrying out latent semantic analysis;
step S1123: and carrying out deep semantic analysis on the third file according to the first semantic knowledge database to obtain a first deep semantic analysis result.
Specifically, the first logic relation expression word set is a word set which performs relation explanation on words and sentences before and after the words and sentences, the words and sentences after or before and after the words and sentences change and affect the relation of the other words and sentences, the words with the functions are summarized, the first logic relation expression word set is obtained according to the summarized result, the first semantic knowledge database is constructed based on the first logic relation expression word set, the first semantic knowledge database is a database which performs integrated analysis on semantic expression information based on the logic relation among sentences, and the third file is subjected to deep semantic analysis according to the first semantic knowledge database, so that the first deep semantic analysis result is obtained. Through the deep analysis of the semantics based on the logic relationship, the obtained semantic analysis result is more accurate, and the basis is tamped for obtaining more accurate classification results.
Further, the embodiment of the application further includes:
step S11231: obtaining a first detection instruction, and detecting the mapping relation of the same position of the first file according to the first detection instruction to obtain a first detection result;
step S11232: judging whether the first detection result contains at least two layers of mapping relations or not;
step S11233: when the first detection result comprises at least two layers of mapping relations, a first evaluation instruction is obtained;
step S11234: performing association degree evaluation on the multi-layer mapping relation in the first detection result according to the first evaluation instruction to obtain a first association degree evaluation result;
step S11235: obtaining a first association degree evaluation preset threshold value;
step S11236: judging whether the first relevancy assessment result meets the first relevancy assessment preset threshold value or not;
step S11237: and when the first relevance evaluation result does not meet the first relevance evaluation preset threshold, only reserving the mapping retrieval classification relation with the highest mapping level in the first detection result.
Specifically, the first detection instruction is an instruction for detecting a mapping relation at the same position under the same archive, the number of the mapping relations at the same position is detected according to the first detection instruction, screening is performed according to the detection result, whether two layers or more than two layers of mapping relations exist at the same position is judged, the positions with the two layers or more than two layers of mapping relations are summarized according to the detection result, a first summarization result is obtained, a first association evaluation threshold is obtained according to the first summarization result, the association evaluation threshold is a threshold set according to the association degree evaluation result analyzed at the same position under big data, association degree verification is performed on the positions with the two layers or more than two layers of mapping relations according to the first association degree evaluation preset threshold, whether the association degree evaluation result at the same position meets the first association degree evaluation preset threshold is judged, and when the first association degree evaluation result does not meet the first association degree evaluation threshold, the keyword with low mapping grade is different from the preset keyword with the preset semantic meaning, and the mapping grade is kept at the same position, and the mapping grade is the same.
Further, the embodiment of the application further includes:
step S112361: when the first relevancy assessment result meets the first relevancy assessment preset threshold value, a first ordering instruction is obtained;
step S112362: performing mapping grade sorting on the mapping retrieval classification relation in the first detection result according to the first sorting instruction to obtain a first sorting result;
step S112363: and classifying the files based on the mapping relation for the first file according to the first sorting result.
Specifically, when the first association degree evaluation result meets the first association degree evaluation preset threshold, it indicates that identification information of the same position under different evaluation results has certain identity and consistency, at this time, a first ordering instruction is obtained, the first ordering instruction is an instruction for controlling ordering of the mapping relationships, the mapping relationships at the same position are ordered according to the mapping levels according to the first ordering instruction, when ordering results of the same level appear, the mapping relationships of the same level are used as peer mapping, a first ordering result is obtained, and mapping files of the first file are classified according to the mapping relationships in the first ordering result.
Further, the embodiment of the application further includes:
step S1210: constructing a first encryption mapping database;
step S1220: inputting the mapping retrieval classification relation into the first encryption mapping database to obtain a sixth mapping retrieval classification relation set;
step S1230: encrypting the mapping relation in the sixth mapping retrieval classification relation set to obtain a first encryption processing result, and adjusting the mapping grade in the sixth mapping retrieval classification relation set to be a confidentiality grade according to the first encryption processing result;
step S1240: and carrying out encryption classification based on the mapping relation on the first document according to the sixth mapping retrieval classification relation set.
Specifically, the first encryption mapping database is a database for detecting and encrypting a sensitive mapping relation, when the first encryption mapping database searches the mapping relation as a retrieval classification basis and a vocabulary in the first encryption mapping database exists, encryption processing is performed on the mapping relation, and the encryption processing process is a security level setting process, namely, the mapping relation still exists, but people with different authorities can use and search the mapping relation under different encryption levels. Inputting the mapping search classification relation set into the first encryption mapping database according to the mapping search classification relation set, screening the mapping search classification relation set according to the identification information in the first encryption mapping database to obtain a first screening result, obtaining a sixth mapping search classification relation set according to the screening result, carrying out encryption processing on the mapping relation to obtain a first encryption processing result, and adjusting the mapping grade in the sixth mapping search classification relation set to be a confidentiality grade according to the first encryption processing result; and carrying out encryption classification based on the mapping relation on the first document according to the sixth mapping retrieval classification relation set. By the encryption processing of the mapping relation, the security of searching and reading of the privacy file and the sensitive file is ensured.
Further, the step S900 of the embodiment of the present application further includes:
step S910: obtaining a mapping result analysis model, wherein the mapping result analysis model is a model obtained through training of multiple sets of training data, and each set of the multiple sets of training data comprises the second mapping retrieval classification relation, the first mapping retrieval classification relation and identification information for identifying a mapping relation analysis result;
step S920: and inputting the second mapping search classification relation and the first mapping search classification relation into the mapping result analysis model to obtain a first output result, wherein the first output result comprises the third mapping search classification relation.
Specifically, the mapping result analysis model is a neural network model in machine learning, can be continuously learned and adjusted, and is a highly complex nonlinear power learning system. In short, the mapping result analysis model is a mathematical model, and after a large amount of training data is trained, the mapping result analysis model is trained to a convergence state, and then mapping relation analysis and integration are carried out through the mapping result analysis model according to the input data, so that mapping retrieval classification relations are obtained.
Furthermore, the training process further includes a supervised learning process, each set of supervised data includes the second mapping search classification relationship and the first mapping search classification relationship and the identification information for identifying the mapping relationship analysis result, the second mapping search classification relationship and the first mapping search classification relationship are input into a neural network model, the mapping result analysis model is supervised and learned according to the identification information for identifying the mapping relationship analysis result, so that the output data of the mapping result analysis model is consistent with the supervised data, and the neural network model is continuously self-corrected and adjusted until the obtained output result is consistent with the identification information, and then the set of data supervised learning is ended, and the next set of data supervised learning is performed; and when the neural network model is in a convergence state, ending the supervised learning process. Through supervised learning of the model, the input information is processed more accurately by the model, and a more accurate third mapping retrieval classification relation is obtained.
In summary, the object classification method and system based on semantic mapping provided by the embodiments of the present application have the following technical effects:
1. The first file is acquired through the first acquisition instruction, a first image is obtained, the first image is converted into a second file according to the first document conversion instruction, the second file is disassembled to obtain a third file, the third file is extracted according to the first keyword extraction instruction, a first keyword extraction result is obtained, a first mapping search classification relation between keywords and the third file is constructed according to the first keyword extraction result, a second mapping search classification relation between semantics and the third file is constructed according to the semantic aggregation result, the second mapping search classification relation and the first mapping search classification relation are input into a mapping result analysis model to obtain a third mapping search classification relation, the first file is disassembled according to the third mapping search classification relation, the mapping search classification result is constructed according to the semantic disassembly and semantic analysis of the file, and the subsequent file classification result obtained according to the mapping result is more accurate, and therefore a more intelligent technology effect is obtained.
2. The method adopts a semantic deep analysis mode based on a logic relationship, so that the obtained semantic analysis result is more accurate, and a foundation is tamped for obtaining a more accurate classification result.
Exemplary electronic device
An electronic device of an embodiment of the present application is described below with reference to fig. 2.
Fig. 2 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the object classification method based on semantic mapping in the foregoing embodiments, the present invention further provides an object classification system based on semantic mapping, and an electronic device according to an embodiment of the present application is described below with reference to fig. 2. The electronic device may be the mobile device itself or a stand-alone device independent thereof, having stored thereon a computer program which, when executed by a processor, performs the steps of any of the methods of transaction classification based on semantic mapping described above.
As shown in fig. 2, the electronic device 10 includes one or more processors 11 and memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
The embodiment of the invention provides a thing classification method based on semantic mapping, which is applied to a mapping classification system, wherein the system is in communication connection with a first image acquisition device, and the method comprises the following steps: acquiring a first acquisition instruction, and acquiring a first image through the first image acquisition device according to the first acquisition instruction, wherein the first image is an image of a first file; obtaining a first document conversion instruction, and converting the first image format according to the first document conversion instruction to obtain a second file; obtaining a first document disassembly evaluation instruction, and carrying out document disassembly evaluation on the second file according to the first document disassembly evaluation instruction to obtain a first document disassembly scheme; according to the first document disassembly scheme, document disassembly is carried out on the second file, and a third file is obtained; obtaining a first keyword extraction instruction, and extracting keywords from the third file according to the first keyword extraction instruction to obtain a first keyword extraction result; constructing a first mapping retrieval classification relation between the keywords and the third file according to the first keyword extraction result; acquiring a first semantic aggregation instruction, and performing semantic aggregation analysis on the third file according to the first semantic aggregation instruction to acquire a first semantic aggregation result; constructing a second mapping retrieval classification relation between the semantics and the third archive according to the first semantic aggregation result, wherein the mapping grade of the second mapping retrieval classification relation is higher than that of the first mapping retrieval classification relation; inputting the second mapping retrieval classification relation and the first mapping retrieval classification relation into a mapping result analysis model to obtain a third mapping retrieval classification relation; and classifying the files of the first file based on the mapping relation according to the third mapping retrieval classification relation. The technical problem that classification arrangement of files is not scientific and accurate enough when the files are classified and arranged in the prior art is solved, and the technical effect of intelligent and accurate classification arrangement of files based on semantic mapping is achieved.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course may be implemented by dedicated hardware including application specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components and the like. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. However, a software program implementation is a preferred embodiment in many cases for the present application. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., including several instructions for causing a computer device to perform the method described in the embodiments of the present application.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.
The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from a computer-readable storage medium, which may be magnetic media, (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid State Disks (SSDs)), among others.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
In addition, the terms "system" and "network" are often used interchangeably herein. The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
It should be understood that in the embodiments of the present application, "B corresponding to a" means that B is associated with a, from which B may be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In summary, the foregoing description is only a preferred embodiment of the technical solution of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (4)
1. A semantic mapping-based object classification method, wherein the method is applied to a mapping classification system communicatively coupled to a first image acquisition device, the system comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method when executing the program, the method comprising:
acquiring a first acquisition instruction, and acquiring a first image through the first image acquisition device according to the first acquisition instruction, wherein the first image is an image of a first file;
obtaining a first document conversion instruction, and converting the first image format according to the first document conversion instruction to obtain a second file;
obtaining a first document disassembly evaluation instruction, and carrying out document disassembly evaluation on the second file according to the first document disassembly evaluation instruction to obtain a first document disassembly scheme;
According to the first document disassembly scheme, document disassembly is carried out on the second file, and a third file is obtained;
obtaining a first keyword extraction instruction, and extracting keywords from the third file according to the first keyword extraction instruction to obtain a first keyword extraction result;
constructing a first mapping retrieval classification relation between the keywords and the third file according to the first keyword extraction result;
acquiring a first semantic aggregation instruction, and performing semantic aggregation analysis on the third file according to the first semantic aggregation instruction to acquire a first semantic aggregation result;
constructing a second mapping retrieval classification relation between the semantics and the third archive according to the first semantic aggregation result, wherein the mapping grade of the second mapping retrieval classification relation is higher than that of the first mapping retrieval classification relation;
inputting the second mapping retrieval classification relation and the first mapping retrieval classification relation into a mapping result analysis model to obtain a third mapping retrieval classification relation;
carrying out file classification based on the mapping relation on the first file according to the third mapping retrieval classification relation;
the method further comprises the steps of:
Obtaining a first semantic deep analysis instruction;
performing deep semantic analysis on the third file according to the first semantic deep analysis instruction to obtain a first deep analysis result, wherein the first deep analysis result comprises: obtaining a first logical relationship expression word set; constructing a first semantic knowledge database according to the first logical relation expression word set, wherein the first semantic knowledge database is a database for carrying out latent semantic analysis; performing deep semantic analysis on the third file according to the first semantic knowledge database to obtain a first deep semantic analysis result;
extracting a position keyword according to the first deep analysis result, and constructing a fourth mapping retrieval classification relation according to the position keyword and the third file, wherein the mapping grade of the fourth mapping retrieval classification relation is higher than that of the third mapping retrieval classification relation;
inputting the third mapping retrieval classification relation and the fourth mapping retrieval classification relation into a mapping result analysis model to obtain a fifth mapping retrieval classification relation;
carrying out file classification based on the mapping relation on the first file according to the fifth mapping retrieval classification relation;
Obtaining a first detection instruction, and detecting the mapping relation of the same position of the first file according to the first detection instruction to obtain a first detection result;
judging whether the first detection result contains at least two layers of mapping relations or not;
when the first detection result comprises at least two layers of mapping relations, a first evaluation instruction is obtained;
performing association degree evaluation on the multi-layer mapping relation in the first detection result according to the first evaluation instruction to obtain a first association degree evaluation result;
obtaining a first association degree evaluation preset threshold value;
judging whether the first relevancy assessment result meets the first relevancy assessment preset threshold value or not;
and when the first relevance evaluation result does not meet the first relevance evaluation preset threshold, only reserving the mapping retrieval classification relation with the highest mapping level in the first detection result.
2. The method of claim 1, wherein the method further comprises:
when the first relevancy assessment result meets the first relevancy assessment preset threshold value, a first ordering instruction is obtained;
performing mapping grade sorting on the mapping retrieval classification relation in the first detection result according to the first sorting instruction to obtain a first sorting result;
And classifying the files based on the mapping relation for the first file according to the first sorting result.
3. The method of claim 2, wherein the method further comprises:
constructing a first encryption mapping database;
inputting the mapping retrieval classification relation into the first encryption mapping database to obtain a sixth mapping retrieval classification relation set;
encrypting the mapping relation in the sixth mapping retrieval classification relation set to obtain a first encryption processing result, and adjusting the mapping grade in the sixth mapping retrieval classification relation set to be a confidentiality grade according to the first encryption processing result;
and carrying out encryption classification based on the mapping relation on the first document according to the sixth mapping retrieval classification relation set.
4. The method of claim 1, wherein said inputting the second map search classification relationship and the first map search classification relationship into a map result analysis model to obtain a third map search classification relationship further comprises:
obtaining a mapping result analysis model, wherein the mapping result analysis model is a model obtained through training of multiple sets of training data, and each set of the multiple sets of training data comprises the second mapping retrieval classification relation, the first mapping retrieval classification relation and identification information for identifying a mapping relation analysis result;
And inputting the second mapping search classification relation and the first mapping search classification relation into the mapping result analysis model to obtain a first output result, wherein the first output result comprises the third mapping search classification relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110642057.1A CN113282752B (en) | 2021-06-09 | 2021-06-09 | Object classification method and system based on semantic mapping |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110642057.1A CN113282752B (en) | 2021-06-09 | 2021-06-09 | Object classification method and system based on semantic mapping |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113282752A CN113282752A (en) | 2021-08-20 |
| CN113282752B true CN113282752B (en) | 2023-04-25 |
Family
ID=77283845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110642057.1A Active CN113282752B (en) | 2021-06-09 | 2021-06-09 | Object classification method and system based on semantic mapping |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113282752B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822021B (en) * | 2021-08-23 | 2024-03-01 | 太原市高远时代科技有限公司 | Method and system for realizing file format conversion of test case |
| CN114003553B (en) * | 2021-09-27 | 2023-12-15 | 上海金慧软件有限公司 | Intelligent counting display method and device for drawing management |
| CN114333829B (en) * | 2022-03-09 | 2022-06-17 | 北京中科开迪软件有限公司 | Method and system for searching optical disk digital archive by voice |
| CN114706960B (en) * | 2022-06-06 | 2022-08-09 | 济南市干部人事档案服务中心 | File information checking method based on cloud computing and file checking terminal |
| CN115774805B (en) * | 2023-02-10 | 2023-04-28 | 江苏联著实业股份有限公司 | File intelligent query method and system based on digital processing |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3528849B2 (en) * | 2003-06-25 | 2004-05-24 | 富士ゼロックス株式会社 | Keyword extraction device and keyword extraction method |
| US8666928B2 (en) * | 2005-08-01 | 2014-03-04 | Evi Technologies Limited | Knowledge repository |
| CN104731797B (en) * | 2013-12-19 | 2018-09-18 | 北京新媒传信科技有限公司 | A kind of method and device of extraction keyword |
| CN106156204B (en) * | 2015-04-23 | 2020-05-29 | 深圳市腾讯计算机系统有限公司 | Text label extraction method and device |
| CN109800303A (en) * | 2018-12-28 | 2019-05-24 | 深圳市世强元件网络有限公司 | A kind of document information extracting method, storage medium and terminal |
| CN112818117A (en) * | 2021-01-19 | 2021-05-18 | 新华智云科技有限公司 | Label mapping method, system and computer readable storage medium |
-
2021
- 2021-06-09 CN CN202110642057.1A patent/CN113282752B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113282752A (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113282752B (en) | Object classification method and system based on semantic mapping | |
| CN107291723B (en) | Method and device for classifying webpage texts and method and device for identifying webpage texts | |
| RU2678716C1 (en) | Use of autoencoders for learning text classifiers in natural language | |
| CN111680490B (en) | Cross-modal document processing method and device and electronic equipment | |
| El et al. | Authorship analysis studies: A survey | |
| US9483460B2 (en) | Automated formation of specialized dictionaries | |
| CN110427612B (en) | Entity disambiguation method, device, equipment and storage medium based on multiple languages | |
| CN110083832B (en) | Article reprint relation identification method, device, equipment and readable storage medium | |
| CN112182148B (en) | Standard aided writing method based on full text retrieval | |
| US20220358379A1 (en) | System, apparatus and method of managing knowledge generated from technical data | |
| CN108228612B (en) | Method and device for extracting network event keywords and emotional tendency | |
| CN111159389A (en) | Keyword extraction method based on patent elements, terminal and readable storage medium | |
| ALBayari et al. | Cyberbullying classification methods for Arabic: A systematic review | |
| CN113806493A (en) | Entity relationship joint extraction method and device for Internet text data | |
| WO2020091618A1 (en) | System for identifying named entities with dynamic parameters | |
| Panchenko et al. | Detection of child sexual abuse media on p2p networks: Normalization and classification of associated filenames | |
| KR102280490B1 (en) | Training data construction method for automatically generating training data for artificial intelligence model for counseling intention classification | |
| CN113722492A (en) | Intention identification method and device | |
| CN112818206A (en) | Data classification method, device, terminal and storage medium | |
| Müller-Budack et al. | Finding person relations in image data of news collections in the internet archive | |
| Saini et al. | Intrinsic plagiarism detection system using stylometric features and DBSCAN | |
| CN111611394B (en) | Text classification method and device, electronic equipment and readable storage medium | |
| CN111341404B (en) | Electronic medical record data set analysis method and system based on ernie model | |
| CN113868424A (en) | Text theme determining method and device, computer equipment and storage medium | |
| Cholissodin et al. | Audit system development for government institution documents using stream deep learning to support smart governance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |