Platform and method for analyzing and applying QC document and media thereof

Abstract

The invention discloses an analysis application platform and method for a QC document and media thereof, and belongs to the technical field of document and media content analysis. The platform comprises a document analysis module, a video text recognition module, a media voice recognition module, a retrieval module, a relational graph drawing module and an authority management module; the document analysis module is used for carrying out content extraction and word segmentation storage on a QC document uploaded by a user; the media voice recognition module and the video text recognition module are respectively used for performing voice and text recognition on media videos which are uploaded by a user and are associated with the QC document; the retrieval module is used for retrieving and displaying documents and video contents by adopting a dynamic weighted similarity algorithm; the relational graph drawing module is used for drawing a relational graph on line; and the authority management module is used for setting and managing the authority of the platform user. The efficiency and accuracy of QC document management and information retrieval are effectively improved, rapid sharing and tracing of information are achieved, and the quality control process is optimized.

Description

Technical Field

[0001] The invention belongs to the technical field of document and media content analysis, and relates to a QC document and media analysis application platform and method. Background Art

[0002] In the current quality control (QC) document management process, processing a large number of QC documents and their associated media files, such as video and audio, is a highly manual task. Traditional processing methods usually require manual browsing of documents one by one, viewing video content, and manually recording or analyzing information. This method has the following obvious defects and shortcomings: Low efficiency: The volume of QC documents and their associated media files is large. Manual processing is not only time-consuming, but also prone to omissions or misjudgments, resulting in low overall efficiency.

[0003] Isolated information is difficult to integrate: The correlation between text, images and video content in QC documents is weak, and there is a lack of a unified processing mechanism. Information extraction and sharing are inconvenient, making it difficult to achieve rapid query and comprehensive tracking.

[0004] Difficulty in tracing: In future quality control inspections or problem tracing, traditional document and video management methods cannot effectively support the rapid search for specific content, which poses a great challenge to problem troubleshooting and analysis.

[0005] Especially in quality control work, accurate and timely analysis and search of relevant documents and video content is crucial, and the existing manual or semi-automatic processing methods can no longer meet the current high requirements of efficiency and accuracy in the quality control industry. Therefore, there is an urgent need for a more intelligent and automated QCQC document and media analysis application platform to improve work efficiency, ensure the comprehensiveness and accuracy of information, and support efficient content retrieval and traceability. Summary of the invention

[0006] In order to solve the deficiencies in the prior art, the present invention provides a QC document and media parsing application platform and method, which can efficiently and accurately parse QC documents and multimedia attachments, and support content-based full-text retrieval and tracing. By automatically and uniformly parsing, storing and retrieving text, pictures and audio content, manual operations are greatly reduced, the efficiency and accuracy of QC document management and information retrieval are effectively improved, the rapid sharing and tracing of information are realized, the quality control process is optimized, and a more intelligent management means is provided for the QC work of the enterprise.

[0007] The present invention adopts the following technical solution.

[0008] The first aspect of the present invention provides a QC document and media analysis application platform, including a document analysis module, a video text recognition module, a media voice recognition module, a retrieval module, a relationship diagram drawing module and a rights management module; The document parsing module is used to extract the content of the QC documents uploaded by the user and store them by categories; The media voice recognition module and the video text recognition module are used to perform voice and text recognition on the media videos uploaded by the user and associated with the QC document, respectively; The retrieval module is used to retrieve and display documents and video content using a dynamic weighted similarity algorithm; The relationship graph drawing module is used to draw the relationship graph online in real time based on the graph data structure; The authority management module is used for role management, batch maintenance and configuration of user authorities.

[0009] Preferably, the document parsing module extracts and parses the text content and image data in the QC document by combining document content extraction technology with OCR recognition technology, and stores them in the database and Elasticsearch. The text content and image data are classified, stored and indexed according to the document structure.

[0010] Preferably, the document parsing module displays the document parsing progress in real time and provides an exception prompt function. When an exception occurs during the parsing process, the exception is displayed immediately.

[0011] Preferably, the media speech recognition module uses an audio processing tool to extract audio content from the media video; The video text recognition module transcribes the audio content into text content through a speech recognition model, extracts key information according to the document structure and stores it in a database and Elasticsearch, and associates it with the corresponding QC document.

[0012] Preferably, the retrieval module performs full-text retrieval according to the query conditions input by the user through a dynamic weighted similarity algorithm, matches the text content of the corresponding QC document, the text content transcribed from the image data and the audio content, and displays the QC documents and media videos containing relevant content.

[0013] Preferably, the algorithm flow of the dynamic weighted similarity algorithm includes: The query conditions entered by the user and the text content in the QC document are processed by word vectorization, and then the dynamic weighted similarity between the query conditions and the QC document is calculated based on the word vector. The text content of the most matching QC document is obtained based on the dynamic weighted similarity, and the image data associated with the text content and the text content obtained by transcribing the audio content are obtained from the database and Elasticsearch.

[0014] Preferably, the calculation formula of the dynamic weighted similarity is: , in: For query conditions and text content Dynamic weighted similarity of; For text content Middle Field The weight of For Field Dynamic factors; is the normalization factor; For text content The number of fields in ; For query conditions Text content field No. The query word vector that matches the word vector; For Field Middle word vectors; For Field The number of word vectors in .

[0015] Preferably, the dynamic factor The calculation formula is: , , , , in, For Field In the text content The global importance of For Field Local relevance to the query conditions; U i Adjustment factor for user behavior feedback; , For Field , Field The word vector of the text content The frequency of words in ; Respectively query term vectors and fields Middle word vectors; is the cosine function; is the weight adjustment parameter; The field in the hth interaction in the user's historical behavior record Importance rating; Field in the hth interaction in the user's historical behavior record relevance; is the total number of samples in the user's history.

[0016] Preferably, the importance score The calculation formula is: , in, For the Interaction fields The probability of the corresponding content being clicked; For the Interaction fields Average dwell time of the corresponding content; For the From the field The proportion of actions that lead to download, open or preview; is the weight parameter.

[0017] Preferably, the correlation The calculation formula is: , in, For the The semantic vector of the user query in the interaction; For Field In the The semantic vector of the interaction content.

[0018] Preferably, the normalization factor The calculation formula is: , in, Indicates the influence coefficient of user feedback on field length normalization.

[0019] Preferably, the relationship graph drawing module draws the relationship graph online in real time based on the graph data structure, including: Based on the nodes and edges of the graph data structure, the relationship diagram is drawn online in real time in the browser, and the node arrangement can be freely set. The nodes and edges can be edited through the event mechanism or the node position can be adjusted by dragging.

[0020] Preferably, the permission management module is based on a role management mechanism, manages user permissions through roles, assigns permission configurations to different roles, and assigns one or more roles to users through batch maintenance, and configures permissions according to actual needs.

[0021] Preferably, the platform adopts a B / S architecture and is deployed in a variety of operating system environments, and the permissions of the various operating systems are associated, and can be expanded in different regions or departments according to needs.

[0022] A second aspect of the present invention provides a method for parsing and applying a QC document and its media, comprising: Extract content and classify and store QC documents uploaded by users; Perform voice and text recognition on media videos uploaded by users and associated with QC documents; Use dynamic weighted similarity algorithm to retrieve and display document and video content; Draw relationship diagrams online in real time based on graph data structures; Through role management, batch maintenance and configuration of user permissions.

[0023] Compared with the prior art, the beneficial effects of the present invention include at least: (1): Openness: The analytical application platform of the present invention is based on an open technical architecture and has good scalability and portability. The platform can be deployed in a variety of operating system environments, such as Linux or Windows, supports permission association, and can be flexibly expanded in different regions or departments according to needs. The system design allows integration with other business systems or data platforms, providing convenience for subsequent function expansion and third-party system docking.

[0024] (2) Practicality and friendliness: The analytical application platform of the present invention adopts a B / S architecture, has a simple and intuitive interface, is user-friendly, supports simultaneous operation by multiple users, and is highly practical.

[0025] (3) Compatibility and advancement: The analysis application platform of the present invention adopts advanced document analysis and speech recognition technology, and can process a variety of document formats as well as audio and video formats. The platform has strong compatibility and supports seamless integration with the company's existing content management systems, databases, search engines and other tools, making it convenient to share and call data with other business systems. At the same time, the platform has advanced functions such as audio-to-text and full-text retrieval, which greatly improves the efficiency of information management.

[0026] (4) Efficiency: The analysis application platform of the present invention can efficiently process large-scale QC documents and multimedia attachments. Through batch uploading and parallel analysis, the platform can quickly extract text, pictures and audio content, and display the analysis progress in real time, reducing user waiting time; at the same time, the retrieval module supports accurate keyword-based search to help users quickly find the required documents and related multimedia content. The efficient processing capability significantly improves the speed and accuracy of document management.

[0027] (5) Security: The analytical application platform of the present invention has powerful security management functions, supports user authority control and encryption technology, and ensures the security of documents and media content. The platform's access control policy can be customized according to company needs to ensure that only authorized users can access and operate. At the same time, the platform can also set up system modules to support logging and auditing processes to ensure transparency and security compliance of data use, which is particularly suitable for quality control scenarios involving sensitive information.

[0028] (6) Dynamic weighted similarity algorithm: Dynamic factors and normalization factors are introduced. The dynamic factor can dynamically adjust the weight based on the importance of the field in the global and local contexts. The normalization factor solves the impact of field length on similarity, so that long fields will not have too high similarity scores due to the large number of words, which can significantly improve the accuracy of search results. In addition, the user behavior feedback adjustment factor is applied to the dynamic factor and the normalization factor, which takes into account the impact of user behavior feedback on weight allocation and the impact of user behavior feedback on the trade-off of field length in similarity calculation. Intelligent semantic matching: Retrieval is no longer limited to simple keyword matching, but is able to understand the contextual semantics of the text to achieve more accurate content matching.

[0029] Efficient full-text retrieval: The combination of NLP and Elasticsearch ensures the efficiency of the system and can quickly respond to user query needs in large-scale documents and multimedia data.

[0030] Improved user experience: The system not only displays the retrieved documents, but also intuitively displays the matching paragraphs and related images, allowing users to quickly locate the required content.

[0031] (7) The relationship diagram drawing module supports users to draw relationship diagrams directly in the browser without downloading additional software, which greatly facilitates use; the module supports automatic definition of layout, and users can also freely set the node arrangement method, which enhances the flexibility of drawing; through the event mechanism, users can easily edit nodes and edges by right-clicking, or adjust the node position by dragging, which improves the user experience.

[0032] (8) The permission management module manages user permissions through roles and assigns permission configurations to different roles, which simplifies the permission management process and improves management efficiency. It has batch maintenance capabilities, allowing users to quickly assign one or more roles to users, facilitating batch permission maintenance and reducing duplication of work and the possibility of errors. Users can flexibly configure permissions based on actual needs to ensure that users can only access the functions they need, thereby enhancing the security and controllability of the platform.

[0033] (9) The document parsing module can automatically extract key information, such as the image title, by accurately locating the location of the image data. It can also identify the attributes and type of the image based on the image title and associate the document paragraph to which the image belongs. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the architecture of the analysis application platform of the QC document and its media of the present invention; Figure 2 This is a schematic diagram of the document parsing and retrieval business process of the present invention; Figure 3 This is a schematic diagram of the video text recognition and retrieval business process of the present invention; Figure 4 The present invention integrates Elasticsearch with NLP retrieval process. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0036] like Figure 1 As shown, Embodiment 1 of the present invention provides a QC document and its media parsing application platform, which solves the problems of low efficiency, information isolation and difficulty in retrieval in the existing QC document and its multimedia content parsing, and specifically includes a document parsing module, a video text recognition module, a media voice recognition module, a retrieval module, a relationship diagram drawing module and a rights management module; The document parsing module is used to extract content and store word segments of the QC documents uploaded by users; More preferably, if Figure 2As shown, the document parsing module is mainly used to automatically extract text and image content from documents submitted by users through document content extraction technology combined with OCR recognition technology, and store them in the database and Elasticsearch. The text content and image data are classified, stored and indexed according to the document structure to facilitate subsequent retrieval and management. Compared with traditional image recognition and content extraction methods, the document parsing module of this platform can also accurately locate the location of image data, automatically extract key information, such as image titles, and identify the attributes and types of images based on the image titles, and at the same time associate the document paragraph to which the image belongs.

[0037] Furthermore, the document parsing module supports multiple file uploads. Users can upload multiple PDF documents or compressed packages containing multiple documents. It supports multiple document formats (such as PDF, Word, etc.). Through OCR (optical character recognition) technology, after the document is uploaded, the system stores it on the server and starts automatic parsing. Through PDF and other parsing tools, the system can extract text paragraphs and pictures in each document, accurately identify the text content in the picture, and store it with other text paragraphs in the document. The parsed text and pictures will be stored in the database and Elasticsearch for subsequent full-text retrieval and information tracking.

[0038] Furthermore, the document parsing module includes content classification and annotation functions, which can automatically identify document structures, such as titles, paragraphs, pictures, etc., and store and index them according to different categories, providing more accurate data support for subsequent retrieval. Picture data will also be stored and indexed according to the document structure.

[0039] The document parsing module also supports real-time display of document parsing progress and provides an exception prompt function. When an exception occurs during the parsing process, the system will immediately display the exception to help users quickly locate and solve the problem, thereby ensuring the smooth progress of the parsing process. Users can view the real-time progress of document parsing and clearly understand the processing status of each document, avoiding the problem of long waiting time caused by large-scale file uploads.

[0040] The media voice recognition module and the video text recognition module are used to perform voice and text recognition on the media videos uploaded by the user and associated with the QC document, respectively; More preferably, if Figure 3 As shown, the media speech recognition module and the video text recognition module are mainly used to extract audio content from video files through audio and video analysis technology, and perform speech-to-text processing on the audio, and finally store the transcribed text content in Elasticsearch for subsequent full-text retrieval.

[0041] Users can upload multiple multimedia files (audio and video) associated with QC documents. The uploaded media files will be stored in the system and associated with the corresponding QC documents; Audio Extraction: Use FFmpeg to extract audio files from videos, supporting parsing and processing of multiple video formats (such as MP4, AVI, etc.). The extracted audio files will be further identified and processed.

[0042] Audio to text: The extracted audio files are transcribed through a speech recognition model (such as ASR, automatic speech recognition), and the system can convert the speech content in the audio into structured text. The recognition process supports the recognition of multiple languages ​​and industry terms to ensure the accuracy of the text content.

[0043] Furthermore, when the video text recognition module converts audio to text, it supports optimizing recognition accuracy through machine learning, and combines language models for specific scenarios to improve the recognition of professional terms or complex audio. The system will extract key information according to the document structure, automatically identify and mark keywords, document titles, authors, groups and other information, and store the results of voice-to-text conversion in the database and Elasticsearch for subsequent full-text retrieval.

[0044] Data association: Each audio transcription text result will be automatically associated with the corresponding QC document, ensuring that users can retrieve relevant multimedia content through QC document information, facilitating subsequent retrieval of media attachments through QC project information.

[0045] The retrieval module is used to retrieve and display documents and video content using a dynamic weighted similarity algorithm; Further preferably, the retrieval module provides users with a powerful full-text search function, allowing fast search of QC documents and their multimedia attachments by keywords.

[0046] Full-text search and accurate display: Users can enter keywords for search, and the system will match the text content, image descriptions, and audio transcriptions of QC documents, and display documents and multimedia attachments containing relevant content, as follows: By integrating Elasticsearch's natural language processing (NLP) algorithm and combining keyword full-text search technology, the accuracy and intelligence of document retrieval are improved. Based on the text analysis function of NLP, the system can semantically understand the content in the document, so that when searching, it not only relies on simple keyword matching, but also can realize semantic-based intelligent search.

[0047] NLP retrieval in Elasticsearch relies on text embedding and semantic matching technologies. The main process includes the following steps: 1) Text preprocessing: Preprocess the text content and generate semantic embeddings through deep learning models (such as pre-trained models like BERT, RoBERTa, etc.). The preprocessing includes stemming, stop word removal, synonym expansion, etc. Extract the key information of the document, including the title, author, company, QC group, and paragraphs of the document. Specifically, it includes: Perform unified preprocessing on all parsed content, including the following steps: Stemming: Use the stemming algorithm of NLTK to remove the inflections of words (such as plurals, tense changes).

[0048] Lemmatization: Utilize dictionary libraries such as WordNet to restore words to their standard forms and unify the expressions.

[0049] Stop word filtering: Delete meaningless stop words (such as "in", "is", etc.) to reduce noise.

[0050] Synonym expansion:借助Word2Vec或预训练词向量模型,生成查询词的同义词列表,用于扩展查询覆盖范围,公式如下: , where is the vector representation of the word , is the vector representation of the candidate synonym. Determine the synonym relationship by calculating the cosine similarity. is the threshold, is the cosine function.

[0051] 2) Vectorization processing: NLP models (such as BERT, Word2Vec, etc.) convert sentences or paragraphs in the document into numerical vector representations. The text of each document is converted into a vector (embedding) of a fixed dimension through the model to capture the semantic relationships between words.

[0052] Specifically, use the BERT pre-trained language model to generate the semantic vector of the text: Sentence vector generation: Input each paragraph into the model to obtain the vector representation of each word ; Use the CLS vector or the average vector to generate the embedding representation of the paragraph or the embedding representation of the sentence : , Vector storage: Store the generated vectors through vector databases such as Elasticsearch to provide a basis for subsequent similarity retrieval.

[0053] It realizes multi-dimensional semantic understanding, improves the intelligence of text matching, and makes the search results more semantically relevant.

[0054] 3) Similarity calculation: After the semantic vector is generated, it is matched by weighted cosine similarity. The weights are adjusted dynamically according to the importance of different fields, and a dynamic factor C is introduced. i Through this factor, the weight is dynamically adjusted based on the importance of the field in the global and local context to improve the personalization and accuracy of the search results: Query vector generation: After the user enters a query, the same BERT model is used to convert the query text into a query vector .

[0055] Weighted cosine similarity calculation: weights of weighted cosine similarity This is usually done in the following ways to ensure that certain specific fields (such as titles, keywords, etc.) are given higher priority in similarity calculations.

[0056] Specific weight setting methods include manual setting based on domain knowledge, weight determination based on statistical analysis, and dynamic weight optimization based on machine learning.

[0057] Manual weight setting in the early stage: You can combine domain knowledge and statistical analysis to manually set weights to lay a good foundation for the model. The manual setting example is as follows: , Based on statistical analysis weights: TF-IDF (Term Frequency-Inverse Document Frequency) analysis: can be used to measure the weights of different fields. For example, the title may have a low word frequency, but a high information density, and a high IDF value for keywords, so a higher weight is assigned.

[0058] , Machine learning in the mature stage: The weights of different fields are automatically adjusted through machine learning methods, so that the weighted cosine similarity score can better reflect the real needs of users. When the system obtains the user's interaction data (such as clicks, likes, etc.), the field weights can be trained through machine learning models (such as LightGBM, XGBoost). The goal is to improve the accuracy of the system's recommended content by optimizing the weights.

[0059] The training steps are: collect user query and click data; use field similarity scores as features and click-through rate or user feedback as target variables; optimize field weights through model training to obtain the optimal weight combination .

[0060] The weights determined by the above method can enable the system to more accurately capture the semantic intent of user queries, thereby obtaining better similarity calculation results in multiple content types.

[0061] Further preferably, the present invention adopts a dynamic weighted similarity algorithm to assign different weights to different fields (such as title, author, content, etc.) to highlight the matching degree of the query field. The calculation formula is as follows: , in: Field weights are adjusted dynamically by manual or machine learning algorithms; is the dynamic weight adjustment factor, which is calculated by the following formula: , : The global importance of the field in the entire document collection, based on the TF-IDF score of the field content, calculated by the following formula: , in, For Field The TF-IDF score in the document.

[0062] : The local relevance of the field in the current document, based on the field's content density (word frequency) or semantic similarity score, calculated using the following formula: , in, and Respectively represent Semantic vectors of query terms and field content terms.

[0063] It is the user behavior feedback adjustment factor, which directly participates in the context dynamic weight adjustment and reflects the importance of user behavior to the field. It is calculated as follows: , : Field The importance score of the hth interaction in the user's historical behavior record (based on indicators such as click-through rate, dwell time, conversion rate, etc.). The calculation formula is: , in, For the Interaction fields The probability of the corresponding content being clicked; For the Interaction fields The average dwell time of the corresponding content; For the From the field The proportion of actions that lead to download, open or preview; is a weight parameter, which can be determined by experiments or machine learning methods.

[0064] : Field in the hth interaction in the user's historical behavior record The correlation (which can be calculated by semantic similarity) is calculated as follows: , in, For the The semantic vector of the user query in the interaction; For Field In the The semantic vector of the interaction content. : Cosine similarity of semantic vectors.

[0065] : The total number of samples in the user's history.

[0066] : Weight adjustment parameter ( ), determined by experiments or automatic optimization.

[0067] is a normalization factor used to address the impact of field length on similarity, so that long fields will not have too high similarity scores due to the large number of words; i Indicates the number of word segments of field i, represents the influence coefficient of user feedback on the normalization of field length, Represents the user behavior feedback adjustment factor, which is used to amplify or suppress the effect of field length on similarity calculation.

[0068] The user behavior feedback adjustment factor Ui is applied to the normalization factor to reflect the correction effect of user feedback on field length, so that user behavior feedback not only affects the weight distribution, but also indirectly affects the trade-off of field length in similarity calculation.

[0069] When field normalization or weight optimization is not required, , , we can return to the original formula, where Manually set initial weight for field i.

[0070] The formula is explained as follows: Assumptions is the document to be retrieved, including fields, the vector representation of each field is considered when calculating the weighted similarity: , in: For text content Middle Field The weight of For Field Dynamic factors; For text content The number of fields in ; For query conditions Text content field No. The query word vector that matches the word vector; For Field The number of word vectors in ; For Field Middle word vectors; is the normalization factor.

[0071] Weight optimization: Optimize weights based on user feedback or using supervised learning algorithms (such as gradient descent) to adapt the system to user search needs and improve search accuracy.

[0072] By calculating the similarity score, the retrieval module can provide users with the document content that best matches the query semantics, and obtain the image data associated with the document content and the text content transcribed from the audio content.

[0073] 4) Result display and sorting: For QC documents, the search results will display the paragraphs that match the keywords according to the defined document weight rules, allowing users to quickly locate the information they need. For media videos, the text content transcribed from the audio content associated with the QC document that best matches the keyword or sentence is displayed.

[0074] The system will sort the search results according to the similarity score and display the documents with the highest similarity to the user first. At the same time, the system supports displaying matching paragraphs and related images in specific documents to improve the user experience.

[0075] How NLP works in ES is as follows Figure 4 As shown, including: The user submits a keyword or sentence query Q.

[0076] The query content is processed by the NLP model to generate a query vector .

[0077] The system converts the content in the document into vectors And stored in ES.

[0078] The similarity between the query vector and the document vector is calculated through dynamic weighted similarity.

[0079] The search results are displayed in order of similarity, including matching document paragraphs and image content.

[0080] By integrating NLP algorithms, the document parsing and retrieval module has the following advantages: Intelligent semantic matching: Retrieval is no longer limited to simple keyword matching, but is able to understand the contextual semantics of the text to achieve more accurate content matching.

[0081] Efficient full-text retrieval: The combination of NLP and Elasticsearch ensures the efficiency of the system and can quickly respond to user query needs in large-scale documents and multimedia data.

[0082] Improved user experience: The system not only displays the retrieved documents, but also intuitively displays the matching paragraphs and related images, allowing users to quickly locate the required content.

[0083] The retrieval module supports full-text retrieval based on audio text, and users can quickly search for video-related content by entering keywords. The system will accurately locate the media text content containing the keyword and display it in association with the video file, making it convenient for users to directly jump to the relevant clips in the video for viewing, and display the associated QC information in association.

[0084] Furthermore, the retrieval module also supports complex query conditions, such as filtering functions based on date, document type, and associated media type, to help users obtain the required information more accurately.

[0085] The relationship graph drawing module is used to draw the relationship graph online in real time based on the graph data structure; Further preferably, the module supports users to draw a relationship graph online in real time, based on a graph data structure, which consists of nodes and edges. The data model is usually represented in the form of a JSON object.

[0086] Browser support: Users can draw relationship diagrams directly in the browser without downloading additional software, which greatly facilitates use.

[0087] Smart layout: The module supports automatic definition of layout, and users can also freely set the node arrangement method, which enhances the flexibility of drawing.

[0088] Convenient operation mechanism: Through the event mechanism, users can easily edit nodes and edges by right-clicking, or adjust the node position by dragging, which improves the user experience.

[0089] The authority management module is used for role management, batch maintenance and configuration of user authorities.

[0090] Further preferably, the rights management module provides a role management mechanism: User permissions are managed through roles, and permission configurations are assigned to different roles, which simplifies the permission management process and improves management efficiency.

[0091] Batch maintenance capability: Users can quickly assign one or more roles to users to facilitate batch permission maintenance, reducing duplication of work and the possibility of errors.

[0092] Flexible permission configuration: Users can flexibly configure permissions according to actual needs to ensure that users can only access the functions they need, enhancing the security and controllability of the platform.

[0093] Embodiment 2 of the present invention provides a method for parsing and applying a QC document and its media, including: Extract content and classify and store QC documents uploaded by users; Perform voice and text recognition on media videos uploaded by users and associated with QC documents; Use dynamic weighted similarity algorithm to retrieve and display document and video content; Draw relationship diagrams online in real time based on graph data structures; Through role management, batch maintenance and configuration of user permissions.

[0094] Embodiment 3 of the present invention provides a terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method.

[0095] Embodiment 4 of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method when executed by a processor.

[0096] Compared with the prior art, the beneficial effects of the present invention include at least: (1): Openness: The analytical application platform of the present invention is based on an open technical architecture and has good scalability and portability. The platform can be deployed in a variety of operating system environments, such as Linux or Windows, supports permission association, and can be flexibly expanded in different regions or departments according to needs. The system design allows integration with other business systems or data platforms, providing convenience for subsequent function expansion and third-party system docking.

[0097] (2) Practicality and friendliness: The analytical application platform of the present invention adopts a B / S architecture, has a simple and intuitive interface, is user-friendly, supports simultaneous operation by multiple users, and is highly practical.

[0098] (3) Compatibility and advancement: The analysis application platform of the present invention adopts advanced document analysis and speech recognition technology, and can process a variety of document formats as well as audio and video formats. The platform has strong compatibility and supports seamless integration with the company's existing content management systems, databases, search engines and other tools, making it convenient to share and call data with other business systems. At the same time, the platform has advanced functions such as audio-to-text and full-text retrieval, which greatly improves the efficiency of information management.

[0099] (4) Efficiency: The analysis application platform of the present invention can efficiently process large-scale QC documents and multimedia attachments. Through batch uploading and parallel analysis, the platform can quickly extract text, pictures and audio content, and display the analysis progress in real time, reducing user waiting time; at the same time, the retrieval module supports accurate keyword-based search to help users quickly find the required documents and related multimedia content. The efficient processing capability significantly improves the speed and accuracy of document management.

[0100] (5) Security: The analytical application platform of the present invention has powerful security management functions, supports user authority control and encryption technology, and ensures the security of documents and media content. The platform's access control policy can be customized according to company needs to ensure that only authorized users can access and operate. At the same time, the platform supports logging and auditing processes to ensure transparency and security compliance of data use, which is particularly suitable for quality control scenarios involving sensitive information.

[0101] (6) Dynamic weighted similarity algorithm: Dynamic factors and normalization factors are introduced. The dynamic factor can dynamically adjust the weight based on the importance of the field in the global and local contexts. The normalization factor solves the impact of field length on similarity, so that long fields will not have too high similarity scores due to the large number of words, which can significantly improve the accuracy of search results. In addition, the user behavior feedback adjustment factor is applied to the dynamic factor and the normalization factor, which takes into account the impact of user behavior feedback on weight allocation and the impact of user behavior feedback on the trade-off of field length in similarity calculation. Intelligent semantic matching: Retrieval is no longer limited to simple keyword matching, but is able to understand the contextual semantics of the text to achieve more accurate content matching.

[0102] Efficient full-text retrieval: The combination of NLP and Elasticsearch ensures the efficiency of the system and can quickly respond to user query needs in large-scale documents and multimedia data.

[0103] Improved user experience: The system not only displays the retrieved documents, but also intuitively displays the matching paragraphs and related images, allowing users to quickly locate the required content.

[0104] (7) The relationship diagram drawing module supports users to draw relationship diagrams directly in the browser without downloading additional software, which greatly facilitates use; the module supports automatic definition of layout, and users can also freely set the node arrangement method, which enhances the flexibility of drawing; through the event mechanism, users can easily edit nodes and edges by right-clicking, or adjust the node position by dragging, which improves the user experience.

[0105] (8) The permission management module manages user permissions through roles and assigns permission configurations to different roles, which simplifies the permission management process and improves management efficiency. It has batch maintenance capabilities, allowing users to quickly assign one or more roles to users, facilitating batch permission maintenance and reducing duplication of work and the possibility of errors. Users can flexibly configure permissions based on actual needs to ensure that users can only access the functions they need, thereby enhancing the security and controllability of the platform.

[0106] (9) The document parsing module can automatically extract key information, such as the image title, by accurately locating the location of the image data. It can also identify the attributes and type of the image based on the image title and associate the document paragraph to which the image belongs.

[0107] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0108] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0109] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0110] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute the computer-readable program instructions, thereby implementing various aspects of the present disclosure.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A QC document and media analysis application platform, including a document analysis module, a video text recognition module, a media voice recognition module, a retrieval module, a relationship diagram drawing module and a rights management module, characterized in that: The document parsing module is used to extract the content of the QC documents uploaded by the user and store them in categories; the media voice recognition module and the video text recognition module are used to perform voice and text recognition on the media videos uploaded by the user and associated with the QC documents respectively; the retrieval module is used to retrieve and display the document and video content using a dynamic weighted similarity algorithm; the relationship graph drawing module is used to draw a relationship graph online in real time based on the graph data structure; the authority management module is used to manage, batch maintain and configure user permissions through roles; the calculation formula for dynamic weighted similarity is: ， in: For query conditions and text content Dynamic weighted similarity of; For text content Middle Field The weight of For Field Dynamic factors; is the normalization factor; For text content The number of fields in ; For query conditions Text content field No. The query word vector that matches the word vector; For Field Middle word vectors; For Field The number of word vectors in ; Dynamic Factor The calculation formula is: ， ， ， ， in, For Field In the text content The global importance of For Field Local relevance to the query conditions; U i Adjustment factor for user behavior feedback; , For Field , Field The word vector in the text content The frequency of words in ; Respectively query term vectors and fields Middle word vectors; is the cosine function; is the weight adjustment parameter; The field in the hth interaction in the user's historical behavior record Importance rating; Field in the hth interaction in the user's historical behavior record relevance; is the total number of samples in the user's history.

2. According to claim 1, a QC document and its media analysis application platform is characterized by: The document parsing module extracts and parses the text content and image data in the QC document by combining document content extraction technology with OCR recognition technology, and stores them in the database and Elasticsearch. The text content and image data are classified, stored and indexed according to the document structure.

3. The QC document and media analysis application platform according to claim 1, characterized in that: The document parsing module displays the document parsing progress in real time and provides an exception prompt function. When an exception occurs during the parsing process, the exception situation is immediately displayed.

4. The QC document and media analysis application platform according to claim 1, characterized in that: The media speech recognition module uses an audio processing tool to extract audio content from the media video; The video text recognition module transcribes the audio content into text content through a speech recognition model, extracts key information according to the document structure and stores it in a database and Elasticsearch, and associates it with the corresponding QC document.

5. The QC document and media analysis application platform according to claim 1, characterized in that: The retrieval module performs full-text retrieval according to the query conditions input by the user through a dynamic weighted similarity algorithm, matches the text content of the corresponding QC document, the text content obtained by transcribing the image data and the audio content, and displays the QC documents and media videos containing relevant content.

6. A QC document and media analysis application platform according to claim 1 or 5, characterized in that: The algorithm flow of the dynamic weighted similarity algorithm includes: The query conditions entered by the user and the text content in the QC document are processed by word vectorization, and then the dynamic weighted similarity between the query conditions and the QC document is calculated based on the word vector. The text content of the most matching QC document is obtained based on the dynamic weighted similarity, and the image data associated with the text content and the text content obtained by transcribing the audio content are obtained from the database and Elasticsearch.

7. The QC document and media analysis application platform according to claim 1, characterized in that: Importance Rating The calculation formula is: ， actually, For the Interaction fields The probability of the corresponding content being clicked; For the Interaction fields Average dwell time of the corresponding content; For the From the field The proportion of actions that lead to download, open or preview; is the weight parameter.

8. The QC document and media analysis application platform according to claim 1, characterized in that: Relevance The calculation formula is: ， in, For the The semantic vector of the user query in the interaction; For Field In the The semantic vector of the interaction content.

9. The QC document and media analysis application platform according to claim 1, characterized in that: Normalization factor The calculation formula is: ， in, Indicates the influence coefficient of user feedback on field length normalization.

10. The QC document and media analysis application platform according to claim 1, characterized in that: The relationship graph drawing module draws the relationship graph online in real time based on the graph data structure, including: Based on the nodes and edges of the graph data structure, the relationship diagram is drawn online in real time in the browser, and the node arrangement can be freely set. The nodes and edges can be edited through the event mechanism or the node position can be adjusted by dragging.

11. The QC document and media analysis application platform according to claim 1, characterized in that: The permission management module is based on the role management mechanism, manages user permissions through roles, assigns permission configuration to different roles, and assigns one or more roles to users through batch maintenance, and configures permissions according to actual needs.

12. The QC document and media analysis application platform according to claim 1, characterized in that: The platform adopts a B / S architecture and is deployed in multiple operating system environments. The permissions of multiple operating systems are associated and can be expanded in different regions or departments according to needs.

13. A method for analyzing and applying QC documents and media thereof, using the platform according to any one of claims 1 to 12, characterized in that: The method comprises: Extract content and classify and store QC documents uploaded by users; Perform voice and text recognition on media videos uploaded by users and associated with QC documents; Use dynamic weighted similarity algorithm to retrieve and display document and video content; Draw relationship diagrams online in real time based on graph data structures; Through role management, batch maintenance and configuration of user permissions.

Images