14 results about "Automatic indexing" patented technology

The invention discloses a mechanism knowledge base intelligent classification and indexing system and device based on multi-modal data fusion, and aims at solving the problems that when a traditional knowledge base processes multi-modal data, the efficiency is low, the classification precision is insufficient, the indexing quality is poor, and non-text resource processing is short. According to the system, through a feature extraction technology, features such as colors and textures are extracted for images, features such as keywords and themes are extracted for texts, and multi-type data such as texts, images and videos are converted into uniform feature vectors. A classification model is constructed by combining an SVM, a CNN and a Transform, and an attention mechanism is introduced to realize adaptive fusion. Based on a classification result, through automatic indexing such as keyword extraction and topic modeling, resources are associated through a knowledge graph. Experiments prove that the processing time of the device is shortened to 1 / 20 of that of an original method, the classification accuracy is improved from 30% to 90% or above, the knowledge base management efficiency and service quality are effectively improved, and support is provided for knowledge utilization and decision making.

The application relates to the field of intelligent decision-making and the field of digital medicine, and discloses a video retrieval method and device based on multiple modes, electronic equipment and a storage medium, the method comprising the following steps: querying multiple mode attributes of a to-be-retrieved video, selecting a multiple mode network, and extracting multiple mode features in the to-be-retrieved video; extracting a feature sequence, constructing a fixed cluster group of the feature sequence, performing mean pooling on the fixed cluster group to obtain a pooled cluster group, performing fixed-length alignment on the feature sequence according to the pooled cluster group to obtain an aligned sequence; extracting a feature dimension, aligning the dimension length to obtain an aligned dimension, and determining aligned multiple mode features of the multiple mode features according to the aligned sequence and the aligned dimension; performing feature splicing and feature fusion; performing feature vector coding on a retrieval text, calculating a cosine similarity, and determining a video retrieval result of the retrieval text according to the cosine similarity. The application can realize automatic indexing and retrieval of videos and improve the comprehensiveness of the entire video retrieval process.

The invention relates to the field of shearing machine cutter grinding, and mainly discloses a shearing machine cutter multi-station automatic transposition grinding platform which comprises a supporting seat, a vertical plate is arranged on the surface of the supporting seat, a mounting plate is arranged on the end face of a supporting rod, a positioning clamping plate is arranged on the side face of the mounting plate, and a fixing screw is arranged on the surface of the supporting plate. And a positioning nut is screwed on the surface of the fixing screw rod. Firstly, a straight cutter is inserted into a positioning groove to be matched with a positioning bolt to be fixed, when the cutting disc needs to be ground, a driving motor is started to rotate a mounting plate by an angle, then a supporting plate can be rotated subsequently through rotation of a limiting bolt, and after the supporting plate rotates by a proper angle, the supporting plate is fixed through the limiting bolt; and then the cutting disc is matched with the positioning nut to be fixed, so that the grinding machine is used for grinding the cutting disc, the situation that different devices need to be replaced when different cutting tools need to be ground is avoided, and the labor amount of workers is reduced.

The invention discloses an automatic indexing tool for radiographic inspection of a bowl-shaped shell and a radiographic inspection system, and belongs to the technical field of radiographic inspection. The invention provides an automatic indexing tool. The automatic indexing tool comprises a base frame and a clamping and rotating assembly arranged on the base frame. The assembly is composed of a driving wheel driven by a servo motor, a plurality of driven supporting wheels supporting the shell in different directions and a pressing mechanism applying pressure to the contact face, and stable clamping and driving of the bowl-shaped shell are achieved. The tool control terminal communicates with the driving motor, and the shell can be accurately controlled to automatically rotate according to preset indexing. The invention also provides a radiographic inspection system comprising the tool. Through one-time clamping and automatic indexing rotation, traditional manual partition and repeated adjustment are replaced, the detection efficiency and consistency are greatly improved, quality fluctuation and missing detection risks caused by manual operation and lead wire identification are eliminated, and equipment loss is reduced.

The invention discloses a legal file key information automatic indexing system based on natural language processing, and belongs to the field of judicial informatization. The system comprises a file multi-mode preprocessing module used for carrying out unified analysis and standardization processing on heterogeneous file materials such as texts, images and audios; the key information intelligent extraction module integrates a named entity recognition sub-model, a relationship extraction sub-model and an event extraction sub-model, and realizes deep semantic understanding and extraction of legal entities, relationships and events; the dynamic indexing rule engine module is used for mapping an extraction result into structured indexing data according to a file type self-adaptive indexing strategy; and the indexing quality evaluation and feedback optimization module continuously optimizes the system performance through a man-machine cooperation mechanism. According to the method, full-automatic, high-precision and self-adaptive indexing of the legal file key information is realized, the intelligent level and information utilization efficiency of file management are remarkably improved, and a high-quality data basis is provided for intelligent court construction.

The application discloses a kind of based on XML fragmentation literature abstract content processing method, including the literature being converted into XML format is divided into fragmented data unit, according to four kinds of mode of chapter, chapter, section and theme constitutes data content model, data content model is dynamically associated by key word semantic relation, extract fragmented data application unit in key word and subject content unit, content unit is dynamically reorganized according to literature abstract demand.The application has beneficial effect that metadata automatic indexing accuracy is >95%, text Xml automatic annotation accuracy is >90%, can effectively improve the prerequisite of target extraction accuracy under the condition of reducing the cost of text decomposition.

The application discloses a word document automatic indexing method and device based on a short text classification task, an electronic equipment and a storage medium. In the method, the word document automatic indexing task is converted into a short text classification task in the field of natural language processing. The task uses a pre-training language model for semantic understanding, can automatically mine potential features of data, and fully utilizes semantic features of articles in sample documents. Through a sample document structure feature and a first short text content generation algorithm, the structure features of the articles in the sample documents are converted into semantic features, so that the pre-training language model can consider the structure features of the articles while learning the semantic features of the sample paragraphs. The preset deep learning model obtained through training automatically establishes a strong dependency relationship between the paragraphs and the labels, so that better indexing effect is achieved.

The invention relates to the technical field of data processing, and discloses an automatic indexing method and system based on a large language model. The method comprises the following steps: carrying out structured analysis on a document to obtain text data and page mapping, obtaining a word list matching entry set by utilizing word list forward matching, inputting an uncovered text interval into a large language model to extract new entries, and normalizing to obtain a model extraction entry set, the two sets are fused, a comprehensive weight value is calculated according to the word frequency value, the inverse document frequency value, the hierarchy weighting coefficient and the position weighting coefficient, the first K entries are screened, sorting is conducted according to pinyin, page numbers are added, and an indexing document is generated. According to the method, the normalization, the coverage integrity and the weight calculation accuracy of the index entries are improved.

This invention belongs to the field of precision machining and measurement technology, and relates to an automatic indexing device based on a multi-tooth subdivision indexing table. Its features include: a multi-tooth subdivision indexing table (5), with a subdivision drive mechanism (1) connected to one side of the table; a coarse indexing drive mechanism (3) and a lifting drive mechanism (4) connected to the other side of the table; and a connecting plate (2) at the bottom of the table (5), which is fixedly mounted on the upper surface of a worktable (6). The advantages of this invention are: it can achieve automatic indexing at any angle, has a simple structure, good reliability, and improves measurement accuracy and efficiency.

The application provides a surgical stage recognition method, device and equipment based on a multi-head attention mechanism. The method is aimed at a surgical video, takes into account the particularity of surgery and relatively more details of the surgical video, and generally has a long surgery time and strong time sequence. Therefore, a modified SwinTransformer network is used instead of a ResNet network to extract features, more detailed features can be extracted, accurate recognition of the surgical stage is realized, and the accuracy is improved by adding a TCN time dependence module. The TCN output and the previous spatial feature matrix are input into a Transformer for encoding, analysis and fusion, the technology for text translation is realized based on video features to "translate" the video, intelligent recognition of the surgical process can be realized, automatic indexing is also realized to facilitate medical records or teaching resources storage, and the method can also be used as a way of quality evaluation of the surgical process, and even can intelligently remind the next work flow to use the instrument.

The application discloses a kind of teaching archives digitization automatic indexing and multidimensional association analysis system, it is related to education information technology field, including: data acquisition module gathers multiple-source heterogeneous teaching archives data and is converted into unified format data to be handled;Intelligent indexing module is according to teaching field special glossary to the semantic analysis and multimodal adaptation of data to be handled, generates multidimensional indexing information;Multidimensional association analysis module identifies direct association according to multidimensional indexing information, excavates implicit association and carries out time series evolution analysis, reveals internal law of teaching;Knowledge graph construction module extracts teaching entity, establishes entity relationship based on association analysis result, constructs dynamic updating knowledge graph;Application service module supports retrieval based on knowledge graph, personalized push and visual analysis, and sets fine-grained access permission.The application can improve teaching resource management efficiency and utilization value, guarantee data security and support teaching decision optimization.

The invention provides a technical document indexing method and device, electronic equipment, a computer readable storage medium and a computer program product, and the method comprises the steps: displaying an indexing dimension determination region which is used for determining the indexing dimension of at least one technical document; in the indexing dimension determination area, displaying the determined target indexing dimension; in response to a determination operation for the target indexing dimension, displaying an indexing result; wherein the indexing result comprises a label obtained by indexing the at least one technical document and an indexing basis associated with the target indexing dimension. In this way, the success rate of automatic indexing of the technical document can be increased.