13 results about "Precision and recall" patented technology

The invention discloses an expert and team intelligent matching method and system oriented to technical requirements, and belongs to the technical field of natural language processing. The method aims at solving the problems that according to an existing scheme, retrieval precision and recall rate are contradictory, single corpus is limited, team synthesis ability is lacked, and interpretability is insufficient. The method comprises the following steps: processing paper and patent data in a cross-domain manner, and constructing vectors, keyword indexes and a heterogeneous knowledge graph; executing cross-domain name disambiguation to obtain a unified expert entity; performing three-mode parallel retrieval and adaptive fusion sorting; sorting comprehensive scores of experts; performing multi-constraint team synthesis optimization; and generating a recommendation explanation containing the evidence number. The system comprises eight core modules. The method is excellent in retrieval performance, accurate in disambiguation, capable of supporting intelligent team synthesis, high in interpretability and suitable for talent discovery and scientific research transformation scenes.

This application provides a CTR prediction optimization method based on differentiable precision and recall, including the following steps: constructing a CTR prediction model by inputting training data and training features into the model; calculating the difference between the predicted value and a threshold after the model's output layer, and calculating the differentiable precision and recall based on the difference; integrating the differentiable precision and recall into the model's loss function, and minimizing the loss function through an optimization algorithm to obtain a trained CTR prediction model, etc. This approach achieves high computational efficiency and differentiability, allowing direct integration into gradient optimization algorithms. By eliminating dependence on threshold, conditional judgment, and ranking operations, this application can handle large-scale imbalanced data, significantly improving the performance and training efficiency of the CTR prediction model. Furthermore, it has broad application prospects in the recommender system field, effectively enhancing the model's predictive ability and commercial value.

The application discloses a Chinese human phenotype ontology recognition method and related equipment, which can be applied to the technical field of text information processing. The application can effectively improve the recall rate by expanding the human phenotype ontology concept synonym set through a large language model, generating an expanded dictionary with the initial dictionary, significantly enhancing the discrimination ability of the recognition model for semantically ambiguous concepts through two-stage comparative learning, balancing the precision and recall rate by constructing an initial dictionary based on the human phenotype ontology official database and the Chinese human phenotype ontology official data, merging and disambiguating the current input text after accurate matching and semantic similarity matching to obtain a fused candidate result list, and finally obtaining the structured recognition result corresponding to each current input text by post-processing each candidate fragment in the fused candidate result list, which can provide effective data support for disease diagnosis.

The invention relates to a corpus construction method and system, and the method comprises the steps: building a multi-dimensional labeling system according to the clinical features of epilepsy, and distributing differentiated labeling strategies for different types of labels; the method comprises the following steps: acquiring original clinical text data related to epilepsy, and labeling the original clinical text data by utilizing a differential labeling strategy to form a labeled corpus with a label; performing consistency evaluation on the obtained tagged corpus, and iteratively revising the tagging rule when the consistency is lower than a preset threshold value until the consistency reaches the standard; taking the tagged corpus as a supervision signal to train and verify an entity recognition model to obtain an epilepsy clinical text-oriented entity recognition model; and applying the trained entity recognition model to an unlabeled epilepsy clinical text to generate a structured corpus. According to the method, the problems of low extraction precision, coarse granularity, poor adaptability and the like of an existing method can be solved, the method gives consideration to precision and recall, and a high-quality corpus with labels can be output.

Systems and methods for implementing auditing of large language model-based tools for bias in inferences is disclosed. Individual entries of the dataset of dialogs may be modified to include stereotypical details of particular contexts. These modified records may then be submitted to an automated response generator to produce a set benchmark records. The baseline records and benchmark records may then be analyzed for completeness, accuracy and conciseness with respect to the particular contexts and disparities in precision and recall may be determined using differences in the benchmark and baseline records. The determined disparities may then be used to further train or fine-tune the automated response generator.

This application relates to the field of data processing technology, and in particular to an AI multi-source data processing method and system based on big data. The method includes: calculating the field correlation degree based on the number of times each field co-occurs with all other fields in the field co-occurrence matrix; using the ratio of the number of non-empty records to the total number of records as the data completeness; and using the product of the field correlation degree and the data completeness as the field weight; randomly sampling content samples multiple times for each field to calculate aggregation stability, and calculating the cross-source similarity between any two fields from different data sources; constructing an adaptive similarity threshold for each field; and for each pair of cross-source fields, if the cross-source similarity is not lower than the adaptive similarity threshold, determining that the field pair is semantically matched, and outputting the field mapping relationship. The technical solution of this application can reduce the false matching rate of key fields while maintaining the overall matching recall rate, achieving synergistic optimization of matching precision and recall.

The application discloses a kind of knowledge graph construction methods based on fine-grained retrieval and reverse restoration self-error correction, specifically: first, standard reference case library is constructed, and standard reference vector is calculated.Then, the long text S to be measured is disassembled into sentences to be processed;Each sentence is vectorized, and the similarity score of its standard reference vector is calculated, and the first standard reference case of each sentence is screened;Through large language model, the non-standard logical relationship contained in each sentence is extracted and vectorized, the cosine similarity is calculated, and the candidate mapping is obtained by descending arrangement, after summarizing, double-feature reordering is carried out using multi-round greedy reordering algorithm, and the first standard reference case is screened out, and the single sentence is spliced into large language model, and triple extraction is carried out;Finally, the relationship triple set of all sentences constitutes knowledge graph.The application improves the precision and recall rate of triple extraction under the premise of avoiding redundancy.

This invention discloses a distributed, adaptive threshold adjustment method and a DAS system applying this method. The method includes the following steps: determining and initializing the capacity of the precision score array, recall score array, and confidence threshold array at system startup; user confirmation and submission of alarm feedback information; indexing and retrieving the previous precision and recall scores of the alarm location from the precision score array and recall score array; using the retrieved previous precision and recall scores, and based on the alarm feedback information, updating the precision and recall scores of the alarm location and each location within its influence range, and updating the confidence threshold within the alarm influence range; storing the updated precision, recall, and confidence thresholds on the DAS system's disk. This invention can dynamically update the precision, recall, and confidence thresholds of each location based on the actual situation of the alarm location reported by the user, in order to balance the precision and recall of the system and optimize the overall system performance.

The invention relates to the technical field of face or human body clustering methods, and discloses a feature clustering method based on KNN neighborhood IOU enhancement, and the method comprises the following steps: S1, extracting recognition features of N data; and S2, calculating a cosine distance between every two data features, and assuming that two vectors are represented as follows, and L2 norms of the recognition features are equal to 1. According to the feature clustering method based on KNN neighborhood IOU enhancement, after a KNN relation graph of original features is established in a common clustering method, the connection relation between the features is directly enhanced according to a trained neural network, and the influence caused by inaccurate features is ignored, so that the clustering accuracy is improved. According to the method, the similarity sequence between the images is converted into the IOU relationship between the nodes, the connection mode of the node 6 is corrected, and the nodes 6 are correctly divided into own categories, so that the connection relationship between the same categories is more reliable, and the precision and recall rate of a clustering algorithm are effectively improved.

The application relates to a corpus construction method and system, which comprises the following steps: establishing a multi-dimensional marking system according to clinical characteristics of epilepsy, and assigning different marking strategies to different types of labels; obtaining original clinical text data related to epilepsy, marking the original clinical text data by using the differential marking strategy, and forming labeled marking corpus; performing consistency evaluation on the obtained labeled marking corpus, and iteratively revising the marking rules when the consistency is lower than a preset threshold until the consistency meets the standard; using the labeled marking corpus as a supervision signal to train and verify an entity recognition model, and obtaining an entity recognition model for epilepsy clinical text; and applying the trained entity recognition model to unmarked epilepsy clinical text to generate a structured corpus. The application can solve the problems of low extraction accuracy, coarse granularity and poor adaptability of the current method, and the method can output high-quality labeled corpus with high precision and recall.

The invention discloses a vector database retrieval method, computer equipment and a readable storage medium. The vector database retrieval method comprises the following steps: retrieving from a vector database by utilizing a plurality of retrieval methods according to a query request to obtain a corresponding retrieval text set and similarity; normalizing each similarity to obtain a normalized score, and obtaining a union set of each retrieval text set to obtain a combined text set; obtaining a first score of each retrieval text in the combined text set according to each normalized score and the text attribute of each retrieval text; sorting the combined text set and the retrieval text sets according to the first scores to obtain a first sequence and a corresponding second sequence; calculating a second score of each retrieval text according to the ranking of each retrieval text in the first sequence and the ranking of each retrieval text in each second sequence; and sorting the retrieval texts according to the second scores to obtain a third sequence. According to the method, the retrieval precision and the recall rate can be improved.

The application provides a grammar error correction large model training method and device based on reinforcement learning, equipment and medium, relating to the technical field of data processing. The method comprises the following steps: obtaining an initial grammar correction corpus containing error sentences and corresponding correct sentence pairs, processing the initial grammar correction corpus to generate a reasoning correction training set, adjusting a first preset language model according to the reasoning correction training set to obtain an initial strategy model, performing reinforcement learning training on the initial strategy model based on a preset composite function by using a reinforcement learning algorithm, and finally obtaining a target grammar correction model. The target grammar correction model can fully utilize the reasoning ability, effectively improve the performance of the model in terms of precision and recall, better meet the actual needs of grammar correction, and generate correction results containing reasoning processes, which provides more transparent and interpretable basis for the correction process.

The invention discloses a multi-modal sentiment analysis model based on multi-head attention perception fusion, and the model comprises the steps: firstly, carrying out the feature extraction of a multi-modal multi-head attention mechanism, enabling the feature to be projected to a vector subspace, reducing the dimension of the feature, keeping the most important sentiment feature information, and making preparations for the subsequent analysis; and secondly, performing data calculation on the multi-modal features by using labels of an emotion data set, and projecting the multi-modal features in a vector space to realize fusion of the multi-modal features, thereby effectively integrating different perception channel information from texts, audios and videos. And finally, carrying out experiments on the multi-modal data sets of the CMU-MOSI and the CMU-MOSEI, thereby verifying the effectiveness and the performance of the multi-head attention mechanism in the multi-modal sentiment analysis task. Experimental results show that the multi-modal sentiment analysis method introducing the multi-attention mechanism is remarkably improved in the aspects of recognition accuracy, sentiment scores, precision and recall rate.