5results about How to "Improve scoring accuracy" patented technology

The application discloses a bronchoscope supply-demand dynamic matching method based on multi-source data fusion, comprising: collecting multi-source heterogeneous data and performing fusion processing to obtain a device feature matrix, a demand feature matrix and an environment feature vector; determining a score calculation strategy according to a comparison result of a historical matching data accumulation amount and a preset threshold, determining a device availability score and a demand urgency score based on the device feature matrix and the demand feature matrix according to the score calculation strategy; constructing a device queue and a demand queue, attaching an initial scene label to each demand and performing identification, and outputting a standardized scene type; outputting an optimal matching scheme through a reinforcement learning intelligent agent based on the device queue, the demand queue, the standardized scene type and the environment feature vector; performing intelligent scheduling based on the optimal matching scheme, updating the queue based on external real-time events, and if both queues are non-empty at the same time, obtaining a new optimal matching scheme, otherwise, keeping a waiting state. The application can improve matching efficiency and accuracy.

The invention discloses a femoral head necrosis scoring system and method based on a CT image, and belongs to the technical field of image processing. By collecting preoperative hip joint CT data of a femoral neck fracture patient, through preprocessing operations of unifying resolution, calibrating an area of interest and the like, and in combination with multiple data enhancement means, sample diversity is improved; the method comprises the following steps: firstly, extracting a plurality of images, then converting the images into sagittal plane views, axial plane views and coronal plane views, fusing features, extracting multi-scale spatial features based on Video Swin Transformer, outputting continuous risk scores between 0 and 1, and finally training the model by adopting a corresponding loss function and an optimizer until convergence; according to the femoral head necrosis scoring system and method based on the CT image, the problems that a traditional method subjectively depends on experience and lacks quantitative indexes are solved, the scoring accuracy and efficiency are improved, and an objective basis is provided for clinical risk assessment.

The invention provides a spoken language evaluation model training method, a spoken language evaluation method, equipment and a medium, and relates to the technical field of natural language processing, the method comprises the following steps: updating parameters of a pre-training language model in a first spoken language evaluation model to obtain a second spoken language evaluation model; constructing a third spoken language evaluation model according to the second spoken language evaluation model and the initialized multi-scale acoustic adaptation module; freezing parameters to be frozen in the third spoken language evaluation model, and updating parameters of an initialized multi-scale acoustic adaptation module in the third spoken language evaluation model to obtain a fourth spoken language evaluation model; and training the fourth spoken language evaluation model to obtain a target spoken language evaluation model for carrying out spoken language score prediction according to the multi-scale acoustic features and the text features. According to the spoken language evaluation method and device, spoken language evaluation is performed by fusing the multi-scale acoustic features and the text features, the objectivity and distinction degree of spoken language evaluation results are improved, and then the spoken language scoring accuracy is improved.

This application discloses an AI-based secure grading system and method based on scoring points, belonging to the field of computer-aided education technology. The system includes: a question bank data interface module, which organizes question bank data hierarchically, labels each scoring point with a preset score, and associates the data with exam type identifiers; a scoring rule configuration layer, which maintains independent scoring meta-rules for each exam type; a scoring prompt word construction module, which establishes a cross-layer index association from the question bank layer to the configuration layer through exam type identifiers, loads scoring meta-rules, and assembles them into structured prompt words; a concurrent scheduling and secure call module, including semaphore rate limiting, exponential backoff retry, and concurrent scheduling; a post-processing score clamping module, which sequentially executes scoring point-level and total score clamping, followed by automatic filtering at multiple confidence levels, without requiring manual intervention throughout the process; and a scoring output module, which outputs the grading results after security verification. This application adapts to the scoring logic of different exams through cross-layer index association, combined with multi-level security clamping and fully automatic confidence filtering, to achieve universal AI-based secure grading.

This application provides a speech recognition method, speech recognition device, electronic device, and storage medium, belonging to the field of financial technology. The method includes: acquiring target speech data; extracting acoustic features from the target speech data to obtain target acoustic features; decoding the target speech data based on a decoding model to obtain a target word graph; the target word graph includes word nodes and a speech feature sequence, the speech feature sequence including at least two speech words; constructing multiple candidate sentence paths based on the word nodes and speech feature sequence; initially scoring the speech words of each candidate sentence path to obtain a preliminary word score; correcting the preliminary word score based on the target acoustic features to obtain a target word score; filtering the candidate sentence paths according to the target word score to obtain a target sentence path, and concatenating the speech words of the target sentence path to obtain target sentence data. This application can improve the accuracy of speech recognition.