4results about How to "Add data source" patented technology

The invention discloses a children autism risk assessment method and system based on multi-modal collaborative reasoning and a vertical domain large model, and the method comprises the steps: collecting the audio data of a to-be-assessed child and a parent in a parent-child interaction link, and collecting the video data through collection equipment; analyzing and marking the collected audio data, and generating a sounding record and a transcription text with a timestamp; performing real-time analysis and labeling on the collected video data, and generating sight line, expression and action recognition records with timestamps; performing independent analysis on the preprocessed multi-modal data, performing feature fusion and collaborative analysis on the multi-modal data such as audio, text and video by using a multi-modal collaborative reasoning method, and generating a scientific data index for autism risk assessment; training a vertical domain large model special for autism risk assessment; and inputting the generated data indexes into a vertical domain large model, and outputting targeted assessment suggestions by the large model in combination with daily information of the children to be assessed obtained by interviews and conversations with parents.

This application relates to the field of vehicle technology, and in particular to a time processing method, apparatus, computer device, and computer-readable storage medium. The method includes: upon detecting a time update event for a local clock source corresponding to a main controller, obtaining corresponding candidate times from candidate clock sources other than the local clock source; wherein each candidate clock source includes the system clock source of the target vehicle system carrying the main controller, and the external clock source of an external device communicating with the main controller; selecting a reference time from the obtained candidate times according to the priority of each candidate clock source; correcting the reference time according to the current timing format corresponding to the reference time, the local timing format of the local clock source, and the timing overflow mechanism of the local clock source to obtain a target time; and updating the local time of the local clock source using the target time.

This disclosure relates to the field of model training technology, and in particular to a model training method and system. It includes: constructing a cold-start dataset for the security field, which contains multimodal security scenario data, target scenario questions, and corresponding text responses; secondly, adjusting the parameters of a basic multimodal model based on this cold-start dataset to obtain an adjusted model with preliminary security recognition capabilities; then, acquiring difficult samples, including failure samples, prediction bias samples, and adversarial generation samples selected from the test set; finally, strengthening the adjusted model based on these difficult samples, ultimately obtaining a high-performance, robust multimodal model for the security field. This solves the technical problem of poor model performance in the security field due to insufficient training data.

The application discloses a heterogeneous data fusion device, method and medium for AI large model pre-training, and relates to the technical field of artificial intelligence. The heterogeneous data fusion device comprises a collection module, a processing module and an output module, the processing module comprises an identification and analysis unit and an alignment and evaluation unit, the output module comprises a filling unit and an index unit; the identification and analysis unit is used for identifying and analyzing heterogeneous data of different modalities, obtaining each standard data object, the alignment and evaluation unit is used for unifying semantic vectors of each standard data object and calculating quality scores of pairs of multi-modal data; the filling unit is used for filling the pairs of multi-modal data to corresponding slots of a semantic driving template, and attaching labels and quality scores to target samples, and the index unit is used for encapsulating the target samples into a standard data structure and constructing a multi-dimensional index of the target samples. The device can unify standards, accurately fuse multi-modal data, and improve processing efficiency and the quality of pre-training data.