Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

3results about How to "Reduce resource costs" patented technology

Trojan detection method and device, electronic equipment, medium and program product

PendingCN122133141AAvoid high resource overhead operationsImprove detection accuracy
This application provides a Trojan detection method, apparatus, electronic device, medium, and program product, specifically relating to the application of large-scale models in information security and fintech fields, and applicable to the fields of big data technology and artificial intelligence technology. The method includes: acquiring a target model file; obtaining a deserialized instruction text sequence based on the target model file; constructing risk analysis prompts using an instruction analysis agent based on the deserialized instruction text sequence; interacting with a Trojan detection model using the instruction analysis agent based on the deserialized instruction text sequence and the risk analysis prompts to obtain a risk assessment result; and generating a Trojan detection result for the target model file based on the risk assessment result.
Owner:INDUSTRIAL AND COMMERCIAL BANK OF CHINA

Portable switch cabinet temperature rise on-line monitoring system

ActiveCN121253945Breduce volumereduce weight
The application discloses a portable switch cabinet temperature rise online monitoring system and relates to the technical field of power equipment detection. The system comprises a portable high-frequency large-current power supply module, a multi-channel temperature acquisition module, an initial temperature rise calculation module, a parameter identification module, a temperature rise correction module and a state determination module. The portable high-frequency large-current power supply module is used for generating a test current and applying the test current to a switch cabinet. The multi-channel temperature acquisition module is used for generating a temperature data sequence of measuring points and an ambient temperature data sequence. The initial temperature rise calculation module is used for calculating and generating an initial measured temperature rise data sequence. The parameter identification module is used for solving a group of dynamic model parameters and determining a predicted steady-state temperature rise value under the test current. The temperature rise correction module is used for calculating and generating a final steady-state temperature rise value under a rated working condition. The state determination module is used for determining a temperature rise state of the switch cabinet. The application adopts high-frequency switching power supply technology and third-generation semiconductor power devices, significantly reduces the volume and weight of the test equipment, and solves the problems of the traditional device being heavy and poor in mobility.
Owner:HUBEI JINLANG HI TECH DEV CO LTD

Bearing residual life prediction method based on multiple working condition information fusion large model

PendingCN121959506Aeasy to handleSolve the generalization problemBiological modelsInference methodsData setAlgorithm
The invention discloses a bearing residual life prediction method based on a multiple working condition information fusion large model, and the method comprises the following steps: constructing a cross-modal data set, extracting time sequence features through a signal encoder, mapping the time sequence features to a large model semantic space through a projection layer, achieving the alignment with a working condition text, carrying out the fine adjustment of the large model based on an LoRA technology, and carrying out the prediction of the residual life of a bearing. Receiving a sequence fusing the instruction, the working condition and the signal characteristics for joint reasoning; in training, an asymmetric dynamic penalty mean square error loss function is adopted, and the penalty weight of optimistic prediction errors is dynamically increased. According to the method, physical signals and semantic information are effectively fused, and generalization and industrial safety of prediction results are improved.
Owner:SOUTH CHINA UNIV OF TECH