7 results about "Impact index" patented technology

This invention discloses a traceable management method for AI model training data, specifically relating to the field of artificial intelligence training data traceability management technology. It addresses the problem in existing AI model training processes where the lack of continuous traceability between original samples, derived samples, training consumption records, and model versions makes it difficult to accurately pinpoint the actual impact range of problematic samples. By continuously associating original sample identifiers, derived sample identifiers, consumption vouchers, model version identifiers, and impact indexes, and tracing derived sample identifiers level by level along the original sample identifier based on the problematic sample trigger request, and locking the associated model version, the actual impact range of problematic samples can be accurately defined. This solves the problem of existing technologies struggling to trace specific problematic samples back to training batches and model versions, leading to inefficient handling.

The present invention is a computer system for creating fractal spider graphs which display data in a nested structure. The present invention includes a data store, a data analytics engines, and a computer platform for data visualization. The present invention analyzes both qualitative and quantitative data to determine a pattern of behavior based on the data. The data is then broken down into key performance indicator (KPI) units using NLP and machine learning. These KPI units are then used as the atomic unit for constructing the fractal spider graphs. The fractal spider graphs of the present invention are hierarchical, nested spider graphs which simultaneously display information and analysis from multiple levels of an organizational hierarchy. Further, the present invention is operable to generate inferences (i.e., decision outputs) based on the data, wherein the inferences are displayed as prioritized action lists, weighted confidence scores, risk-impact indices, and / or narrative recommendations.

This invention provides a water hammer prediction system and device. The invention relates to the field of pipeline fluid transport safety technology. The water hammer prediction system is configured to: acquire static topology and physical attribute information and multi-dimensional real-time operating condition data of the fluid transport system, and pre-calibrate a dynamic simulation model based on the information and data; when a water hammer triggering event is detected, invoke the pre-calibrated dynamic simulation model to perform an initial prediction to generate an initial prediction result, and issue a pre-control command to the first-level protection device based on the initial prediction result; acquire the measured impact index at the first-level protection device and compare it with the initial prediction result to determine the prediction error; and, based on the prediction error, correct the dynamic simulation model in real time, and drive the corrected dynamic simulation model to perform cascade control of the next-level protection device.

This invention proposes a safety control method and system for ultra-high bridge towers based on the time-varying effect of concrete, belonging to the technical field of bridge tower control systems. Addressing the problems in existing technologies such as insufficient prediction accuracy of long-term internal force redistribution caused by concrete shrinkage and creep, and insufficient consideration of the coupling effect between multiple risk factors and bridge tower concrete shrinkage and creep, resulting in low accuracy in predicting the state of bridge towers and a lack of guidance for maintenance control, this invention integrates multi-source heterogeneous data to calculate the impact indices of concrete shrinkage and creep, dynamic ice impact, static ice pressure, concrete freeze-thaw cycles, and ice wedging. A machine learning-based comprehensive risk assessment model is then used to fuse these indices, generating a comprehensive risk report containing risk levels and control recommendations. This invention significantly improves the accuracy of single risk factor assessment, enhances the comprehensive prediction accuracy of complex coupled risks, and strengthens the system's decision-making robustness and maintenance efficiency in complex scenarios with multiple concurrent risks.

The invention discloses a building material life cycle traceability management system and method based on RFID, and relates to the technical field of building material life cycle traceability management, and the method comprises the steps: S10, generating a traceability feature of a building material product; s20, predicting a life influence index of the building material product in a logistics transportation stage based on the searched abnormal transportation data; s30, obtaining a traceability index of each building material product to be used; and S40, carrying out life traceability management on the building material product to be used. According to the method, the traceability index of the to-be-used building material product is calculated, the building material product with the quality problem can be quickly and accurately screened out from numerous products, the quality prevarication problem caused by the storage mode or storage time of the building material product is avoided, and the quality of the building material product can be accurately determined according to the occurrence frequency of various target traceability indexes. And the root cause of the quality problem of each to-be-used building material product is quickly and accurately locked.

The application discloses a kind of urban system resilience dynamic measurement method, device, equipment, medium and product, it is related to urban disaster management and risk assessment field, the method comprises: obtaining the resilience index data and disaster environment data of target city;According to disaster environment data, determine initial storm impact index;According to resilience index data and initial storm impact index, construct resilience index system;According to each resilience index value under each resilience dimension, the weighted comprehensive index of each resilience dimension is calculated respectively, obtain multiple resilience attribute parameter values;According to each resilience attribute parameter value, using parameterized gamma family recovery function model simulates the system performance change of target city after suffering disaster impact, generates dynamic performance recovery curve;Based on dynamic performance recovery curve, the dynamic resilience quantitative value and recovery time of target city are calculated.The application can carry out dynamic simulation to the whole process of "impact-response-recovery" of city, improve the accuracy of city resilience measurement.

The application provides a knowledge graph construction method, system, device and medium, relates to the technical field of knowledge graph construction, and the method comprises the following steps: in response to a trigger event sent by a user end, acquiring basic information of an enterprise corresponding to the user end, combining the trigger event and the basic information, determining a plurality of characteristic data affecting the result of the trigger event, and constructing a sub-knowledge graph of each characteristic data; acquiring an influence index of each sub-knowledge graph on the result of the trigger event and a correlation coefficient between the sub-knowledge graphs; combining the influence index and the correlation coefficient to construct an initial knowledge graph; acquiring an abnormal conduction edge in the initial knowledge graph; processing the correlation coefficient and the influence index carried by the abnormal conduction edge to generate a target knowledge graph; and generating a strategic decision suggestion of the trigger event according to the target knowledge graph. The application has the technical effect that the accuracy of the strategic decision suggestion generated by the knowledge graph is improved.