41 results about "Preliminary diagnosis" patented technology

The application provides a data center infrastructure equipment state intelligent diagnosis method and system, comprising the following steps: transmitting encrypted equipment data set to a diagnosis center to obtain qualified equipment data set; performing model construction on the infrastructure equipment set to obtain a fault identification model group; identifying a current identification model in the fault identification model group based on the qualified equipment data; performing fault identification on the qualified equipment data by using the current identification model to obtain equipment fault value and fault type probability group; obtaining a preliminary diagnosis result; if the preliminary diagnosis result is a suspected fault, performing multi-equipment joint diagnosis on the equipment fault value to obtain a joint fault value; and if the joint fault value is greater than a maximum fault value, confirming the equipment fault data. The application can reduce the false negative rate of data center infrastructure equipment state diagnosis and improve the accuracy of infrastructure implicit coupling fault diagnosis.

The application discloses a farm veterinarian question and answer and auxiliary diagnosis method and system based on a large language model, which comprises the following steps: standardizing a colloquial query to obtain structured query information; based on the information, mixed retrieval is carried out from a hierarchical veterinarian knowledge base to obtain a candidate disease list and a multi-source evidence set; a preliminary diagnosis answer is generated according to the multi-source evidence set, semantic and evidence alignment evaluation is carried out, and evidence sufficiency scores are generated; the differential diagnosis attributes of each disease in the candidate disease list are compared to identify key differences, and information missing items are identified by comparison with standard symptom profiles; based on the scores, key differences and information missing items, a multi-round diagnosis enhanced retrieval framework and user interaction are adopted, the candidate disease list and the multi-source evidence set are updated, and a diagnosis report is generated in combination with veterinary drug compliance rules. The application integrates hierarchical knowledge graphs, multi-evidence alignment and multi-round diagnosis logic, improves the accuracy of veterinarian question and answer, reduces knowledge illusion, and ensures drug compliance.

This invention discloses a method and system for intelligent diagnosis and optimization of network anomalies in iOS device apps. The method specifically includes: parsing system logs to identify network error patterns, and temporally associating the identified network error patterns with user operation event sequences to form a preliminary diagnostic event chain; extracting features and performing semantic understanding on interface screenshots and voice descriptions, and matching them with a preset fault knowledge base to obtain preliminary fault inferences; constructing a relationship graph based on the preliminary diagnostic event chain and preliminary fault inferences, calculating the probability of each node as the root cause of the network anomaly, and outputting the root cause location result; and generating a targeted personalized configuration optimization suggestion sequence based on the root cause location result through interactive exploration. This invention achieves accurate diagnosis and personalized optimization of network anomalies in iOS device apps, enabling rapid location of the root cause of the problem, reducing the time and cost of manual troubleshooting, and improving fault handling efficiency and user experience.

This invention relates to the field of bearing fault diagnosis technology, specifically to a bearing fault diagnosis method based on neural networks and multi-criteria preference consensus. The method includes: data acquisition and feature extraction, data preprocessing, matching a fault diagnosis model, preliminary diagnosis and probability generation, final diagnosis and probability generation, and bearing state decision-making. This invention provides a multivariate decision-making auxiliary model that integrates physical marginal value functions and neural network attention mechanisms, combined with a reinforcement learning-driven consensus-building process, to achieve adaptive optimization of multi-expert fault diagnosis results. This not only solves the problems of existing bearing fault diagnosis methods being unable to handle complex working conditions, lacking physical interpretability, relying heavily on single decision-making patterns, and using static weight allocation, but also improves the accuracy, robustness, and interpretability of bearing fault diagnosis, achieving high-precision, low-round group fault diagnosis.

This application provides an AI-based diagnostic fee adjustment method and related apparatus. The method includes: acquiring basic diagnostic data of a target vehicle; performing preliminary AI diagnosis on the basic diagnostic data to obtain a first diagnostic result; the first diagnostic result includes a preliminary diagnostic report; determining a target diagnostic strategy based on the preliminary diagnostic report; the target diagnostic strategy includes any one of the following: AI-only diagnosis, AI-assisted and manual determination, or manual diagnosis only; determining a target diagnostic report based on the target diagnostic strategy; determining the AI ​​contribution based on the target diagnostic report; and determining the target diagnostic fee based on a preset basic fee standard and the AI ​​contribution. By constructing a differentiated human-machine collaboration process based on diagnostic confidence, quantifying the AI ​​contribution, and differentiating fees based on the AI ​​contribution, the accuracy of AI fault diagnosis applications and user engagement are improved.

The present application relates to the field of medical imaging technology, disclose a biliary tract cancer CT image prediction method and system based on momentum attention and large model verification, the method comprises: based on the pre-training visual-linguistic large model extracts the visual features of the patient's upper abdominal non-enhanced CT image, constructs a high-dimensional visual embedding vector, initializes the historical momentum attention map and the initial reasoning text sequence, and the first momentum attention map is obtained by guiding and updating through the momentum mechanism; again extract the key image patch set and the initial reasoning text sequence, and the first reasoning text is obtained by interlacing fusion of the image and the text; repeatedly execute attention update and image-text fusion operation until the reasoning thought chain and the preliminary diagnosis conclusion are generated; the correlation degree of reasoning and diagnosis is evaluated by a pure text logical verifier to obtain a logical consistency score, and the target intelligent auxiliary diagnosis report is generated by assembling the score, the present application can improve the efficiency of biliary tract cancer CT image prediction.

The invention provides a staged progressive drainage pipe network system diagnosis method, which comprises preliminary diagnosis and detailed diagnosis: the preliminary diagnosis comprises the following steps of: constructing a pipe network basic data framework, quickly screening and accurately positioning a high-risk area by using detection equipment, and outputting a problem hotspot map; giving monitoring point distribution suggestions in the detailed diagnosis step according to the problem hotspot map; the detailed diagnosis comprises the following steps: deploying a multi-parameter water quality sensor and an electromagnetic flowmeter at a monitoring point position according to a monitoring point distribution suggestion in the preliminary diagnosis step; continuously collecting data in dry and rainy seasons, and generating an external water infiltration amount, a concentration attenuation curve and a pipe network health index according to the data; and generating an engineering decision support report according to the data, and defining a repair target region, a regulation and storage scale and risk control measures. The method effectively avoids the treatment dilemma that the pipe network is damaged after being repaired, improves the scientificity and effectiveness of pipe network treatment, and is especially suitable for pipe network diagnosis projects needing precise cost control and efficient promotion.

The application discloses a bicycle maintenance record management system and method, and relates to the technical field of maintenance management informatization. The system comprises receiving original maintenance work order data stream submitted by a bicycle maintenance terminal, which contains vehicle identification, repair time, fault description and preliminary diagnosis information; performing multi-source information verification and standardized coding on the data stream to generate a to-be-processed maintenance record with unified specifications; based on the record, performing maintenance task dynamic allocation and path planning, continuously updating the maintenance resource state library, and matching the optimal maintenance personnel and spare part resources for the work order according to optimization rules; generating a detailed maintenance scheme containing operation procedures, estimated working hours and required parts according to the matching result; issuing the scheme to the mobile terminal of the matched maintenance personnel to trigger the execution of the maintenance according to the scheme and record feedback. The application realizes the automatic, standardized processing of maintenance data from the source to the execution and the dynamic intelligent scheduling of maintenance resources.

The application discloses a bone marrow morphology acute event identification early warning system and relates to the technical field of intelligent medical treatment, and the technical solution points are as follows: acquiring bone marrow cell image data, pre-processing, obtaining pre-processed image data; inputting the pre-processed image data into a trained AI model, and outputting a classification prediction result. The application can more accurately identify and classify bone marrow cells by applying a visual Transformer and a visual Mamba model, can identify different cell development stages, and can diagnose various blood diseases through an AI model standardized analysis process, reduce professional barriers in the field of bone marrow morphology, reduce absolute dependence on expert experience, and enable areas with insufficient medical conditions to also obtain high-quality preliminary diagnosis.

The present application relates to the technical field of fire safety monitoring, and more particularly to an intelligent fire sensing terminal monitoring system for industrial scenarios, comprising an intelligent fire center, a multi-channel preliminary diagnosis module, a diagnosis matching module, a self-calibration correction module, a screening and hidden danger right module, a fire evolution prediction module and a visual early warning module; the present application is through periodic sampling of multiple sensing channels, fuses multi-dimensional state data to quantitatively evaluate the health of sensors, combines hierarchical judgment and continuous periodic diagnosis to accurately identify channel abnormalities, simultaneously implements directional self-calibration for zero point drift and response attenuation faults, and captures micro-abnormalities in the latent period of fire through baseline difference and other technologies, and combines linear extrapolation and dynamic correction to accurately predict the arrival time of the smoldering period and the open fire period and the remaining safe disposal time, realizing a full-link closed loop from sensor self-diagnosis, self-calibration to fire prediction, and significantly improving the intelligent level of early warning and safe disposal of industrial plant fires.

The application discloses an edge inference driven intelligent auxiliary decision system for medical image recognition, relates to the technical field of medical image recognition auxiliary decision, and comprises a multi-modal adaptation module, an edge inference module, a cloud collaborative module, a knowledge distillation module, a resource scheduling module and a decision output module; the multi-modal adaptation module is used for extracting modal features of CT, MRI and X-ray images through a differentiable neural architecture search method to generate a lightweight edge model; the edge inference module is used for performing real-time inference on the medical images by using the lightweight edge model to output preliminary diagnosis results and confidence scores; the cloud collaborative module is used for setting a threshold value; when the confidence score is lower than the threshold value or the lesion area is smaller than a preset value, the medical images are transmitted to the cloud for deep analysis to output accurate diagnosis results and a lesion segmentation mask; and the knowledge distillation module is used for taking the lesion segmentation mask as a spatial constraint.

The application discloses a molten salt energy storage system leakage early warning method and system based on multi-parameter fusion, and belongs to the technical field of industrial process safety monitoring. The method comprises the following steps: collecting multiple operation parameters of a molten salt energy storage system in real time; executing a main leakage detection logic to generate a primary leakage early warning signal; executing an auxiliary leakage detection logic to generate an auxiliary alarm signal; performing fusion processing based on the primary leakage early warning signal and the auxiliary alarm signal to obtain a preliminary diagnosis result; if there is a detection result of a directly detected leakage point, correcting the preliminary diagnosis result based on the detection result to obtain a final diagnosis result; and outputting a corresponding grade of molten salt energy storage system leakage early warning based on the final diagnosis result. Through comprehensive analysis of multiple parameters related to leakage, and by using the mass balance principle and intelligent algorithms, the application can early discover and accurately diagnose tiny leakage, and realizes early, accurate and reliable early warning of molten salt energy storage system leakage monitoring.

The application provides an explainable AI model dynamic optimization method and system for medical diagnosis. Firstly, the application receives a continuous patient data stream, and then establishes a dynamic calculation priority based on emergency indicators in multi-modal clinical information, which is used to trigger the diagnosis reasoning process of the explainable AI model to generate a preliminary diagnosis opinion. Then, an explanation consistency verification channel is established between the diagnosis analysis processes to perform a cross-model explanation logic alignment operation to generate a consistency verification result. Based on the consistency verification result and the preliminary diagnosis opinion, an optimization trigger instruction is generated, and the internal decision logic of the explainable AI model participating in the diagnosis analysis process is dynamically adjusted according to the optimization trigger instruction. The technical scheme provided by the application realizes the collaborative management and continuous improvement of the explainable AI system in a real medical scenario by constructing a complete closed-loop process from data reception, priority sorting, model reasoning to cross-model verification and dynamic optimization.

The application relates to the technical field of video diagnosis, and particularly discloses a video quality diagnosis system and method based on a multi-modal large model, which comprises a data acquisition module, a data set construction module, a model fine-tuning module, a preliminary diagnosis module and a deep diagnosis module, constructs a professional knowledge enhanced data set of a current video quality diagnosis process, fine-tunes a visual-linguistic base model in a field by using the professional knowledge enhanced data set, obtains a field video quality diagnosis model, inputs video frame sequences and equipment metadata in a to-be-diagnosed original video stream into the field video quality diagnosis model, and outputs a preliminary diagnosis result; deep root causes leading to fault phenomena in the preliminary diagnosis result are inferred to generate a structured comprehensive diagnosis report; and the application can improve the diagnosis efficiency of video quality.

This invention relates to the field of photovoltaic power generation fault diagnosis technology, and in particular to a photovoltaic array fault diagnosis system and method based on artificial intelligence. By encrypting and preprocessing multi-source data, a multimodal dataset is constructed, providing a comprehensive and collaborative data foundation for subsequent analysis. The collaborative diagnosis model can analyze the battery and inverter status in parallel. By combining circuit equivalent models, spatial adjacency relationships, and theoretical power models for calculation, the diagnosis results have physical interpretability. A physical consistency verification rule based on power flow analysis is introduced to cross-validate and logically fuse the preliminary diagnosis results, generating reliable comprehensive fault diagnosis results. This approach solves the technical problem in existing technologies that focus on independent analysis of single components such as photovoltaic cells or inverters, lacking effective fusion and collaborative utilization of multi-source heterogeneous data, which limits the accuracy of diagnosis results.

This invention discloses a bearing fault diagnosis method and system based on a multi-level judgment mechanism. The method involves acquiring bearing vibration signals and preprocessing the signals; calculating the kurtosis index and peak-to-peak value of the preprocessed signal, and determining whether both exceed set values. If both exceed the set values, a fault determination is recorded. The preprocessed signal is then processed using FFT to obtain a spectrum, and the presence of abnormal frequency bands is assessed. If abnormal bands are found, another fault determination is recorded. The number of preliminary fault determinations is accumulated (N). If N ≥ 2, the bearing is determined to be faulty. If N < 2, the preprocessed signal is subjected to algorithm detection. The results of the preliminary diagnosis and algorithm detection are combined to determine whether the bearing is faulty. The introduction of a multi-level judgment mechanism effectively reduces the false alarm rate and significantly improves the accuracy and reliability of fault diagnosis.

The application provides a regional new energy hierarchical diagnosis system based on big data cloud edge-end collaborative calculation, relates to the technical field of power diagnosis, and comprises the following: a data preprocessing unit for preprocessing multi-source state data; a preliminary diagnosis unit for determining a preliminary abnormal device; a model construction and solving unit for determining key abnormal devices and root causes affecting regional performance indexes based on adjoint theory; a strategy determination unit for determining an optimal operation strategy of the device; and a strategy evaluation unit for generating a strategy effect evaluation report and encrypting and uploading the report to the cloud to realize continuous optimization of cloud edge-end collaboration. The application realizes accurate positioning of equipment-level hidden faults of regional new energy field groups to active early warning of system-level operation risks, finally generates and executes a globally optimal collaborative control strategy, forms a closed loop of diagnosis, decision-making and optimization, and significantly improves the comprehensive operation efficiency of regional new energy assets.

The application relates to the field of building anti-seismic technology and discloses a building structure anti-seismic early warning method based on displacement monitoring, which comprises the following steps: mode matching is performed on real-time displacement monitoring data of key monitoring points on a building structure to obtain an intrinsic safety displacement domain; based on the intrinsic safety displacement domain, abnormal spectrum series identification is performed on the real-time displacement monitoring data to obtain an abnormal evolution preliminary diagnosis; the abnormal evolution preliminary diagnosis and position information of the key monitoring points are combined in a topological relationship to obtain an abnormal displacement field distribution; based on the abnormal displacement field distribution, feature comparison is performed on a historical earthquake damage case library to obtain a potential damage type; based on the potential damage type, trend consistency determination is performed on a real-time displacement growth rate and direction of the building structure to obtain a deterioration degree grade of the building structure; strategy mapping is performed on the deterioration degree grade to obtain an anti-seismic early warning response scheme of the building structure; and the application can improve the generation efficiency of the anti-seismic early warning response scheme of the building structure.

The application discloses a high-altitude photovoltaic power station intelligent operation and maintenance and fault prediction method based on artificial intelligence, belongs to the technical field of data processing, and comprises the following steps: step one, estimating the real illumination value of each component at any time; step two, constructing the theoretical power output of the component on the basis of combining temperature aging and installation altitude and other information; step three, determining whether an abnormal trend exists by comparing the deviation trend of the theoretical power and the actual power in a time window and combining the light fluctuation condition to generate an event trigger signal; step four, collecting key data to generate structured features after the event is triggered, and completing preliminary diagnosis based on rules; and step five, outputting the final diagnosis result by fusing the edge feature preliminary judgment result and the power deviation information on the center side. The scheme combines physical modeling and rule judgment, and constructs an intelligent diagnosis scheme suitable for the plateau power station environment.

The application discloses a double-fed wind power converter fault diagnosis method and system based on multi-source data fusion. When the converter detects that an electrical quantity exceeds a threshold value or receives a manual starting instruction of an operation and maintenance personnel, each acquisition module is triggered to work. A preprocessing unit performs interpolation, time axis alignment and denoising processing on the acquired multi-source data, and generates a data set in a unified format. A feature extraction unit extracts fault characteristic quantities by using Fourier algorithm, symmetrical component method, four sampling value method and other methods, and outputs a feature data set. Multiple subsystems are independently diagnosed, and respective preliminary diagnosis results are output. A fusion decision unit substitutes the preliminary results of each subsystem into a preset rule base, performs multi-source data fusion by using a weighted voting method, outputs a final diagnosis conclusion, and outputs the result to a closed loop feedback. The application significantly improves the accuracy and engineering practicability of double-fed wind power converter fault diagnosis by using multi-source data fusion and hierarchical diagnosis, and reduces operation and maintenance costs.

The application discloses a GIS insulation defect diagnosis method and system, collects ultrasonic waves, light pulses and ultra-high frequency signals, and carries out denoising and space-time alignment, forms unified representation after modality coding and cross attention alignment of the three modal signals, inputs an edge lightweight multi-modal model to obtain preliminary diagnosis results and confidence, and when the confidence is lower than a threshold value, triggers cloud edge cooperation, completes deep reasoning by a cloud teacher model and outputs an explanatory report. The application is suitable for GIS equipment online insulation defect diagnosis.

This application provides a method and system for monitoring the counterweight balance of a machine tool spindle, belonging to the field of mechanical equipment condition monitoring technology. The method includes: acquiring multi-source time-series monitoring data during spindle operation; fusing the multi-source time-series monitoring data to extract feature datasets related to the spindle imbalance state; based on the feature datasets, inputting a preset preliminary diagnostic model to perform a preliminary diagnosis of imbalance risk and obtaining current risk index data; if the current risk index data is greater than a preset warning threshold, generating a preliminary imbalance warning signal and identifying the spindle parts that need attention; responding to the preliminary imbalance warning signal, acquiring an enhanced dataset for final imbalance analysis; based on the enhanced dataset, performing imbalance analysis and classification on the spindle parts that need attention based on a dynamic model to obtain the results of imbalance analysis and classification; and outputting corresponding graded warning and correction decision information based on the results of imbalance analysis and classification.

The disclosure provides a kind of self-learning method and system based on non-inductive feedback chemical fault diagnosis, by constructing the operation state perception system of multi-source data fusion, in the setting time window, combined with water quality index change trend, control operation log and equipment operation image constructs non-inductive feedback verification model, realizes the automatic verification and correctness discrimination of preliminary diagnosis result;Further, according to the verification result, the weight of the diagnosis rule node is dynamically adjusted, the secondary diagnosis is triggered for the wrong diagnosis, and the alternative rule path is introduced, while the rule base is scanned regularly for frequency and accuracy, and dynamic optimization operations such as node weight attenuation, redundant path compression and new rule structured insertion are implemented;In addition, the multi-cycle fault mode feature distribution weight dynamic adjustment mechanism and video auxiliary multi-modal consistency verification are introduced, so that the system can adapt to high-frequency and high-risk faults, and enhance the identification ability of physical and chemical coupled faults.

The application discloses a sintering machine full life cycle operation and maintenance method and system based on digital twinning, relates to the technical field of sintering, and comprises the following steps: acquiring single-dimension standard data streams corresponding to each monitoring dimension of a physical entity of a sintering machine; mapping each single-dimension standard data stream to form a single-twin body state data stream; generating sub-component health quantification data streams of each sub-component, generating an initial system diagnosis result data stream of a preliminary diagnosis conclusion of the whole machine based on the sub-component health quantification data streams of each component; generating an intelligent decision control instruction data stream with a target identifier; performing maintenance operations in response to the intelligent decision control instruction data stream, and updating each single-twin body state data stream and dynamic attributes of the digital twin body. The method is based on a complete closed-loop idea of perception, calculation, decision, execution and feedback, and realizes intelligent operation and maintenance of the sintering machine trolley from commissioning, operation, maintenance to scrapping of the full life cycle.

The application relates to the technical field of industrial operation and maintenance, and discloses a production equipment visual operation and maintenance method and system based on digital twinning, which comprises the following steps: structurally recombining real-time operation data to obtain operation data base; virtually and virtually synchronously binding a three-dimensional geometric skeleton and the operation data base to obtain an initial digital twinning body; anchoring the operation parameter nodes in the initial digital twinning body to historical fault records of a target production equipment to obtain an associated digital twinning body; performing real-time abnormal threshold detection and intelligent traceability deduction on the fault parameter nodes in the associated digital twinning body to obtain a preliminary diagnosis report; performing hierarchical coupling rendering on the preliminary diagnosis report and the associated digital twinning body to obtain a visual operation and maintenance interface; and performing visual operation chain compilation on the interactive operation behavior of the visual operation and maintenance interface to obtain precise regulation and control operation instructions; and the application can improve the efficiency of the production equipment visual operation and maintenance based on digital twinning.

Systems and methods for providing a visual representation output descriptive of a preliminary diagnosis can include obtaining radiograph data, processing the radiograph data with a machine-learned model to generate one or more classification outputs, and generating the visual representation output based on the one or more classification outputs. The visual representation output can be generated such that the visual representation output can be provided for display on a plurality of different display types with a plurality of different technical capabilities.

The application discloses a method and application for visual detection of grape guignardia based on RPA-CRISPR / Cas12a Dactylonectria The detection method comprises RPA specific amplification primers, crRNA and ssDNA probes. TUB The RPA specific amplification primers take the gene as a specific recognition target, and can be amplified specifically for the guignardia genus. Dactylonectria The method has high specificity and sensitivity, and is simple, fast and convenient in operation process, and is suitable for rapid screening and preliminary diagnosis of the target pathogen in a field environment or a primary detection scene.

The application provides a multi-source information fusion edge-control-cloud collaborative cable head fault diagnosis method, which comprises the following steps: collecting multi-source signal data at the edge end, preprocessing the multi-source signal data to generate preprocessed multi-source signal data; uploading the preprocessed multi-source signal data to an ultra-fusion base learner deployed in the cloud at the control end; performing preliminary diagnosis on the preprocessed multi-source signal data by the ultra-fusion base learner and outputting a preliminary diagnosis result; transmitting the preliminary diagnosis result to a KAN hypergraph decision fusion network also deployed in the cloud; and performing fusion decision on the preliminary diagnosis result by the KAN hypergraph decision fusion network to obtain a cable head fault diagnosis result. The method provided by the application improves the real-time performance, accuracy and robustness of cable head fault diagnosis through multi-source information integration, distributed computing power collaboration and precise decision fusion, provides a strong guarantee for the safe and stable operation of the power grid, and has important theoretical significance and engineering application value.

Various processes, methods and systems are provided herein for assisting patients, medical providers and other personnel in predicting cancer stage and cancer survival. The systems and methods include determining an indication of a preliminary cancer diagnosis of a given type of cancer for a patient, receiving results of transcriptional sequencing analysis, extracting a set of isoform expression information from transcriptomic data, processing a cancer stemness isoform dataset for a patient, and outputting an indication of the cancer stage prediction or the survival prediction.

The application discloses a kind of multi-modal medical model training, medical information processing method and device, it is related to intelligent medical treatment and artificial intelligence technical field.The specific embodiment of the method includes: generating medical sample data in line with data instruction template;Utilize medical sample data to train basic multi-modal model and obtain multi-modal medical model;In the process of training the basic multi-modal model, the model parameters of the target component are adjusted using a low-rank update matrix;By constructing a variety of medical sample data, the training effect of the trained multi-modal model is improved, and the model training efficiency is improved by the adjustment operation during the training process;By using the trained multi-modal medical model to analyze the health description information of the medical demand party, generate a preliminary diagnosis result, and recommend a matched medical provider for the medical demand party, the degree of refinement of the service for the medical demand party is greatly improved, and the internet medical service experience of the medical demand party is improved.