30 results about "Laboratory Test Result" patented technology

The invention discloses a multi-agent large-model disease diagnosis knowledge reasoning system based on data dual drive, and relates to the technical field of artificial intelligence assisted medical diagnosis. The system collects patient symptom follow-up records, laboratory test results, observation diagnosis probabilities and expert diagnosis recommendation results in a multi-source manner; time sequence evolution characteristics are extracted, a time sequence diagnosis sensitivity coefficient is calculated, and early recognition of disease risks is achieved; in combination with anti-fact simulation and statistical reasoning, a causal consistency coefficient is obtained and is used for verifying causal reasonability of observation diagnosis and contrast results; based on agent group consensus analysis, calculating a game consistency coefficient for judging the credibility of a diagnosis conclusion; positioning and multi-level verification are carried out on abnormal reasoning steps and knowledge fragments, so that the reliability and safety of a result are guaranteed; continuous optimization of the diagnosis model is realized through a log analysis and knowledge backflow mechanism; according to the invention, the accuracy, interpretability and safety of disease diagnosis can be obviously improved.

The invention discloses a shear strength parameter determination method considering earthquake action, which comprises the following steps: collecting a soil sample of a research area, air-drying, dispersing the soil sample into single particles, and sieving to obtain the stone content of the soil sample; the method comprises the following steps: preparing a compacted cylindrical sample from a soil sample, and placing the compacted cylindrical sample in a triaxial testing machine for a triaxial test to obtain static strength parameters of the soil sample; collecting seismic magnitude data of the research area, and determining the seismic magnitude of the research area; and according to the stone content, the static strength parameter and the earthquake magnitude, calculating the shear strength parameter of the research area under the earthquake action by adopting a shear strength damage cracking model. Based on PFC numerical simulation software, dynamic triaxial numerical simulation of the accumulation body is carried out and compared with an indoor test result, the change rule and numerical value of the numerical simulation result are close to those of the indoor test result, the parameter error is smaller than 50%, and the reasonability of the established accumulation body sample model and the calculated dynamic strength parameters is verified.

The invention provides an unmanned aerial vehicle laboratory testing method and device, and belongs to the technical field of unmanned aerial vehicle testing. The scheme comprises the following steps: determining a global reference point based on the position of a laboratory, and further determining a conversion relation between a local northeast high coordinate system and a global coordinate system and a plurality of fixed reference points; according to the fixed reference point, sequentially executing stand setting and starting of an automatic measurement tracker in a laboratory, and further obtaining real-time coordinates of the to-be-tested unmanned aerial vehicle by using the automatic measurement tracker; the GNSS signal generator generates a simulation navigation signal according to the real-time coordinates of the to-be-tested unmanned aerial vehicle and records a simulation track; the to-be-tested unmanned aerial vehicle performs indoor flight test based on the simulation navigation signal; and comparing the simulation track with a flight track recorded by a flight control system of the to-be-tested unmanned aerial vehicle so as to output a laboratory test result. The scheme does not depend on hardware modification of the unmanned aerial vehicle, the implementation difficulty is reduced, the implementation cost is saved, and controllable testing of medium and large unmanned aerial vehicles in the indoor environment is facilitated.

The invention relates to the technical field of biological and medical diagnosis, in particular to a biomarker for predicting whether a patient suffering from pyotoxic myocardial injury has a short-term death risk or not and application of the biomarker, and the biomarker is the ratio of erythrocyte distribution width to albumin. According to the method, retrospective queue research design is adopted, two data sets, namely MIMIC-IV and eICU-CRD, are used, suppurative myocardial injury patients meeting conditions are included, covariants such as baseline features, laboratory inspection results and complication information of the patients are collected, the patients are divided into two groups according to RAR medians, the relation between RAR and short-term death of the patients is analyzed by adopting multiple statistical methods, and the accuracy of the short-term death of the patients is improved. A risk prediction model of short-term death of the patient suffering from the pyotoxic myocardial injury is constructed, so that a clinician can identify the patient suffering from the pyotoxic myocardial injury with high death risk in an early stage, a personalized treatment strategy can be formulated more accurately, the survival rate of the patient suffering from the pyotoxic myocardial injury is increased, and the method has a wide application prospect.

The invention relates to the technical field of clinical medical treatment, and discloses a disease deterioration risk identification method and system based on depth time sequence clustering enhancement, and the method comprises the steps: 1, obtaining multi-modal clinical sequence data of a patient, including physiological indexes of a time sequence, a laboratory detection result, historical diseases and medication data; 2, performing feature extraction and classification on the patient sequences by adopting a knowledge enhanced sequence clustering method, and grouping the patient sequences according to future outcome distribution of the patient sequences; 3, enabling the model to quickly adapt to a prediction task of a new patient subgroup through a meta-training process; and step 4, based on the trained meta-model, carrying out rapid adaptation on the new patient subtype, and predicting the possibility that the new patient subtype has a deterioration event in a certain time window in the future. The method and the system can effectively learn the disease change mode of the patient under the condition of limited clinical data, improve the prediction accuracy of the new patient subgroup, and are especially suitable for clinical prediction scenes under the condition of small samples.

The invention discloses a carbonate rock pore retention mechanism simulation method under an ultra-deep heat-fluid-solid coupling effect, and relates to the technical field of rock physics. The method comprises the following steps: preparing a carbonate rock sample, obtaining a CT scanning slice image of the carbonate rock sample, extracting three-dimensional pore information, preparing a plunger sample in a laboratory, carrying out a quasi-triaxial experiment, calibrating mesoscopic parameters by using a laboratory test result, constructing a carbonate rock model, and arranging a measuring ball in the carbonate rock model, the method comprises the following steps: dynamically monitoring the change of porosity and pore pressure, determining a strength reduction function of carbonate rock through a laboratory experiment, applying a true triaxial compression servo environment in which a temperature field and a stress field cooperatively change to a carbonate rock model, and performing true triaxial experiment numerical simulation by using the carbonate rock model. The internal pore condition of the carbonate rock in each evolution stage is obtained, the pore retention mechanism of the carbonate rock under the ultra-deep heat-fluid-solid coupling effect is determined, and technical support is provided for research of carbonate rock reservoirs.

The present disclosure relates to techniques for preprocessing samples and using preprocessed samples and machine learning models to predict clinical diagnostic tests for a patient from their historical laboratory testing data. Particularly, aspects are directed to obtaining datasets including features and / or historical laboratory test results for subjects, filtering the datasets based on a denoise-balance scheme to obtain filtered datasets, training a machine learning model using the filtered datasets to obtain a trained machine learning model, and providing the trained machine learning model. A candidate machine learning model may be an ensemble of classifiers implemented with a boosting algorithm, and the ensemble is trained by applying base machine learning algorithms on different distributions of the filtered datasets. The ensemble is then combined into a machine learning model having the set of learned model parameters for predicting results for clinical diagnostic tests.

The invention discloses a rock physical forward modeling method applicable to formation pore fluid of carbon dioxide, and relates to the technical field of petroleum and natural gas engineering. The method comprises the steps of firstly obtaining a carbon dioxide physical property constraint condition based on a state equation of carbon dioxide under a reservoir temperature and pressure condition, and then based on the constraint condition and according to logging information of a target well, core analysis and a laboratory test result, carrying out formation evaluation to calculate reservoir parameters. Then, based on reservoir parameters, the sandstone content is obtained through calculation, a rock physical volume model of a target well is constructed, and finally, based on the model, corresponding rock physical forward modeling is conducted according to different carbon dioxide saturations by means of the equivalent medium theory to generate stratum elastic attribute parameters. And the change relation between the corresponding saturation and the stratum elastic attribute parameters is quantitatively represented, so that the CO2 quantitative monitoring precision and reliability can be remarkably improved by comprehensively considering the special physical properties of CO2, the fluid replacement mechanism and the seismic wave propagation characteristics.

The invention relates to an infectious tophus ulcer wound nursing scheme assessment method and system, and the method comprises the steps: collecting the standardized electronic medical record data of a patient through a medical information system, including demostatistics, wound characteristics, laboratory inspection index sequences and nursing records; after structured processing, timestamp unification and missing value filling are conducted on the data, the data are input into a pre-trained deep learning model, expected wound healing probabilities, predicted healing time and complication risk scores corresponding to different nursing schemes are output, then a comprehensive assessment report is generated, the report is stored in a database, and a visual query interface is provided. And meanwhile, collecting actual nursing result data for continuous optimization and updating of the model. According to the invention, quantitative evaluation and prediction of the nursing scheme are realized, clinical decision making is effectively assisted, and the accuracy of nursing management and the resource utilization efficiency are improved.

The present application relates to the field of oil and gas field development engineering, disclose a kind of intelligent optimization method for discrete element contact parameters of proppant particle and flexible fiber mixture, comprising: based on the principle of injection method angle of repose experiment, build micro funnel device, reduce the scale of experiment under the premise of keeping the original size of material, improve the efficiency of calculation;Adopt "ball column chain + joint" fiber model, coupling JKR adhesion model represents the interfacial adhesion between particles, establish high-precision discrete element simulation model;Through Plackett-Burman, steepest climbing experiment screening key influencing factors, for the problem that each factor and angle of repose is nonlinear mapping relationship, construct GA-BP model, combine GA algorithm optimization, preferred parameter combination, compare the results of discrete element simulation and laboratory test results, verify the accuracy of contact parameters.The present application solves the problem that the existing method is difficult to calibrate mixture, improves the precision and efficiency of parameter calibration, and is helpful to the research and development of hydraulic fracturing process.

The invention discloses a cytarabine syndrome risk prediction model, a training method thereof and a system adopting the same. The model training method comprises the following steps: constructing an artificial intelligence model; wherein the input of the artificial intelligence model comprises the weight and the heating duration of the to-be-evaluated object; the output of the artificial intelligence model is the risk probability that the to-be-evaluated object belongs to the cytarabine syndrome fever; large sample data are adopted to train the artificial intelligence model, cases with fever of the cytarabine syndrome are positive samples, and other fever cases are negative samples. According to the present invention, the identification standard of the cytarabine syndrome fever and the infected fever is established, and the risk probability of the cytarabine syndrome of the object to be evaluated can be evaluated by analyzing the difference of the two detection results in the laboratory, such that the unreasonable use of the antibacterial agent is reduced, the medical cost is reduced, and the drug resistance risk of the antibacterial agent is reduced.

This invention provides a method for calculating the critical point of fatigue damage in full-thickness asphalt pavement, relating to the field of road engineering technology. The invention first divides the full-thickness asphalt pavement into multiple sub-layers, then obtains its annual temperature field and annual axle load spectrum, determines the temperature model of the full-thickness asphalt pavement and the number of equivalent axle load applications per hour, and combines laboratory test results to obtain the dynamic modulus calculation equations and multi-temperature fatigue equations for each sub-layer. The temperature of each sub-layer is obtained using the full-thickness asphalt pavement temperature model, and the dynamic modulus value of each sub-layer is determined using the dynamic modulus calculation equations. Then, the flexural strain response of each sub-layer is calculated based on its dynamic modulus value, and its fatigue life is calculated using the multi-temperature fatigue equations for each sub-layer. Combined with the number of equivalent axle load applications per hour, the fatigue damage value of each sub-layer is calculated and accumulated to obtain the cumulative fatigue damage of each sub-layer in the full-thickness asphalt pavement, accurately obtaining the critical damage point of the full-thickness asphalt pavement.

The invention discloses an intelligent private data fragmentation and recombination method and system based on AI, and relates to the technical field of data protection. Comprising the following steps: S1, constructing a medical knowledge graph: identifying electronic medical record data, a medical image report and a laboratory detection result, taking identified entities as knowledge graph nodes, constructing the medical knowledge graph, and marking clinical importance levels and sensitive data types; s2, intelligent fragmentation: according to the set clinical value-privacy risk two-dimensional evaluation matrix, performing association maintenance fragmentation on the high clinical value data, and performing differential privacy fragmentation on the high sensitive data; and S3, data recombination: according to a fragmentation result, storing the fragments in heterogeneous nodes, and meanwhile, according to an access permission level, carrying out differential data recombination on the fragments. Therefore, while the data security is ensured, the semantic integrity after recombination is also ensured, and intelligent balance between privacy protection and clinical value of the medical data is realized.

The invention relates to a pneumoconiosis nodule detection method, and belongs to the technical field of pneumoconiosis nodule detection, and the method comprises the following steps: S1, summarizing the detection case information of pneumoconiosis nodules of all hospitals, and importing the model learning case information into a pneumoconiosis nodule detection analysis model; s2, importing the basic information of the patient, the laboratory examination result and the lung function test result into a pneumoconiosis nodule detection and analysis model for comparison; s3, if no hidden danger exists in the examination result, determining that no pneumoconiosis nodule exists; s4, screening and analyzing; and S5, constructing learning information, deleting the person sensitive information of the patient after the diagnosis of the patient is completed, constructing model learning case information, and importing the model learning case information into a pneumoconiosis nodule detection and analysis model for diagnosis and learning. According to the method, the doctor seeing information and the examination reports of pneumoconiosis nodules of all hospitals are summarized to form the case information, the analysis model is constructed to perform mechanical learning on the pathological information, and the information features are extracted, so that doctors are assisted to perform judgment, and the diagnosis efficiency is improved.

This invention discloses a method and system for processing clinical medical laboratory data based on big data, belonging to the field of clinical data analysis technology. First, clinical laboratory data and medical record data are collected from a hospital database. The clinical laboratory data undergoes structured preprocessing to construct a word co-occurrence matrix. Based on the entity relationships between the clinical laboratory data, clinical feature vectors are generated. A knowledge graph is established based on the medical record data. Based on the knowledge graph, the clinical feature vectors are classified using an improved ConvE model to obtain laboratory test results data. Finally, a disease probability processing engine is constructed to characterize the laboratory test results data and output the final diagnostic medical record. This invention solves the problem that the model's diagnostic logic does not conform to medical common sense, making the AI's diagnostic reasoning process closer to that of human experts.

The invention relates to the technical field of rubber puncture resistance, and discloses a rubber material puncture resistance testing device and evaluation method based on pavement simulation, and the evaluation method comprises the following steps: S1, sample preparation; s2, performing a puncture test; s3, extracting parameters; s4, calculating a motion state correction coefficient of the rubber sample, and performing primary correction on the puncturing energy consumption by using the motion state correction coefficient; s5, calculating a puncture speed correction coefficient of the to-be-detected probe, and performing secondary correction on puncture energy consumption by using the puncture speed correction coefficient; and S6, replacing the to-be-tested probe or the rubber sample, and repeating the steps S2 to S5 to obtain performance data under different temperatures and different puncture forms. Therefore, the puncturing energy consumption is continuously corrected twice based on the motion state correction coefficient and the puncturing speed correction coefficient of the rubber sample, the actual working condition mapping and the rate dependence are considered, the actual working condition of the tire is simulated as much as possible, and the prediction capability of a laboratory test result on the real use performance is further effectively improved.

The invention discloses a construction method and application of a prediction model for primary corpus callosum-related pneumonia, and the construction method comprises the following steps: obtaining clinical data and laboratory test results of patients with primary corpus callosum degeneration; carrying out single-factor analysis and screening related factors having statistical significance with the primary corpus callosum degeneration-related pneumonia; the method comprises the following steps: carrying out dimensionality reduction treatment on related factors with statistical significance of primary corpus callosum degeneration-related pneumonia, and carrying out multi-factor logistic regression analysis on the related factors subjected to dimensionality reduction treatment to determine independent related factors of primary corpus callosum degeneration-related pneumonia; and according to the independent related factors of the primary corpus callosum degeneration-related pneumonia, constructing a prediction model of the primary corpus callosum degeneration-related pneumonia. The prediction model constructed by the invention has good prediction capability, and clinicians can identify high-risk patients with primary corpus callosum degeneration related pneumonia as soon as possible and perform intervention and treatment as soon as possible.

The invention provides an early grading decision-making method for an acute pulmonary embolism deterioration risk. The method comprises the steps of obtaining a data set; the data set comprises clinical information, laboratory detection results and CT pulmonary artery imaging of the acute pulmonary embolism patient; three-dimensional structures of the pulmonary artery, the pulmonary vein, the left ventricle, the right ventricle, the left atrium and the right atrium in CT pulmonary artery imaging are segmented; constructing a three-dimensional pulmonary vein and pulmonary artery blood vessel tree model; obtaining difference filling data of contrast agent imaging; obtaining a pulmonary circulation reflux score; constructing a four-cavity center plane; calculating RV / LV; screening the preprocessed clinical information and laboratory detection results; fusing the screened characteristic data related to the exacerbation of the acute pulmonary embolism disease, the pulmonary circulation reflux score and the RV / LV; inputting the training set into the model for training, and inputting the verification set into the trained model for optimization; and inputting the test set into the final optimized model to obtain a prediction result of the grading diagnosis index of the acute pulmonary embolism patient.

The application discloses a joint wellbore casing deformation-acoustic emission b-value fracture activation condition multidimensional judgment method, which comprises the following steps: based on casing deformation analysis, preliminarily statistically controlling law of fracture own properties on fracture activation, obtaining acoustic emission b-value of experimental scale critical activation point, and constructing a fracture activation condition judgment method combining casing deformation analysis and acoustic emission b-value; the application considers the influence law of multiple properties of the fracture itself on casing deformation intensity, combines wellbore casing deformation information with acoustic emission sequence b-value of the experimental scale critical activation point, and extrapolates the experimental results to geological conditions by taking the underground statistical law as a constraint, thereby solving the problem that the laboratory test results are too idealized, simultaneously considering the multi-solution of the actual geological engineering data, and realizing quantitative characterization of the fracture activation, which greatly improves the accuracy and applicability of the activation condition prediction in theory and method, and meanwhile, the wellbore casing deformation information and fracture geometric data are easy to obtain, and the application range is wide.

The application discloses a kind of simulation methods of carbonate rock pore retention mechanism under super deep thermal fluid-solid coupling, it is related to rock physics technical field.The application is prepared by preparing carbonate rock sample, obtains its CT scanning slice image extraction three-dimensional pore information, after laboratory preparation plunger sample is carried out pseudo triaxial experiment, laboratory test result is used to calibrate micro parameter after construction carbonate rock model, cooperate in carbonate rock model and layout measuring ball, dynamically monitor porosity and pore pressure variation, by laboratory experiment, determine the strength reduction function of carbonate rock after, carbonate rock model is applied temperature field and stress field collaborative change true triaxial compression servo environment, using carbonate rock model carries out true triaxial experiment numerical simulation, obtains the pore condition inside carbonate rock of each stage evolution, determines the pore retention mechanism of carbonate rock under super deep thermal fluid-solid coupling, provides technical support for carbonate rock reservoir research.

The present invention discloses a medical intelligent dialogue method based on deep learning, which relates to the field of intelligent medical technology. The present invention constructs a rare disease knowledge graph. Even when the training data is insufficient, the implicit connection between the disease and the symptoms can be deduced through the correlation relationship in the graph, which greatly enhances the ability to handle complex cases such as rare diseases. Through the graph reasoning mechanism, a more accurate list of rare diseases can be provided, and relevant diagnostic solutions can be reasonably and preferentially displayed to users to reduce the risk of misjudgment. Through the multimodal Transformer model, multi-source data such as medical records, medical images and laboratory test results can be effectively integrated to generate a unified comprehensive feature representation. The deep integration has the ability to comprehensively analyze the patient's health status from different angles, thereby improving the accuracy of diagnosis. Based on the preliminary diagnosis results, the order of inquiries and the depth of questions can be adjusted according to the specific conditions of different patients, providing a more accurate and personalized inquiry experience.

In the diagnosis process, a clinician makes full use of multi-modal information such as chief complaint, medical images and laboratory test results. A deep learning model used for auxiliary diagnosis does not meet the requirement. In some aspects, a transformer-based representation learning model may be used as a clinical diagnostic aid for processing multi-modal inputs in a unified manner. The model does not learn modal-specific features, but uses an embedded layer to convert an image, an unstructured text and a structured text into visual lexical elements and text lexical elements. And using bi-directional blocks with intra-modal and inter-modal attention to learn an overall representation of radiographs, unstructured chief complaints and medical records, structured clinical information, such as laboratory test results and patient demographic information. The performance of the unified model in the aspect of lung disease recognition exceeds that of an only image model and that of a non-unified multi-modal diagnosis model (respectively improved by 12% and 9%), and the performance of the unified model in the aspect of COVID-19 patient adverse clinical outcome prediction exceeds that of the only image model and that of the non-unified multi-modal diagnosis model (respectively improved by 29% and 7%). A unified multi-mode transformer-based model is fully utilized, so that a patient triage process can be simplified, and a clinical decision-making process is promoted.

The invention provides a method and system for checking the sensitivity of a sensor emitting ultrahigh frequency by using an iron core, and the method comprises the following steps: carrying out a laboratory test, and determining the relation between the injection signal intensity of the iron core of a transformer and the apparent discharge capacity; a nanosecond ultrahigh-frequency pulse generator is arranged in combination with a laboratory test result; injecting an ultrahigh-frequency pulse signal into a transformer core by using the nanosecond ultrahigh-frequency pulse generator, and collecting an output signal of the ultrahigh-frequency sensor to be detected; processing the output signal; checking the sensitivity of the ultrahigh frequency sensor to be tested according to the processed output signal; and optimizing the arrangement of the ultrahigh frequency sensor to be tested or replacing the sensor according to the checking result. According to the invention, the test process is simplified through field verification, and the accuracy and practicability of sensitivity verification are significantly improved.

The invention discloses a heart failure risk prediction model construction method based on transfer learning, and the method specifically comprises the following steps: firstly, collecting clinical data, including medical history, sign data and laboratory examination results, of a person without heart failure and a person with heart failure, carrying out the data cleaning and standardization processing, and generating a heart failure data set; secondly, enabling the medical pre-training model to adapt to a heart failure risk prediction task through a transfer learning technology, and generating a heart failure model; then, optimizing heart failure model parameters on a heart failure data set to improve prediction accuracy; dividing the heart failure risk into three levels of low risk, medium risk and high risk by using a threshold algorithm; and finally, evaluating the effect of the heart failure model by adopting the performance indexes. The method has the advantages of high prediction precision, high adaptability, high calculation efficiency and the like, and is suitable for early prediction and intervention of clinical heart failure risks.

The present invention provides a method for constructing a mesoscopic joint constitutive model of high-temperature rock, which relates to the technical field of numerical simulation of rock mechanics. The method first establishes a preliminary mathematical expression of the mesoscopic joint constitutive relationship of rock considering crack slip and temperature effects, and obtains the macroscopic physical and mechanical properties of the rock; then establishes a numerical geometric model of the rock sample, and assigns the thermodynamic parameters and preliminary constitutive relationship of the target rock to the unit body and the contact surface of the unit body of the numerical model; replicates the laboratory test conditions and conducts parallel numerical simulation tests; finally, compares the numerical simulation results with the laboratory test results, and uses the back analysis method to obtain the coefficient equation required for the mesoscopic joint constitutive relationship of the corresponding rock specimen, thus completing the construction of the mesoscopic joint constitutive model of high-temperature rock. This method simultaneously considers the crack slip effect and the temperature effect. The mesoscopic joint constitutive model of high-temperature rock constructed by using the back analysis method has a high degree of coincidence with the test results and can be applied to the numerical simulation of rock mechanics.

The invention provides a method for controlling the internal quality of round steel through numerical simulation. The method comprises the steps that S1, the change trend of a prefabricated hole in the core of a casting blank under the laboratory condition is obtained; s2, according to the boundary dimension of the laboratory test material, the shrinkage cavity dimension, the material parameters and the rolling reduction parameters of each pass, establishing a thermal-mechanical coupling numerical calculation model, simulating and calculating the rolling process of the laboratory material, comparing and analyzing the matching degree of the shrinkage cavity simulation calculation results of different passes and the laboratory test results, and verifying the accuracy of the model; and S3, the verified model is used for calculating the minimum compression ratio needed after rolling of the shrinkage cavities of different grades, the minimum compression ratio needed when a certain mark of casting blank with the shrinkage cavities inside is rolled into qualified round steel is obtained, and the casting blank with the shrinkage cavities is guided to be put into the rolling specification range. According to the method, the maximum level needing to be controlled by the casting blank internal shrinkage cavity under the conditions of different casting blank marks, different casting blank sizes and different rolling ratios can be quantitatively researched, and requirements are provided for level control of the continuous casting blank internal shrinkage cavity.

The application discloses a multi-agent large model disease diagnosis knowledge reasoning system based on data double driving, relates to the technical field of artificial intelligence assisted medical diagnosis, and through multi-source collection of patient symptom follow-up records, laboratory test results, observation diagnosis probability and expert diagnosis recommendation results, the system extracts time sequence evolution characteristics and calculates a time sequence diagnosis sensitivity coefficient, realizes early identification of disease risk; combined with counterfactual simulation and statistical reasoning, a causal consistency coefficient is obtained, which is used for verifying the causal rationality of observation diagnosis and control results; based on agent group consensus analysis, a game consistency coefficient is calculated, which is used for judging the credibility of the diagnosis conclusion; abnormal reasoning steps and knowledge fragments are positioned and verified in multiple levels, so that the reliability and safety of the results are guaranteed; through log analysis and knowledge backflow mechanism, the diagnosis model is continuously optimized; the application can significantly improve the accuracy, explainability and safety of disease diagnosis.

The invention discloses a pulmonary tuberculosis recognition system based on multi-modal fusion and expert-assisted optimization, which belongs to the technical field of artificial intelligence and comprises a data acquisition module, an imaging examination image, a laboratory examination result and an electronic medical record. The data preprocessing module is used for extracting a first feature by utilizing an iconography examination image, extracting a second feature by utilizing a laboratory examination result and extracting a third feature by utilizing an electronic medical record; the third feature comprises 32 sub-features and contribution degrees corresponding to the sub-features; the optimization module is used for optimizing the contribution degree based on expert diagnosis experience; and the fusion module is used for performing modal fusion on the first feature, the second feature and the optimized third feature to generate a pulmonary tuberculosis recognition result. According to the method, imaging examination images, laboratory examination results and electronic medical records are fused, the contribution degree of expert experience to the features is optimized, intelligent detection of pulmonary tuberculosis is finally achieved, and the method has good generalization ability and pulmonary tuberculosis detection precision.

The cerebrospinal fluid collection and storage rack comprises a collection box, a supporting frame, a hollowed-out plate, a controller, a storage unit and a temperature control unit, the bottom of the collection box is fixedly installed at the top of the supporting frame, and the outer wall of the hollowed-out plate is fixedly installed on the inner wall of the collection box; the bottom of the controller is fixedly installed on the temperature control unit, the storage unit is fixedly installed in the collection box, and the temperature control unit is fixedly installed on the top of the supporting frame. Under the control of the temperature control unit, the negative pressure sampling tube is stored at low temperature, so that the problems of biomarker change caused by microbial growth and enzyme activity change, change of form or quantity of cell components such as white blood cells, influence of chemical substance decomposition on detection accuracy, pH value fluctuation, pollution risk increase and the like are solved; the quality of the cerebrospinal fluid and the reliability of a laboratory detection result are ensured.

This invention relates to a method and system for early disease warning and diagnosis in large-scale pig farms, belonging to the field of pig farming technology. This method utilizes knowledge graphs and abnormal features for comprehensive disease risk assessment, determining the target disease type and current disease stage of the target pigs. Based on this, an early warning is generated. An initial treatment plan is generated based on the warning information, disease type determination, and disease stage determination. On-site diagnosis and treatment are then performed on the target pigs, and samples are collected and sent for testing, forming diagnostic verification data. This invention unifies and links the initial warning record, initial diagnosis result, on-site actual treatment execution information, re-examination results, and laboratory test results of the target pigs, forming a verification data chain for individual cases. This provides a basis for subsequent verification of warning and diagnosis results, reducing the accumulation of misjudgments caused by the inability to verify model outputs alone.