47 results about "Diagnosis tool" patented technology

The invention relates to the technical field of medical and multi-modal large models, and discloses a disease prediction and auxiliary diagnosis system construction method and system based on a multi-modal large model. The method comprises the steps of report format conversion, data cleaning and table image-to-structured text conversion. Constructing a retrieval knowledge base to enhance the retrieval capability; precise cue word design and reasoning optimization are carried out; small sample learning and model fine tuning; the invention discloses a multi-modal large model integration and visualization system. According to the system, the accuracy problem of a traditional disease risk prediction method is effectively solved, and a more reliable auxiliary diagnosis tool is provided.

Methods and systems are provided for information retrieval pathway guidance. In particular, the systems and methods provided apply artificial intelligence to novel tasks related to retrieving remotely accessible data such as detecting competency levels of users, generating personalized guidance for individual users based on the retrieval goals and initial competency level of a user, generating custom diagnostic assets for those goals based on current strengths and weaknesses, generating content for custom questions for those diagnostic assets, and dynamically tracking and updating the competency level of the user during the course.

The invention provides a breast cancer patient pCR prediction classification method based on image-gene interpretability deep learning. The method comprises the following steps: dividing an obtained data set into a training set and a test set; splitting all the three-dimensional MRI images into two-dimensional slice images; the gene text features of each breast cancer patient are classified into N different sets; segmenting a two-dimensional slice image corresponding to the training set into a plurality of patches; each patch and the gene text feature corresponding to each patch are converted into a corresponding high-dimensional Embedding (high-dimensional Embedding); respectively multiplying H by Wk and Wv to obtain K and V; multiplying G by WQ to obtain Q; obtaining a gene guidance image feature CoAttn; the CoAttn and the Q are fused to obtain a feature set F; inputting the F into a network model, and training the network model based on a loss function; inputting the two-dimensional slice image corresponding to the test set into the trained network model, and outputting a plurality of classification results; and adopting a maximum voting strategy to make decisions on the plurality of classification results. According to the method, pCR and npCR classification is carried out on the patient based on a co-attention mechanism of gene text features and MRI images, the interpretability of model decision is enhanced, and a more visual and reliable auxiliary diagnosis tool is provided for clinicians.

The invention discloses a bidirectional reasoning diagnosis method based on a large model, which can be applied to a clinical intelligent diagnosis scene. Firstly, key abnormal features in hospital admission records of patients are concerned through abnormal feature extraction; secondly, similar medical records are retrieved as diagnosis experience learning; thirdly, forward reasoning is deduced from the features of the patient, and possible diseases are deduced; in the reverse reasoning, a cause tracing method is adopted, and related characteristics are traced back from a diagnosis result. And through combination of deduction and induction, the reasoning ability of the large model is enhanced. And finally, carrying out correction and confidence evaluation on the diagnosis result to realize iterative reflection optimization and ensure the reliability and interpretability of the diagnosis process. An automatic diagnosis tool based on a large model is provided for the medical field, the diagnosis accuracy and efficiency can be improved, and an innovative solution is provided for clinical intelligent diagnosis.

The invention relates to a method for constructing a radio and television service fault diagnosis agent, which comprises the following steps of: 1, completing the construction of a basic agent project based on an MCP architecture, realizing the construction, deployment and association of three components, namely Host, Client and Server, of the MCP, and calling and packaging an existing diagnosis service API; step 2, realizing Qamp; the retrieval of the A document is enhanced and optimized, so that the response accuracy of an agent component MCP Host is improved; 3, based on the semantic slicing technology, retrieval enhancement optimization of a service fault diagnosis guide manual is achieved, and the decision accuracy of an agent component MCP Host is improved; 4, management, association, prompt word optimization and vectorization of an API document are achieved based on the semantic slicing technology, the description detail degree of a tool under an agent component MCP Server on an MCP Host is improved, and the hit rate and the accuracy rate of the MCP Server diagnosis tool are called; the problem that the manual service process of the current traditional radio and television service fault diagnosis scene is low in efficiency is solved, and the expansion of the service fault diagnosis agent scene is completed by using the natural language.

A vehicle diagnostic system and method for identifying and presenting vehicle safety systems on a vehicle for calibration by an operator includes providing a vehicle diagnostic computer tool that includes a display screen and is configured to be connected to a diagnostic port of a vehicle. The vehicle diagnostic tool is configured to determine vehicle safety systems present on the vehicle and to receive vehicle damage information inputs corresponding to areas on the vehicle in which there is damage. A system list program generates a list of vehicle safety systems equipped on the vehicle requiring calibration based on the determined vehicle safety systems present on the vehicle and the vehicle damage information inputs, where the list corresponds to vehicle safety systems present on the vehicle that are disposed in damage areas. The vehicle diagnostic computer tool is further configured to display the list on the screen.

The invention relates to the field of disease risk prediction models, and discloses a thyroid cancer metastasis risk prediction model and a construction method and application thereof. The construction method of the model comprises the following steps: S1, collecting and preprocessing a sample; s2, gene expression quantity detection; s3, data set division and standardization processing; s4, constructing a deep learning model; s5, performing model evaluation; and the biomarker group for detecting the gene expression quantity in the S2 is composed of RPS4Y1, PKHD1L1, CRABP1, KRT18P8, AGPAT4, CPQ, SLC26A7 and RBP4. The prediction model can be used as a clinical auxiliary diagnosis tool and is used for guiding operation range selection, postoperative follow-up visit strategy making and early intervention of high-risk patients, and the precise diagnosis and treatment level of thyroid cancer is improved.

The application relates to the field of disease prediction, and particularly relates to an epilepsy prediction system based on electroencephalogram-electrogastrogram signals collected synchronously, which comprises the following modules: a data acquisition module, which is used for acquiring data, wherein the data comprises electroencephalogram data and electrogastrogram data; a first analysis module, which is used for obtaining average electrode inconsistency indexes of first channels and second channels based on a first model according to time sequence data; and a prediction module, which is used for comparing the average electrode inconsistency indexes of a subject with preset evaluation thresholds, so as to predict epilepsy patients. The system provided by the application can more accurately and efficiently distinguish epilepsy patients from healthy people, and can be applied to the preliminary screening of epilepsy for a large population (for example, a community or a physical examination center) as an auxiliary diagnosis tool.

The application relates to the technical field of intelligent agriculture and plant protection, and particularly discloses a broccoli black spot early diagnosis system and method based on multi-modal machine learning fusion, which comprises a portable collection platform, a mobile experiment terminal and a server. The portable collection platform is integrated with a hyperspectral imaging camera, a chlorophyll fluorescence imager, a dark-adapted leaf clamp and a camera for sample barcode recognition, and is provided with an adjustable height support and a controllable light source to ensure the consistency of data collection conditions. The mobile experiment terminal is internally provided with a physicochemical index rapid detection module, including a portable PCR instrument for on-site nucleic acid rapid extraction and amplification and a miniature ultraviolet spectrophotometer for rapid determination of pigment content. The broccoli black spot early diagnosis system and method based on multi-modal machine learning fusion are highly integrated, portable and automated, are suitable for a field environment and provide an efficient disease diagnosis tool for non-expert users.

The invention discloses an interpretable machine learning method for predicting multi-organ injuries of diquat poisoning patients, and the method comprises the steps: constructing and verifying a prediction system of eight kinds of organ injuries through a clinical database; toxic encephalopathy, myocardial injury, acute kidney injury, circulatory failure, skeletal muscle injury, liver injury, lung injury and gastrointestinal tract injury are covered. According to the method, early-stage efficient prediction of multi-organ injury is achieved, deep insight is provided for potential biological mechanisms of organ injury, clinical formulation of individualized intervention strategies is facilitated, the prognosis management level of diquat poisoning patients is expected to be remarkably improved, and the incidence rate and case fatality rate of multi-organ failure are reduced. According to the technical scheme, high prediction precision is kept, meanwhile, balance of interpretability, stability and clinical applicability of the model is achieved, a reliable auxiliary diagnosis tool is provided for organ injury risk assessment of acute poisoning patients, and the method has important clinical application value and wide market prospects.

The present invention provides a magnetic contact comprising: a stationary core magnetized by a coil; a movable core spaced apart from the stationary core by a first distance (d1) and moved by the magnetic attraction of the magnetized stationary core; a longitudinal cross bar connected to the movable core; a movable contact carrier horizontally disposed on one side of the cross bar; a movable contact disposed on one surface of the movable contact carrier; a stationary contact spaced apart from the movable contact by a second distance (d2)<sb / >; and a longitudinal contact residual quantity diagnosis tool disposed upright on the movable contact carrier so as to be adjacent to the cross bar, wherein, when over travel of the cross bar represented by the difference between the first distance and the second distance occurs, the upper side of the contact residual quantity diagnosis tool opens to the outside at the same height as the value of the over traveling.

The invention discloses a system for endometriosis diagnosis and a computer storage medium. Aiming at major adjustment of endometriosis diagnosis standards, biomarkers and ploidy information of circulating endometrial cells in easily available samples such as peripheral blood of a patient are detected, and comprehensive risk assessment is performed by utilizing an optimization algorithm model, so that the diagnosis accuracy of endometriosis is improved. The invention provides an objective and quantifiable noninvasive diagnostic tool adapted to the adjusted standard, and the method solves the problem of missed diagnosis caused by false negative in the existing surgical diagnostic method, and has important clinical application value, social benefit and market prospect for improving the overall diagnostic level of endometriosis.

We provide the system. [Solution] Information collection methods for collecting users' biometric data, A signal transmission means for transmitting the aforementioned biometric data to an augmented reality platform, The platform includes a diagnostic means that analyzes the biometric data to evaluate the user's mental state, Activity generation means that generates activities optimized for the user based on the results of the diagnostic means, A presentation means for notifying the user of the generated activity through visual or audio feedback, A feedback collection means collects user responses to the aforementioned activities again using information gathering means and reflects them in subsequent optimization, A system that includes this.

This invention discloses an apparatus and medium for an automated terminal AGV fault diagnosis system, including an AGV control unit, an AGV network connection unit, a vehicle selection unit, a task selection unit, a driving file selection unit, a task execution unit, an automatic report generation unit, a dispatch building module, a remote monitoring unit, and a remote fault diagnosis system. This invention optimizes the AGV network connection unit by establishing a 5G vehicle-mounted base station within the unit, increasing the bandwidth to 1000 Mbps to support the data flow of subsequent remote fault diagnosis tools. It also incorporates a driving process parameter recording unit and a self-developed remote fault diagnosis software tool, enabling real-time acquisition and processing of AGV driving data and remote, intelligent, and automated identification and processing of abnormal states. This lowers the technical threshold for maintenance personnel, improves the operational efficiency and accuracy of fault diagnosis, and reduces the frequency of on-site fault handling by maintenance personnel.

The invention relates to the technical field of operation and maintenance of communication operators, in particular to a method and system for complementing a positioning rule based on large model reasoning ability, and the method comprises the following steps: fault feature and tool preparation, cue word framework construction, thinking process generation and expert auditing, rule generation and current network verification, and feedback optimization mechanism. The method has the beneficial effects that by virtue of the reasoning capability of the Deepseek large model, the rule data of fault diagnosis is generated by continuously adjusting the input conditions such as the fault feature library and the fault diagnosis tool. Supplementing or perfecting a current network fault positioning rule; the problems of high expert dependency, insufficient rule credibility, difficulty in verification and the like in a traditional rule are solved, the time investment of experts is reduced, and the existing rule is perfected; an efficient, credible and iterable fault positioning mechanism is realized, and the intelligent level of network operation and maintenance is improved.

A system is provided.SOLUTION: A system comprising: diagnostic means for diagnosing a technical level of a user; teaching material providing means for providing a teaching material and a task suitable for the user based on a result of the diagnostic means; evaluation means for evaluating a result of the task and generating feedback; and progress management means for managing learning progress of the user and providing a message and a reward for maintaining motivation.SELECTED DRAWING: Figure 1

The invention is suitable for the technical field of medical intelligent diagnosis and machine learning, and provides a pneumonia screening and risk prediction model construction method based on a reverse neural network, and the method comprises the steps: firstly carrying out the preprocessing of a bacterial pneumonia clinical symptom data set, and dividing a multi-classification problem into a plurality of binary classification tasks; secondly, constructing a CPT algorithm based on a random forest and a convex hull theory, calculating a feature weight through information gain, and screening out high-contribution symptom features; and finally, inputting the screened features into the optimized BPNN, and obtaining a prediction model through repeated iterative training. The method has good classification accuracy, the number of the selected features is obviously reduced compared with a traditional model, and the method can be used as a clinical auxiliary diagnosis tool, is applied to clinical bacterial pneumonia infection screening and severe risk early warning, and provides decision support for timely treatment.

The invention relates to the field of medical auxiliary diagnosis, in particular to a tool calling method and system for medical auxiliary diagnosis, and the method comprises the steps: collecting historical case data from a medical information system, carrying out the preprocessing, generating an empirical data set, receiving the current symptom information of a patient, and carrying out the semantic analysis of the current symptom information, extracting scene features of the current symptom segmented words, building a tool matching model, inputting the current symptom segmented words and the scene features into the tool matching model, outputting a corresponding auxiliary diagnosis tool type, and calling a corresponding auxiliary diagnosis tool according to the auxiliary diagnosis tool type. And the current symptom information of the patient is transmitted to the auxiliary diagnosis tool to generate the diagnosis suggestion, so that the historical case data and the current symptom information of the patient are effectively integrated, the auxiliary diagnosis tool currently corresponding to the patient is accurately matched, the diagnosis efficiency and accuracy are improved, and powerful support is provided for medical diagnosis.

The invention provides a multi-target joint detection kit for prostatic cancer, a detection system and application, multiple targets in the kit are selected from a PCAT1 gene, a PSA gene, a TTC3 gene, an EPCAM gene and an MIR4435 gene, and the kit further comprises a primer and probe combination aiming at each marker. According to the method, the diagnosis accuracy can be improved, the weight interpretation model can be constructed, the clinical decision can be optimized, and a non-invasive and high-compliance auxiliary diagnosis tool is provided for the problems of traumatic detection and gray areas in the prior art.

The invention discloses a sarcopenia assessment system and medical equipment, and the system comprises a data processing module which is used for splitting and preprocessing clinical data; the feature screening module is used for determining an optimal feature subset; the model building and training module is used for building and optimizing a sarcopenia evaluation model; the model evaluation module is used for evaluating the generalization performance of the model; and the practical application module is used for evaluating a new patient. Based on a bioelectrical impedance analysis technology, four key characteristics of gender, body weight, extracellular fluid resistance and intracellular fluid resistance are automatically screened out, and a multi-model preferential strategy is adopted to construct a high-performance evaluation model. According to the method, the defects that a traditional method depends on expensive equipment, complicated processes, subjective indexes and the like are overcome, rapid, objective and accurate screening of sarcopenia is achieved, and an efficient and reliable auxiliary diagnosis tool is provided for clinic.

The present application relates to the field of disease prediction, and particularly relates to a cognitive impairment prediction system based on synchronous acquisition of electroencephalogram and electro-gastrogram signals, comprising: a data acquisition module, configured to acquire data, wherein the data comprises electroencephalogram data and electro-gastrogram data; a first analysis module, configured to obtain average electrode inconsistency indexes of first and second channels based on a first model according to time series data; and a prediction module, configured to compare the average electrode inconsistency indexes of the subject with preset evaluation thresholds, thereby predicting cognitive impairment patients. The system provided by the present application can more accurately and efficiently distinguish mild cognitive impairment patients from healthy people, and can be applied as an auxiliary diagnosis tool for the initial screening of mild cognitive impairment in a large population (for example, a community or a physical examination center).

A disease diagnosis tool validates a diagnosis of a patient. The disease diagnosis tool receives a high-resolution image of a body part. The disease diagnosis tool divides the high-resolution image into a plurality of tiles and inputs a representation of each tile into an encoder portion of a model configured to perform a disease diagnosis based on the representations. The encoder has an attention mechanism. The disease diagnosis tool obtains a plurality of tokens representative of an attention of the encoder based on the attention mechanism. Each token is associated with a position of a tile of the plurality of tiles. The disease diagnosis tool generates a heat map corresponding to the image of the body part. The heat map comprises a two-dimensional image having pixels corresponding to tiles each with an amplitude based on a level of attention represented in the plurality of tokens corresponding to the tiles.

The invention discloses a gene marker combination, a kit and a system for breast cancer molecular typing, and belongs to the field of precise medical big data analysis. The gene marker combination is composed of 17 gene markers, namely, CLDN19, DSG1, FABP7, FGFBP1, KLK7, KLK8, MAPK4, MAPT-AS1, MAPT-IT1, MIA, PTPRZ1, ROPN1, ROPN1B, SCN2B, SERPINA11, SOX11, and SRARP. The invention further discloses a preparation method of the gene marker combination. Based on the combination, a brand new breast cancer GPS17 molecular typing system is constructed, the breast cancer can be finely divided into eight molecular subtypes with remarkable expression difference, and at least four different molecular subgroups in the Luminal A subtype are systematically analyzed for the first time. Experiments show that the molecular typing system is obviously superior to a traditional PAM50 molecular typing system in balance accuracy, macro F1 score and macro AUC score. The invention further provides a corresponding detection kit and an automatic typing system integrated with a machine learning model, and an auxiliary diagnosis tool with excellent performance is provided for accurate diagnosis and treatment decision of breast cancer.

The application discloses a visual AI auxiliary writing and intelligent diagnosis system and method for quantification strategy learning, and belongs to the technical field of financial technology and artificial intelligence. The system comprises: a teaching AI strategy generation module, which analyzes natural language strategy description into a three-layer structure of a strategy skeleton layer, a condition logic layer and a parameter configuration layer, generates a structured strategy description language intermediate representation with three-layer teaching annotations of logic annotations, variant prompts and learning point annotations, and converts the structured strategy description language intermediate representation into target real-time environment code; a learning path adaptive scheduling module, which adopts deep reinforcement learning dynamic planning personalized learning paths based on user multi-dimensional capability portraits and strategy difficulty quantification models; a strategy risk diagnosis and market adaptation module, which generates a strategy multi-dimensional risk portrait, calculates strategy-market adaptation degree scores and triggers early warnings; a strategy variant intelligent generation module, which generates diversified strategy variants based on a genetic algorithm and analyzes parameter-performance influence modes through comparative learning; and a multi-agent collaborative strategy diagnosis module, which performs parallel diagnosis by four special agents of code auditing, overfitting detection, market sensitivity analysis and signal quality evaluation, performs causal reasoning by an arbitration agent, and generates a natural language diagnosis report. The application solves the problems of poor code learnability, incompatible learning and real-time code, lack of personalized path guidance and intelligent diagnosis tools in existing quantification strategy learning platforms, and significantly reduces the learning threshold of quantification strategies.

A digital intelligence teaching diagnosis tool comprises a network interconnection display module, a teaching screen and a learning screen which are connected through a wireless network. An audio module and a screen recording module are arranged in the learning screen, and the audio module records teaching of a teacher, so that students can conveniently review; the online examination module comprises an examination paper issuing terminal with a teaching screen as a host and an examination paper receiving terminal with a learning screen of each student as an extension, and the learning screen of each student has an independent IP number; the network interconnection touch pen comprises a coding label, an identification unit, an AI auxiliary analysis unit and a comprehensive analysis module, wherein the coding label, the identification unit and the AI auxiliary analysis unit are arranged in the network interconnection touch pen; in teaching interaction, the network interconnection display and interaction feedback module realizes real-time synchronization of a teaching screen and a learning screen, so that teachers and students can communicate with each other in time, the teachers can comment the students to answer in time, and the students can also quickly feed back questions, teaching interactivity is greatly improved, and the learning effect is enhanced.

The invention relates to an in-vehicle device which suppresses that a server cannot provide appropriate service. A communication module (16) performs processing for collecting vehicle information from a vehicle control ECU (12) connected to an in-vehicle network and transmitting the vehicle information to a management server (20). A communication module (16) monitors a CAN signal transmitted via the DLC. The communication module (16) determines whether or not the diagnostic tool (21) is connected via the DLC on the basis of the monitoring result of the CAN signal. The communication module (16) includes the determination result of the connection determination in vehicle information and transmits the vehicle information to a management server (20).

The present invention discloses a container fault recovery method, device, and electronic device. Relating to the field of cloud computing technology or other related fields, the method comprises: inspecting a container to be diagnosed based on a fault diagnosis container to obtain inspection data; analyzing the inspection data using a fault diagnosis tool within the fault diagnosis container to obtain a diagnosis result; when the diagnosis result indicates an abnormality in the container to be diagnosed, determining a target recovery strategy corresponding to the diagnosis result; and performing fault recovery on the container to be diagnosed based on the target recovery strategy. This invention addresses the technical problems of the prior art, such as the inability to achieve automatic recovery of container faults and the low troubleshooting efficiency.

The invention belongs to the technical field of intelligent household appliances, and particularly relates to a household appliance fault processing method and device and a storage medium. According to the method, fault processing data of the household appliance is acquired through a cloud server, and the fault processing data at least comprises one or more of the following items: data reported by the household appliance, detection data for detecting the household appliance by adopting a fault diagnosis tool, and fault field confirmation data; inputting the fault processing data into a pre-trained fault recognition model to obtain a first fault recognition result output by the fault recognition model, the first fault recognition result comprising a fault type, one or more fault causes, confidence of each fault cause, and a processing measure corresponding to each fault cause, the fault identification result is sent to the fault processing terminal; according to the method, the fault processing efficiency of the household appliance is improved, and the user experience is improved.

The invention discloses a CTSNet model construction method for grading the severity of a carpal tunnel syndrome, and the method is characterized in that a CTSNet backbone network, an Attention Pooling attention fusion layer and a classification layer which are sequentially cascaded are adopted to construct a CTSNet model for intelligently grading the carpal tunnel syndrome through multi-modal electrophysiological signals, five multi-modal time-frequency diagrams of a patient are used as model input, and the model input is used as model output. According to the method, CTS intelligent grading based on time-frequency graph deep learning is realized, and a CTSNet backbone network is a residual structure integrating a frequency attention mechanism and optimization and comprises a 7 * 7 initial convolution layer, a BatchNorm2d batch normalization layer, a ReLU activation function, a 3 * 3 maximum pooling layer and four CTS special residual blocks which are cascaded in sequence. Compared with the prior art, the method has the advantages that different development stages of CTS can be accurately recognized, the accuracy, fineness and reliability of CTS grading are remarkably improved, the performance of the model on different patient groups and equipment is more stable through a two-stage training strategy and a residual framework, and a more effective intelligent auxiliary diagnosis tool is provided for clinical practice.

The invention discloses a method for optimizing a memory tool. The method comprises a development stage, a test stage for preventing a memory problem from being introduced, and a test stage, wherein the memory problem missed in the development stage is found; in the construction and deployment stage, the memory problem of the production environment is monitored and quickly responded; establishing a problem checking process and a knowledge base; and accurately positioning and radically treating the problem. According to the method, a problem finding stage is advanced to a development and test stage as far as possible, the problem finding stage is solidified into a research and development process through an automatic tool chain, and meanwhile, a powerful monitoring and diagnosis tool is provided for a production environment, so that a complete closed loop from'prevention '-gt, 'discovery'-gt, 'monitoring '-gt and'radical treatment' is formed.