117 results about "Case analysis" patented technology

The invention discloses a construction method and a construction system for a clinical diagnosis model, and a clinical diagnosis system, and relates to the technical field of medical treatment. The construction method for a clinical diagnosis model comprises: step S1, acquiring data, data acquisition sources being a plurality of electronic medical records; step S2, processing the acquired data; step S3, according to known typical medical history in the processed data, establishing a case analysis model, and training and evaluating the case analysis model; step S4, applying the trained and evaluated model in the clinical diagnosis system, to form a the clinical diagnosis model. The method and the systems are used to improve accuracy for a doctor to diagnose diseases.

The invention relates to a traffic signal coordination control optimization method for an emergency rescue vehicle driving path. The method comprises emergency rescue prioritization, path type classification, signal priority control, signal coordination control, and a bi-level programming model; relevant coordination control research on paths is conducted; first, emergency rescue characteristics and objects are analyzed, research on upper level dynamic phase difference and lower layer path green wave coordination in different path forms is conducted, and relevant case analysis and verificationare performed. The method disclosed in the invention is characterized by real time performance, traffic signal coordination priority control over an emergency rescue path can be exerted based on timewhen an emergency rescue team reaches a crossroad and real time vehicle load information of general vehicles, emergency rescue response time can be shortened, and casualties and property loss can beeffectively reduced.

A computer performed method models a spatial index having n spatial regions defined in a multidimensional space using a tree-based model representing an infinite number of arrangements of n spatial regions in the multidimensional space allowable by the spatial index using a finite number of tree representations, computes an average retrieval complexity measure for content retrieval using the spatial index based on the tree based model, and provides a spatial index recommendation based on the average retrieval complexity measure. In some embodiments a spatial index selection module selects the spatial index based on average retrieval complexity measures for candidate spatial indices that are functionally dependent upon a number of spatial regions to be defined by the spatial index.

The invention provides a large legal data management system based on fuzzy inference. The system comprises a data collection module, a data preprocessing module, a database module, a central server, an information push module and a mobile terminal; the data collection module is used for collecting laws and regulations, cases, monitoring, legal practitioners and social data, storing the same in corresponding databases, and storing the data in the database module after being processed by the data preprocessing module to be trimmed and classified, a fuzzy inference module of a central database carries out large data analysis on the legal provisions and case data and generates accurate case analysis and relevant legal analysis reports, and finally, the information push module pushes the reports to the mobile terminal to provide accurate legal services for users. According to the large legal data management system based on fuzzy inference provided by the invention, internal data relations in related legal laws and regulations systems, case systems, monitoring systems, legal practitioner systems and social systems in law management are mined in depth by the fuzzy mathematics algorithm to provide accurate and efficient quantitative tool support for judicial works.

The invention discloses a remote teaching method and system for sharing digital pathological section data. By means of the remote teaching method and system, pathological sections are digitalized, students major in pathology can call the digital pathological sections and corresponding diagnostic messages and case analysis information conveniently for remote study, wherein the digital pathological sections, the corresponding diagnostic messages and the case analysis information are stored in a server, so that the students can obtain remote video of teachers and training cost and training period of pathological doctors are greatly reduced.

Financial transformation in one aspect establishes a hub and spoke network of models including at least a process model as the hub and at least components model, value driver model, applications model, solutions models as the spoke connected to the process model. A plurality of correlations is inferred among said models using daisy-chain analyses that navigate the hub and spoke network of models, and heat map is generated. Heat map analysis, application shortfall analysis, organization shortfall analysis, solution analysis, and business case analysis are performed.

The invention provides a people's contradiction conciliation case searching and mediation strategy recommending method. The method includes the following steps of 1, data collecting and preprocessing; 2, word segmentation and vector representation; 3, TF_CDF feature clustering; 4, automatic generation of a desensitization typical case set and obtaining of clustering categories and category keywords; 5, generation of a medication strategy prompt; 6, index creating and relevance calculating, wherein the core of a full text search engine comprises index creating and relevance calculating, and typical case data and the clustering categories obtained in the step 4, the mediation strategy prompt obtained in the step 5 and the like are synchronized in elasticsearch for index creating; 7, search result and interface display, wherein a user inputs query content, similar typical cases, case classes and class tag information and mediation strategy recommendation are obtained, and a similar case analysis report is automatically generated. The people's contradiction conciliation case searching and mediation strategy recommending method is high in accuracy and speed.

The invention provides a medical and health management system based on big data. The system comprises a case management subsystem. The medical and health management system is characterized in that the case management subsystem comprises a case analysis module, a patient takes a photo of a case and uploads the photo through a client side, analysis and classification are performed through an application server, the case is converted into a wordpages formatted file to be stored in a storage server, an early warning is given out if testing data of testing items are higher than a normal value and sent to the client side, an outpatient prescription in the case is sent to an artificial background terminal, and the accuracy of the outpatient prescription is artificially recognized. By recording patient cases, examination results, healthy living way, treatment conditions at any time, prognosis conditions, follow-up visit conditions, hospital diagnosis and treatment process optimization, network medicine purchasing and a doctor-patient communication platform, particularly on the basis of large-data analysis, the health conditions of a patient are known at any time, a sanitary system can achieve guidance conveniently, expense budget and monitoring are achieved, and the intelligent and user-friendly degree is high.

A method, system and apparatus for constructing a comprehensive test plan using a case analysis graph is provided. Embodiments of the present invention further provide for automatically generating test cases from a case analysis graph and for measuring functional coverage of the test cases. Additional embodiments of the present invention provide for visualizing both the comprehensive test plan and functional coverage data.

The invention provides a power distribution network project investment decision technology considering comprehensive effects. The power distribution network project investment decision technology comprises the following steps: s1, establishing a multi-dimensional power distribution network investment comprehensive effect evaluation index system; s2, determining an evaluation index set and a comment set, and establishing a fuzzy relation matrix of evaluation indexes; s3, carrying out comprehensive weight calculation by using an analytic hierarchy process and an entropy weight method; s4, obtaining a final evaluation result according to the product of the comprehensive evaluation fuzzy vector and the weight vector of the index. Calculation case analysis shows that the investment decision ofthe power distribution network project can be scientifically and comprehensively supported, and the method has good application and popularization prospects.

A computer performed method models a spatial index having n spatial regions defined in a multidimensional space using a tree-based model representing an infinite number of arrangements of n spatial regions in the multidimensional space allowable by the spatial index using a finite number of tree representations, computes an average retrieval complexity measure for content retrieval using the spatial index based on the tree based model, and provides a spatial index recommendation based on the average retrieval complexity measure. In some embodiments a spatial index selection module selects the spatial index based on average retrieval complexity measures for candidate spatial indices that are functionally dependent upon a number of spatial regions to be defined by the spatial index.

The invention relates to a BIT and case fusion based equipment fault diagnosis method and system. The system comprises an equipment information collection module, a fault analysis and diagnosis module, a case analysis and diagnosis module, a fault processing module and a fault information management module; the equipment information collection module, the fault analysis and diagnosis module, the case analysis and diagnosis module and the fault processing module are connected successively; the fault information management module is in bidirectional connection with the fault analysis and diagnosis module, the case analysis and diagnosis module and the fault processing module; and the fault analysis and diagnosis module is connected with the fault processing module. An equipment BIT diagnosis is fused with a fault case diagnosis, an equipment fault is diagnosed in a manner that the BIT diagnosis plays a leading role and the fault case is used for inference and post supplement, and the fault diagnosing accuracy and efficiency of the equipment are improved.

The invention discloses a perforation transient well fluid pressure prediction method. According to the perforation transient well fluid pressure prediction method, theoretical derivation, algorithm implementation and case analysis are combined, condition hypothesis is carried out based on perforation physical process analysis, and a one-dimensional model of a perforation wellbore pressure field is built; according to the change characteristics that well fluid pressure movement has the one-dimensional unsteady plane movement rule, the well fluid state and the gas state for pushing well fluid to move, underground relevant characteristic parameters are substituted in, well fluid pressure prediction is achieved through certain duration calculation, and well fluid pressure prediction passes energy conversation inspection. By means of the perforation transient well fluid pressure prediction method adopting physical modeling, numerical calculation and energy conversation inspection, the well fluid pressure peak prediction precision can be ensured, the change rule of pressure along with time is obtained, more useful information can be provided, and a theoretical foundation is provided for scientific perforation design.

The invention discloses an electric vehicle resident area charging load analysis and prediction method based on a mathematical model. The method comprises: 1, regional parking behavior analysis is conducted on the parking generation rate and the parking space supply and demand conditions of sub-regions in a city; 2, SOC characteristic analysis is carried out according to the mileage model and therelation model of electric vehicle movement and power consumption; 3, analyzing the charging behavior of the electric vehicle by combining the step 1 and the step 2 according to the charging characteristics of the residential area in the city; 4, integrating all stages of analysis to form a mathematical model, carrying out specific case analysis, and obtaining a design evaluation scheme. The electric vehicle charging load prediction can provide technical support for reasonable scheduling, peak clipping and valley filling and electric power strategies of an urban intelligent power grid, and meanwhile provide reference basis for distribution, site selection and constant volume of charging piles in future. The invention aims to study the location property of an urban resident area, and meanwhile, the behavior characteristics of the electric vehicle are investigated in detail.

The invention discloses an intelligent signal processing system of power grid equipment. A data layer is provided with a database module and a real-time information receiving module, an application layer is provided with an auxiliary decision making module, an abnormal signal association analysis and diagnosis module and a fault signal analysis and diagnosis module, and a user layer is provided with a human-machine interaction module and an online decision making module. The system comprises a real-time state and a research state, both of which can realize the association analysis and diagnosis of an equipment abnormal signal before the occurrence of an accident, a fault signal diagnosis function when the accident occurs, and timely assistance to the decision of the regulation and control personnel; and meanwhile, a historical signal analysis and diagnosis result can be inquired so as to provide historical data to the case analysis and training of the regulation and control personnel. The system has expandability and can be embedded with an SCADA / EMS system; and meanwhile, the system reserves partial interfaces to facilitate the compatibility with other systems. The intelligent signal processing system of the power grid equipment ensures the universality and independence of the system function.

The invention provides a case intelligent pushing method and system based on case semantic analysis, and the method comprises the following steps: S1, carrying out the preprocessing of a case description text of a case, which comprises word segmentation, part-of-speech tagging, and stop word removal; S2, extracting important features of the case according to the preprocessed case description textto form a feature vector of the case; And S3, associating related cases according to the feature vectors, obtaining the comprehensive similarity between the case and each related case by adopting a case feature similarity calculation method, sorting the related cases according to the similarity, and pushing the cases with high similarity. Through the method and the system provided by the invention, the workload of case analysis and manual processing can be reduced, the working cost and the time cost of police officers are greatly reduced, and the case solving efficiency is improved.

The invention provides an automatic steel plate surface defect recognition method based on case-based reasoning in order to solve the problems that a mechanism model used for recognizing steel plate surface defects is difficult to establish, which does not facilitate detection and control of product quality. The automatic steel plate surface defect recognition method automatically recognizes seven defects of cracks, scaling, scarring, humping and others. A case-based reasoning recognition model is established through the steps of case library establishing, weight allocation, target case obtaining, numerical value normalization, case retrieval, case reusing, case storing and others. A recognition algorithm is implemented, so that recognition accuracy is improved. The problem that due to subjectivity and uncertainty of allocating case-based reasoning characteristic variable weights, the recognition accuracy rate is low is solved. The experiment result shows that the method can accurately recognize the defects on the surface of a steel plate and is good in sensitivity and distinctness, the processing efficiency of the defects on the surface of a steel plate is improved, the rejection rate is decreased, and the method is of great significance to case analysis on the defects on the surface in the production process of the steel plate, production operation method improving and product quality improving.

The invention relates to the fields of judicial experts and natural language processing, and particularly relates to an intelligent dispatching method and system for mediation cases based on feature extraction. The method comprises the steps of obtaining mediation case classification conditions and feature words, comparing feature word similarity of a to-be-assigned mediation case and each mediator mediation case under the same case type, and in combination with current workload and service rating of each mediator, sorting the mediators and assigning the mediation cases. The system comprises adata acquisition module, a text classification module, an intelligent distribution module, a mediator portrait module, a case input module, a case analysis module and a data storage module. The method and the system have the characteristic of high assignment accuracy, the mediation satisfaction can be improved, the mediation efficiency and the service quality can be improved, dispute checking canbe performed, the mediation resources can be optimized, and the working efficiency can be improved.

A method, system and apparatus for constructing a comprehensive test plan for a design under test (DUT) using a case analysis graph is provided. Embodiments of the present invention provide for automatically generating test cases of the test plan from the case analysis graph by traversing paths through the case analysis graph to select a sequence of components to be exercised by a DUT. Selection of the components is constrained by one or more rules. The rules, in aspects of the invention, provide for selection of specified components to be included in the sequence of components.

A method and an apparatus to obtain a surface mapping of a ballistic piece of evidence (BPOE) under examination, such as a bullet or a spent cartridge case, that can be used thereafter as a 3D signature for identifying purpose during ballistic test comparison. The method comprises providing a measurement unit adapted to acquire a relief map of the surface of the BPOE and acquiring with the measurement unit the relief map of the surface to thereby obtain the mapping of the surface of the BPOE. Preferably, the measurement unit of the present invention comprises a confocal sensor such as confocal microscope. Also, the present invention includes acquiring the relief map of the bullet surface or of the cartridge case surface by acquiring and assembling a mosaic of regional reliefs that are partly overlapping with their surroundings regional reliefs.

A surveillance target positioning method requires arrangement of a laser ranger, a thermal imaging camera, an optical imaging camera and a control unit on a head in an area under surveillance; the optical imaging camera, the thermal imaging camera and the laser ranger are mounted on a suspension arm of the head, and optical axes of lenses of the three components are kept coaxial in order to perform positioning and surveilling. The surveillance target positioning method comprises the steps of setting coordinates of the head; setting a reference azimuth; driving, by a surveillance system, the thermal imaging camera and the optical imaging camera to scan a target area, performing laser ranging in case of emergency, and reading the azimuth and pitching angle from the control unit on the head;uploading to a GIS (geographic information system) for displaying. The surveillance target positioning method according to the technical scheme has the advantages that after discovering emergencies, surveillance personnel can position coordinates quickly and accurately, an emergency site is subjected to correspondence with the displayed position in the GIS, and conveniences and quick response areprovided for case analysis and disposal options.

The invention discloses an elevator safety early warning method based on machine learning. Automatic motion matching, noise interference processing, the super resolution and other methods are adopted,effective information is subjected to fusion processing, and related features are extracted to conduct dynamic capturing and early warning. According to the elevator safety early warning method, thevideo information is dynamically captured to be correlated to an automatic early warning mechanism, so that a security check person is reminded of appearance of targets so as to take measures in time;and meanwhile, videos of related information are automatically extracted so that maintaining personnel can conduct series and incorporate case analysis and video comparison analysis treatment, and valuable clues and the like are found.

A system and method for evaluating multiple corner case static timing analyses. For each node within the analysis, the variability and margin of the node is used to create a risk factor that is used to identify nodes for further analysis. In some cases, a subset of nodes may be selected for static timing analysis with several additional corner cases. The variability of the node may be determined by the difference between the maximum and minimum value of the node between corner case analyses. The margin may be determined by the difference between the actual timing and the required timing. Various ratios using variability and margin may be used to identify those nodes on which to perform further analysis.

The invention discloses an autism child social dysfunction symptom analysis method based on machine learning. The method comprises the following steps of acquiring a social behavior characteristic setof the autism child in each type; acquiring the previous case analysis report of the autism child; learning the recorded information by a system; updating a fitting function; and performing new caseanalysis by means of the updated fitting function. The invention further discloses an autism child case analysis system based on machine learning. According to the analysis method based on machine learning, a related characteristic analysis rule is automatically learned according to existing case analysis information of the child; and furthermore in the later analysis activity, a diagnosis resultis automatically recommended to rehabilitation personnel according to the newly input characteristic parameter and the learned analysis method, thereby greatly improving rehabilitation efficiency andaccuracy, and realizing wide application prospect.

The invention provides a data analysis system based on electronic physical evidence rapid extraction. The data analysis system comprises a mobile phone communication analysis module; The mobile phonecommunication analysis module comprises a statistical analysis graph unit which is used for formulating a communication activity rule, a time-sharing activity rule and an average daily call time rulestatistical graph and classifying communication opposite ends according to social relations between regions and owners of the mobile phone; The address book collision unit is used for collision of atleast two address books; The call record unit is used for screening and querying all call records, and screening different query conditions according to different case analysis dimensions to obtain corresponding key call information; And the short message unit is used for extracting the consumption information in the mobile banking short message. The data analysis system based on rapid extractionof the electronic physical evidence solves the problem that the working efficiency of police officers is low due to the fact that the police officers manually find the electronic physical evidence inthe prior art.

Systems and methods for estimating the lifetime of an electrical system in accordance with embodiments of the invention are disclosed. One embodiment of the invention includes iteratively performing Worst Case Analysis (WCA) on a system design with respect to different system lifetimes using a computer to determine the lifetime at which the worst case performance of the system indicates the system will pass with zero margin or fail within a predetermined margin for error given the environment experienced by the system during its lifetime. In addition, performing WCA on a system with respect to a specific system lifetime includes identifying subcircuits within the system, performing Extreme Value Analysis (EVA) with respect to each subcircuit to determine whether the subcircuit fails EVA for the specific system lifetime, when the subcircuit passes EVA, determining that the subcircuit does not fail WCA for the specified system lifetime, when a subcircuit fails EVA performing at least one additional WCA process that provides a tighter bound on the WCA than EVA to determine whether the subcircuit fails WCA for the specified system lifetime, determining that the system passes WCA with respect to the specific system lifetime when all subcircuits pass WCA, and determining that the system fails WCA when at least one subcircuit fails WCA.

The invention relates to a magnetic powder brake type testing device of a large-torque electric actuator for a valve. The testing device comprises a support, a pulling and pressing sensor component, a force arm component, a magnetic powder brake, an optical-electricity encoder component, a closed-type transmission mechanism and a control box of a programmable logic controller (PLC). The magnetic powder brake is fixed on the support. An output shaft of a tested electric actuator transmits torque to the magnetic powder brake through the closed-type transmission mechanism. A connecting disc of the tested electric actuator is fixed with the force arm component. The pulling and pressing sensor component is connected with a force arm rod of the force arm component in a 90-degrees mode. The optical-electricity encoder component is respectively connected with a main shaft of the closed-type transmission mechanism and the control box of the PLC. The testing device is compact in structure, high in test precision, low in production cost, capable of conveniently and accurately measuring and displaying the torque, travel, a rotation speed, case analysis of service life test and the like of the tested electric actuator in real time, and especially suitable for testing of the electric actuator with large torque of 12000Nm.

The invention relates to a flight taxi-out time prediction method based on the queuing theory. The method comprises steps that a static flight taxi-out time prediction model is constructed; actual whole-year historical flight operation data is acquired and pre-processed; historical flights are grouped according to gate position proximity and sliding path consistency principles, the barrier-free taxi-out time of each flight group is calculated; the actual historical flight operation data is utilized, the waiting-for-departure time of a flight is predicted based on the queuing theory; the barrier-free taxi-out time and the waiting-for-departure time are substituted into the static flight taxi-out time prediction model, and model output is the taxi-out time of the flight group. The method is advantaged in that a method integrating theoretical derivation, algorithm implementation, system simulation and case analysis is utilized, the departure flight taxi-out time is predicted by utilizing the static flight taxi-out time prediction model and is predicted based on the queuing theory, and taxi-out time prediction accuracy is improved compared with a traditional prediction method.

The method comprises the input of boundary condition, the definition of magnetic tube recovery expected value, the real-time process data acquisition of the shaft roasting system, the parameter determination based on the case inference, the feed correction based on the magnetic tube recovery ratio prediction, the feedback correction based on the magnetic tube recovery ratio analysis value, the case storage and maintain and other steps. In the method, the on-line process data provided by the routine computer control system and the routine instrumentation is combined in the hand sampling data to set up the intelligent optimization setting model of the shaft roasting system main technical parameter based on the case analysis, so as to realize the optimization control of the shaft roasting system being gearing to the needs of the production target.