Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

48 results about "Case model" patented technology

A case modeling is a model which deals with how diverse users communicate with the system in resolving a problem. It depicts the objectives of the users, the communications between the systems and the users, and the procedures of the system in fulfilling these objectives. A case model has numerous model elements.

Hospital doctor-seeing navigation method

The invention discloses a hospital doctor-seeing navigation method. The method comprises the following steps that a hospital navigation system is established, and the hospital navigation system comprises a symptom analysis module, a hospital map module and a voice navigation module, wherein the symptom analysis module comprises case models of each department of a hospital, and the hospital map module is a three-dimensional modeling map for simulating actual buildings of the hospital; the hospital navigation system is logged in; symptom descriptions are input, and the system provides the department corresponding to symptoms for a patient, and a whole set of map navigation of the corresponding department is generated; the patient confirms the assigned department and makes a corresponding choice, and if the patient obeys the assignment of the system, the patient conducts a series of procedures such as registration and doctor-seeing according to the navigation; if the patient thinks that the assigned department is unreasonable, the patient can manually select the department, the system generates corresponding department navigation, and the patient conducts a series of procedures such as the registration and the doctor-seeing according to navigation indication. According to the hospital doctor-seeing navigation method, the patient can be instructed to register, and a series of doctor-seeing route navigation is provided for the patient.
Owner:AFFILIATED YONGCHUAN HOSPITAL OF CHONGQING MEDICAL UNIV

Optimization method for wind-generation-set gear-case elastic support span

The invention discloses an optimization method for the wind-generation-set gear-case elastic support span. The optimization method includes the steps that 1, according to the initial parameter of a target wind generation set, a wind-generation-set transmission chain model containing a gear case model is set based on the many-body dynamics, and the initial parameter comprises an initial value of the span of a gear-case elastic support; 2, the value of the span in the wind-generation-set transmission chain model is continuously adjusted, and is subjected to modal and time domain analysis during adjusting every time, the potential resonant frequency obtained by modal and time domain analysis can be avoided after adjustment, and the adjusted wind-generation-set transmission chain model is output; 3, the value of the span in the adjusted wind-generation-set transmission chain model is continuously subjected to fine tuning optimization, the operating characteristic of a transmission chain in the wind-generation-set transmission chain model is best accordingly, and the best span value is obtained and output. By means of the optimization method, the resonance risk of the transmission chain can be avoided, and meanwhile the movement performance is best; the optimization method has the advantages of being simple in achieving method, reasonable in span design and high in optimization efficiency.
Owner:CSR ZHUZHOU ELECTRIC LOCOMOTIVE RES INST

Method and device for optimizing non-intrusive terminal identification capability test scheme

PendingCN110969281ARealize intelligent optimization combinationExcellent test timeForecastingSpecial data processing applicationsMatrix expressionCase model
The invention discloses a method and device for optimizing non-intrusive terminal identification capability test scheme, and belongs to the field of intelligent power utilization. The method comprisesthe following steps: solving a pre-constructed optimization model of ta non-intrusive terminal identification capability test scheme to acquire an optimized test scheme, creating a non-intruding terminal identification capability test scheme optimization model according to a matrix expression model obtained through pre-conversion, and acquiring the matrix expression model through conversion according to a pre-established case model in a residential electricity consumption scene case library; and applying the obtained optimized test scheme to a simulated detection platform of a non-intrudingterminal to generate a test report. The method is applied to the detection platform of the non-intruding terminal and the test scheme optimization realizes the optimization combination of test cases,so that the resident power utilization environment can be more closely simulated and demonstrated practically, and the objectivity and validity of the load identification capability test of the non-intruding terminal are improved.
Owner:STATE GRID JIANGSU ELECTRIC POWER CO ELECTRIC POWER RES INST +3

Anti-fraud identification method and device based on big data and related equipment

The invention relates to the technical field of artificial intelligence, and discloses an anti-fraud identification method and device based on big data, computer equipment and a storage medium, and the method comprises the steps: obtaining the user information of each user in a user group, the user information comprises a user identifier and an attribute feature set corresponding to the user identifier, and inputting the user identifier, the attribute feature set and a preset abnormal attribute feature set into a trained isolated forest model for abnormal recognition to obtain a high-risk user identifier, importing each piece of user information into a graph database, generating a graph model, and querying the high-risk user identifier on the basis of the graph model and a preset data query request. The method comprises the steps of obtaining a community sub-network with each high-risk user identifier as a center node, calculating the high-risk probability of each node in the community sub-network, carrying out feature extraction on the community sub-network based on a neural network to obtain sample data of each node, inputting the sample data and the high-risk probability into a logistic regression model for training to obtain an anti-fraud identification group case model, and carrying out fraud identification on the group case model. And the identification accuracy of the fraudulent group is improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Four-dimension model intelligent contrast system and method for public security system

The invention relates to a four-dimension model intelligent contrast system and method for a public security system. The system comprises a semantic analysis module connected with a peripheral report-receiving information database through a data interface, a semantic classification lexicon and a case model database which are respectively connected with the semantic analysis module, a model contrast model and a case serial-to-parallel module which are respectively connected with the case model database, a result analysis module simultaneously connected with the model contrast module and the case serial-to-parallel module, a criminal characteristic database connected with the model contrast model, a lexicon update module connected with the semantic classification lexicon, and a criminal characteristic database updating module connected with the criminal characteristic database. The system is based on the thought of big data, and can perform four-dimension contrast by combining the case basic information, the field inquisition, and the case information data mastered in the early investigation process, the personnel with criminal record meeting the characteristic can be analyzed, the investigation vision is reduced, thereby providing support for case detection.
Owner:上海赛铭特科技有限公司

Model-free data center resource scheduling algorithm based on reinforcement learning

PendingCN110347478AAvoid the Difficulty of Environment ModelingScientific and rational distributionResource allocationEnsemble learningData centerReturn function
The invention discloses a model-free data center resource scheduling algorithm based on reinforcement learning. The algorithm comprises an environment model and a DRL model. The environmental model includes a time model, a VM model, a task model. The Task model is used for storing tasks which are not executed yet. The VM model is used for performing tasks. The DRL model comprises an Agent1 model and an Agent2 model. The Agent1 model is used for judging whether a task is executed or not, the Agent2 model is used for increasing or decreasing virtual machines, and the Agent1 model and the Agent2model respectively comprise a state space, an action space, a return function and a deep neural network. In the present invention, tasks arriving at a data center are large in size fluctuation, cost is provided to measure the waiting time of the task. Compared with the traditional fair scheduling, the shortest task first execution strategy and the first-in-first execution strategy, the task allocation is more scientific and reasonable, and meanwhile, for the resource waste caused by the change of the arrival number of the tasks, the number of the VMs in the cluster is dynamically adjusted, andthe efficient utilization and the load balance of the data center resources are realized.
Owner:白紫星
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products