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

38results about How to "Guaranteed personalization" patented technology

Dual-path road network individuation inductivity distribution method under user equalization principle

The present invention relates to a dual-path road network individuation inductivity distribution method under a user equalization principle. The method comprises the following steps: 1) aiming at a regulated dual-path road network, performing statistics of road network basic parameters; 2) based on the GreenShields model and the traffic flow theory, solving an optimal separation rate under an ideal condition according to the road network basic parameters to optimize the whole traffic flow of the road network; 3) under the constraint condition of the whole optimal road network, establishing the basic constrained condition of an individuation induction distribution strategy according to the proportion of an individual vehicle historical driving optimal paths; 4) establishing the concept of the vehicle priority, and calculating the individuation induction rate distribution value under the known condition of the vehicle priority through adoption of the equal difference distribution principle according to the concept; and 5) according to the distribution principle determined in the step 4) and the probability distribution of the vehicle historical optimal ratio, distributing the induction information. The dual-path road network individuation inductivity distribution method under the user equalization principle satisfies the user equalization principle to the utmost extent under the probability meaning to ensure the fairness of vehicle induction acceptance.
Owner:TSINGHUA UNIV

Intelligent cloud processing system and method for selecting wardrobe to generate three views

The invention provides an intelligent cloud processing system and method for selecting a wardrobe to generate three views. The system mainly comprises the following modules of a wardrobe selection module, a projection marking and layout module, a front-end drawing frame and drawing splicing adjustment module and a drawing file export module. According to the system and the method, the drawing process and the label drawing logic of the wardrobe drawings in the market are summarized and concluded, the rules capable of covering most wardrobe drawing requirements of users are extracted, the drawing requirements of most users are met, and the production and landing of the wardrobe can be more truly guided. Compared with other decoration design software, a self-defined configuration adjustment function is additionally provided, and the universal drawing logic and the personalized adjustment are combined, so that the starting difficulty for drawing the whole wardrobe is reduced, a certain personalized drawing capability is guaranteed, and meanwhile, the correctness, universality, personalization and attractiveness of the drawings are guaranteed, and the time expenditure for drawing the wardrobe of the user is greatly reduced.
Owner:HANGZHOU QUNHE INFORMATION TECHNOLOGIES CO LTD

Driving event recognition and training method and device, equipment and storage medium

The embodiment of the invention provides a driving event recognition method and device, a training method and device, equipment and a storage medium. The method comprises the following steps: collecting data representing a driving event as a driving parameter, and dividing the driving parameters in the first time period into a first target parameter and a second target parameter; in an event recognition model matched with the type of a vehicle, searching an event recognition model suitable for processing the second target parameter as an original event recognition model, training an original event recognition model by taking the first target parameter as a sample for identifying urgency and the second target parameter as a sample for identifying non-urgency; obtaining a target event recognition model, wherein the target event recognition model is called to recognize the emergency driving event from the driving parameters in the second time period, training is continued on the basis ofthe previous event recognition model, the training amount is small, the real-time requirement is met, the event recognition model conforming to the driving style of the user is learned, and the personalized driving event is recognized.
Owner:广州景骐科技有限公司

Advertisement expired release dynamic control method and system

Embodiments of the invention provide an advertisement expired release dynamic control method and system. The method comprises the steps of obtaining a release speed of a target advertisement in a current time period and a release speed limit coefficient in the current time period; according to the release speed of the target advertisement in the current time period and the release speed limit coefficient in the current time period, obtaining the remaining release time of the target advertisement; determining a release speed limit coefficient of the target advertisement in the next time periodaccording to the remaining release time of the target advertisement; and outputting the release speed limit coefficient of the target advertisement in the next time period. According to the method andthe system, the optimization is performed for the problem of expired release; by utilizing a characteristic that the release speeds of different advertisements are different, dynamic speed control iscarried out, so that the personalization of speed control strategies is realized. While the personalized speed control is ensured, the effective time of the speed control strategies of all the advertisements is measured by the remaining release time in a unified mode, so that the implementation difficulty of the system is lowered.
Owner:MICRO DREAM TECHTRONIC NETWORK TECH CHINACO

Grayscale user management method, device and platform, and storage medium

The embodiment of the invention discloses a grayscale user management method, device and platform and a storage medium. The method is applied to a grayscale user management platform and comprises thefollowing steps: receiving a scene label of a service in connection with the grayscale user management platform and at least one user identifier; according to a preset grayscale policy rule sequence corresponding to the scene label, sorting the at least one grayscale policy rule; and determining a grayscale user corresponding to the scene label from the at least one user identifier according to the sorted grayscale policy rules. The embodiment of the invention implements flexible adjustment of the grayscale policy and ensures the individuation of the service scene; the product is preferentially experienced for a specific user group, different product characteristics are displayed for different users, and a grayscale policy of thousand people and thousand faces is achieved.
Owner:SHENZHEN LEXIN SOFTWARE TECH CO LTD

Treatment scheme recommendation method and device, equipment and storage medium

PendingCN113539409APersonalization and reliability guaranteedGuaranteed personalizationMedical data miningTherapiesEngineeringMedical practitioner
The invention discloses a treatment scheme recommendation method, and the method comprises the steps: obtaining a current case symptom and a medical case database, and extracting a candidate treatment scheme corresponding to the current case symptom from the medical case database based on a self-attention mechanism; preprocessing the candidate treatment scheme to obtain a first vector set; constructing a medical knowledge graph, extracting a medical node set from the medical knowledge graph, performing characterization learning on the medical node set by adopting a heterogeneous graph neural network, screening characterization results according to the current case symptom, and obtaining a second vector set corresponding to the current case symptom; calculating the similarity between the first vector set and the second vector set; determining a target vector from the first vector set according to a similarity calculation result, and taking a candidate treatment scheme corresponding to the target vector as a recommended treatment scheme. By means of the mode, the medical knowledge graph and the candidate treatment schemes of doctors can be fully combined, and the reliability of the recommended treatment schemes is guaranteed.
Owner:PING AN TECH (SHENZHEN) CO LTD

Architecture of trusted platform module and method for providing service thereof

ActiveCN101183413BGuaranteed not to be interceptedGuaranteed interceptionComputer security arrangementsRedundant operation error correctionBus interfaceKey generator
The invention provides a trusted platform module TPM system structure and a method of providing service. The structure comprises an I / O bus interface module, a password coprocessor module, an HMAC engine module, an SHA-1 engine module, an Opt-In module, a nonvolatile memory module, a volatile memory module, an execution engine module, a power-detecting module, a random number generator, a key generator module and an I / O interface module for special information; wherein, interaction operation is performed internally for the I / O interface module for special information and the execution engine module; preset, backup and recovery of internal information for trusted platform module are performed through the connection with each parallel or serial trusted equipment and the function of pin PP isreplaced. The trusted platform module provides the following services: reading identification information of connected equipment for I / O interface module for special information; testing status of I / O interface module for special information; presetting initial information, moving information, backing up or recovering TPM sensitive data. The invention can be used for enabling safe operation of internal sensitive information of TPM module.
Owner:XIDIAN UNIV +1

Federal learning-oriented dynamic personalized network construction method and device

The invention discloses a federated learning-oriented dynamic personalized network construction method and device, and the method comprises the following steps: creating a neural network model, initializing the neural network model, and transmitting the neural network model to a client; performing dynamic calculation on a sample of the client according to an early-leaving strategy, and finishing updating of an early-leaving layer; selecting an early leaving strategy execution layer, and selectively sending parameters in the selected early leaving layer; after the server receives the nodes and the parameters uploaded by the client, aggregation of the weights of the nodes of the early leaving layer is completed according to an aggregation strategy; and receiving the aggregated parameters from the server, completing the updating operation of the model parameters in the client, and completing the construction of the personalized network by means of the updating of the early leaving layer. According to the dynamic personalized network construction method disclosed by the invention, the reasoning efficiency of the model and the attention of the difficult sample are improved, and the cost of federal learning in sample calculation and model reasoning is reduced while the personalization of the client model is ensured.
Owner:SOUTH CHINA UNIV OF TECH

Service processing method and device based on acceleration and deceleration, equipment and storage medium

The embodiment of the invention provides a service processing method and device based on acceleration and deceleration, equipment and a storage medium. The method comprises the steps of 1, detecting that a vehicle executes an acceleration and deceleration operation in a specified service scene; acquiring the acceleration in response to the acceleration and deceleration operation; updating an eventrecognition model matched with the acceleration by taking part of the acceleration as a training sample under the constraint of the service scene; obtaining a target event recognition model; inputting part of the acceleration into a target event recognition model for classification so as to identify an operation representing emergency acceleration and deceleration; performing service processing on the vehicle according to the emergency acceleration and deceleration operation in the service scene; and recognizing the condition of the emergency acceleration and deceleration operation by takingthe service scene as a training event recognition model, so that the calculation amount is reduced, the accuracy of the event recognition model is guaranteed, the event recognition model conforming tothe driving style of the user is learned step by step, the personalized emergency acceleration and deceleration operation of the user is recognized, the operation is easy and convenient, and a basisis provided for decision making of service processing.
Owner:GUANGZHOU WERIDE TECH LTD CO

A self-adaptive multi-terminal visualization method for geospatial information

Disclosed is a geographic space information self adaption multiple terminal visualization method. The geographic space information self adaption multiple terminal visualization method is characterized by being based on a three layer architecture system structure, wherein a top layer of the three layer architecture system structure is a spatial data visualization interface layer directly interacted with a user, and used to display spatial data in graphic mode according to a self adaption graphic design scheme, and simultaneously generates various interfaces adaptive to the user according to situations of the user, and presents the various interfaces to the user, a function layer of the three layer architecture system structure is used to achieve the whole self adaption spatial data visualization process, and comprises various core control modules for adaptively visualizing the spatial data, which are respectively a self adaption graphic format model, a self adaption graphic representation model and a self adaption map symbol design model, and a data layer of the three layer architecture system structure is a spatial data library, and comprises user management and geographical space time data analyzing and processing models. Compared with an existing terminal visualization method, the geographic space information self adaption multiple terminal visualization method further considers initiative, spatial attributes and a method adaptive to multiple terminals on the premise of keeping personalized, and really meets exact demands of the multiple terminals based on geographic space information service.
Owner:武汉图歌信息技术有限责任公司

Personalized induction rate allocation method for dual-path road network under the principle of user balance

The present invention relates to a dual-path road network individuation inductivity distribution method under a user equalization principle. The method comprises the following steps: 1) aiming at a regulated dual-path road network, performing statistics of road network basic parameters; 2) based on the GreenShields model and the traffic flow theory, solving an optimal separation rate under an ideal condition according to the road network basic parameters to optimize the whole traffic flow of the road network; 3) under the constraint condition of the whole optimal road network, establishing the basic constrained condition of an individuation induction distribution strategy according to the proportion of an individual vehicle historical driving optimal paths; 4) establishing the concept of the vehicle priority, and calculating the individuation induction rate distribution value under the known condition of the vehicle priority through adoption of the equal difference distribution principle according to the concept; and 5) according to the distribution principle determined in the step 4) and the probability distribution of the vehicle historical optimal ratio, distributing the induction information. The dual-path road network individuation inductivity distribution method under the user equalization principle satisfies the user equalization principle to the utmost extent under the probability meaning to ensure the fairness of vehicle induction acceptance.
Owner:TSINGHUA UNIV

Transverse control method and device based on steering, equipment and storage medium

The embodiment of the invention provides a transverse control method and device based on steering, equipment and a storage medium. The method comprises the following steps: when it is detected that the vehicle steers on the curve, calculating the type and deviation value of the curve, using the lane line of the curve as a reference, dividing the partial deviation value into a first target deviation value representing emergency steering and a second target deviation value representing non-emergency steering; taking the first target deviation value and the second target deviation value as classified samples; updating an event identification module matched with the type of the curve; obtaining a target event recognition model, inputting part of the deviation values into a target event recognition model for classification; identifying an operation indicative of emergency steering; conducting transverse control on steering of the vehicle on the curve according to emergency steering operation, collecting the deviation value of the vehicle driven by the user in real time, continuing to train on the basis of the previous event recognition model, the training amount is small, the real-timerequirement is met, and the event recognition model conforming to the driving style of the user is obtained through training step by step.
Owner:广州景骐科技有限公司
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