445 results about "User driven" patented technology

A framework for machine learning modeling of structured data that includes one or more artificial intelligence-based agents. These artificial intelligence-based agents are configured to create and execute chains of repeatable actions to perform user-driven and user-defined workflows with a given problem set and identified outcomes. Structured data that has been processed is fed by the artificial intelligence-based agents to language models to formulate actions operate as tools for analyzing a problem set that can be chained together to address a given workflow, in one or more prompts for constructing and delivering the identified outcomes. Chains of repeatable actions for saved and utilized for additional workflows having similar problem sets, and executed based on pre-identified triggers.

The invention discloses an unmanned aerial vehicle cooperative inspection monitoring system based on BIM construction. The system comprises a data acquisition module which acquires an original visible light image, infrared thermal imaging and point cloud data of a construction area through unmanned aerial vehicle carrying equipment; the data processing module carries out denoising, enhancement, noise reduction, temperature calibration or downsampling processing on the three types of data; the BIM module performs spatial pairing on the processed three types of data, constructs a basic three-dimensional model of a construction area based on point cloud data, maps image and thermal imaging information, and adds a construction progress and a project amount plan to form a 4D BIM model; the construction inspection module obtains time and engineering quantity deviation from the 4D BIM model, generates a construction inspection report, and calculates a monitoring priority value of each building area according to the construction inspection report; and the user interaction module generates an inspection target according to the monitoring priority value, and a user drives the unmanned aerial vehicle to obtain new data according to the inspection target. The system realizes accurate monitoring of the construction progress and intelligent allocation of resources, improves the construction management efficiency and quality, and is suitable for building construction scenes.

A document processing platform transforms unorganized documents into interactive systems where users can ask questions and get answers. The document processing platform implements a User-Driven Contextualization Process, which allows users to add meaning to data. The process also improves user productivity by automatically tagging information and allowing for the prioritization of relevant details. The user may then ask questions for which narrative answers are provided including the relevant details extracted from the document. The process of transforming an unorganized document into an interactive system where users can ask questions and receive answers is broken down into three phases including document upload and data extraction, user-driven contextualization and definition, and configuring the new documents for questions using a large language model such as OpenAI.

The invention provides an energy recovery control method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the driving habit data and road condition data of a user, the driving habit of the user being the habit of the user controlling the vehicle speed and the rotating speed, and the road condition data being used for representing the road congestion condition; calculating a target energy recovery torque according to the driving habit data and the road condition data; and controlling the motor controller to output the target energy recovery torque. In the embodiment of the invention, the target energy recovery torque is calculated according to the driving habit and the road condition data of the user. It can be understood that the self-adaptive energy recovery mode in the embodiment of the invention is more in line with the driving habits of users, and even if different users drive vehicles, different target energy recovery torques can be calculated respectively, so that the requirements of different users for energy recovery intensity are met, and the user experience is improved.

The invention relates to a traffic engineering BIM (Building Information Modeling) and VR (Virtual Reality) technology combined interactive design and simulation system, which relates to the field of traffic engineering and comprises an interactive configuration module used for selecting simulation configuration to obtain user feedback information; the route mining module is used for performing networking frequent mining to obtain a mobile route case set; the virtual driving module is used for starting simulated driving and obtaining a three-dimensional dynamic time sequence diagram of a vehicle and heart rate monitoring time sequence information of a user; the safety scoring module is used for receiving a user driving safety score through the user side; the risk evaluation module is used for obtaining a driving risk evaluation value set; and the safety identification module is used for performing safety identification and then sending the information to the traffic engineering design end. Through combination of BIM and VR technologies, virtual simulation acquisition and analysis of user driving behaviors are realized, so that the driving risk of a design scheme is evaluated in a targeted manner, traffic engineering optimization design is guided, and the safety of traffic engineering design is improved.

The invention discloses a new energy vehicle endurance display method and system based on a power battery SOH, electronic equipment and a vehicle. The method comprises the steps that a vehicle, a vehicle control unit, a battery management system and a display module are triggered to be started through a KL15 signal wake-up signal, and power-on initialization and self-inspection are executed; after the self-inspection is completed, reading the stored current state-of-health initial value SOH0 of the power battery and the stored current state-of-charge initial value SOC0 of the power battery from the EEPROM; performing dynamic correction on the read SOC value, performing fixed value locking on the SOH value, and sending the corrected SOC value and the locked SOH value to a CAN bus of the whole vehicle; based on the SOH0 and the SOC1 sent by the battery management system, the remaining endurance mileage S is calculated in combination with the total delivery mileage L of the new vehicle; and the instrument and large-screen display module is used for displaying the current remaining endurance mileage in real time. According to the method, the problem of display deviation caused by neglecting battery aging in a traditional method is solved, and the user driving experience and the battery management efficiency are improved.

The utility model discloses a battery swap station which comprises a battery swap position and a transportation system, the transportation system is used for transporting and guiding an electric vehicle to the battery swap position, and the battery swap position is used for replacing a battery pack of the electric vehicle, so that the time required by a user to drive the vehicle to find the corresponding battery swap position is saved, the battery swap efficiency is improved, and the battery swap efficiency is improved. The situation that the user needs to drive the vehicle to consume a long time to find the battery replacement potential when the battery replacement potential is too much is effectively avoided, and the battery replacement experience of the user is improved. According to the technical scheme, the transportation system can preferentially select the electric switching potential closer to the electric vehicle and the optimal route for transportation guidance, compared with the situation that a user may bypass or miss the nearest electric switching potential during self-driving, the electric vehicle can enter the corresponding electric switching potential in the shortest time, the time used for electric switching can be further shortened, and the electric switching experience is improved. And the battery replacing station can coordinate the battery replacing position of each electric vehicle as a whole, so that the vehicles in the whole battery replacing station can be parked more regularly.

The invention discloses a personalized recommendation method and device based on a large language model and logical relationship mining. According to the method, user-driven logic relation extraction is constructed, the semantic reasoning ability and graph structure analysis of the large language model are fused, the high-order logic relation in the heterogeneous graph is mined, and the problems that an existing method is incomplete in logic relation and insufficient in semantic understanding are solved. The method comprises the following steps: analyzing user-article interaction data through a user-driven logic relationship extraction module, and identifying implicit association; performing rule expansion by utilizing a large language model, and generating a high-order logic rule in combination with semantic and structural information; screening high-quality rules through confidence score to construct an enhanced heterogeneous graph; and finally, demand perception recommendation is realized in combination with user preference embedding and logic relation characteristics.

The invention discloses an actuating mechanism and a surgical instrument, and relates to the field of medical instruments. The actuating mechanism comprises a transmission assembly, and the transmission assembly comprises an actuating piece, a dowel bar, a locking arm, an unlocking piece and a locking elastic piece. During specific operation, a user drives the dowel bar to move by adjusting the rotation stroke of the actuating piece, so that the dowel bar can pull an external dowel wire to execute expected operation, and the actuating piece is automatically locked by the locking arm; a user acts on the locking arm to move away from the actuating piece through the abutting action of the unlocking piece so as to unlock the actuating piece, the locking elastic piece is compressed, then the rotating stroke of the actuating piece is adjusted, and therefore the dowel bar is driven to move. According to the actuating mechanism provided by the invention, the transmission assembly is at least partially arranged on the far-end area in the assembly cavity, so that the occupation of excessive space of an interventional instrument can be avoided, the flexibility of operating the instrument can be improved, and a user can be promoted to adapt to surgical operation at an extreme angle.

The invention discloses a vehicle-mounted computing power sharing scheduling method based on user driving behavior analysis, and the method comprises the steps: 1), evaluating the vehicle computing power sharing priority based on the historical driving behavior data of a vehicle-end user and the current state of a vehicle; 2) the user side sends a computing power request to the cloud side; 3) based on the vehicle computing power sharing priority, the cloud side dispatches one or more vehicle side computing power with the highest priority, responds to the computing power request, and uploads a response result to the cloud side; and 4) the cloud side summarizes the response results and transmits the response results to the user side. According to the method, the driving style data is subjected to clustering analysis, the vehicle starting computing power sharing time is dynamically determined, the method does not depend on a charging pile, and the idle computing power of the vehicle is effectively utilized.

The invention discloses a driving style detection method and system based on a mobile phone sensor, and relates to the technical field of driving style detection, and the method comprises the steps: collecting various mobile phone sensor data when a user drives; the method comprises the following steps: respectively inputting various mobile phone sensor data into a full convolutional network FCN and a time sequence model TimesNet, capturing one-dimensional features of signals changing along with time in the input mobile phone sensor data through the FCN, expanding a one-dimensional time sequence in the mobile phone sensor data to a two-dimensional space through the TimesNet to obtain two-dimensional features, and merging the one-dimensional features and the two-dimensional features to obtain two-dimensional features; and performing category division to obtain scores of each mobile phone sensor on different classification categories, and obtaining a driving style through the scores. According to the method, the one-dimensional features extracted by the FCN and the two-dimensional features extracted by the TimesNet are combined to be used in the DSD task, so that the obtaining effect of the two-dimensional features is improved, and the accuracy of driving style detection is improved.

The invention belongs to the technical field of traffic, and particularly relates to a competition-considered electric vehicle charging reachability analysis method, system and device. The method comprises the following steps: rasterizing and coding a map of a target area, marking grids containing charging stations, and generating a starting point set and an ending point set; defining a path that a user drives a vehicle from a starting point to any charging station and then drives out in a non-driving mode as a charging trip chain; and generating all candidate charging trip chains from the specified starting point to the specified terminal point through the optional charging station, finally, calculating the charging accessibility between any two points in the target area by combining the weighted average generalized charging process cost of the vehicle between any two points and the competitive attraction of the charging station to the vehicle, and generating a corresponding thermodynamic diagram. According to the invention, the problems that the space distribution of the actual travel demand of the user is not considered in the space layout of the existing charging station, the charging reachability distribution among different places in the area is unbalanced, and the charging experience of the user is poor are solved.

The invention discloses a camera parameter calibration method and device, a computer readable storage medium and a vehicle, and the method comprises the steps: collecting a checkerboard image shot by at least one camera, and extracting a line contour in the checkerboard image based on an edge detection algorithm; in the line contour, detecting a straight line segment based on Hough transformation or an LSD algorithm, and fitting the straight line segment based on a least square method; determining an internal reference matrix and a distortion coefficient of the camera based on the fitted straight line segment and a nonlinear optimization algorithm; and determining a rotation matrix and a translation vector of the camera based on the straight line segment, the internal reference matrix and the distortion coefficient. According to the method, the robustness of parameter calibration in a calibration field aging, fouling or reflective scene can be improved, the success rate, the automation degree and the efficiency of the calibration process are improved, and the driving safety of a user is improved.

Systems and methods are presented for providing personalized content based on gestures, in order to provide a seamless and user-driven feedback capture platform that captures user gestures and provides improved personalized content. The system captures biometric data from the user during the presentation of a first content item from a first content source. The system identifies the feedback indicator from the biometric data captured during the output of the first content item and stores an identifier of the second content item associated with the first content item in the master list. The system generates the master list for display and, in response to receiving a selection of the identifier of the second content item, retrieves for output the second content item from the second content source on the user device.

The invention provides a controller strategy optimization method for user behavior analysis, and relates to the technical field of controllers, and the method comprises the steps: collecting user driving parameters; speed risk level and speed change feature recognition segmentation is carried out according to the driving speed, and a speed adaptive interval is determined; according to the braking and steering force and frequency, steering and braking risk evaluation is conducted on the speed self-adaption interval; performing controller strategy matching analysis according to the stability risk coefficient, determining an optimization adjustment coefficient, and adding the optimization adjustment coefficient to a speed adaptive interval; matching is carried out according to the monitored current driving speed and the speed self-adaptive interval, an optimization adjustment coefficient is obtained, and controller strategy adjustment is carried out. The technical problem that in the prior art, due to the fact that the electric tricycle is prone to insufficient stability and rollover during high-speed turning, driving is unstable can be solved, the control strategy is dynamically adjusted according to the actual driving behavior of a user and the state of the tricycle, and the driving safety and stability are improved.

A system that generates relevant and vetted training data using intelligent simulated users and evaluation of conversation data. A simulated user and an automated agent engage in a conversation to generate conversation and / or interaction data. The simulated user is guided by scenarios which are generated based on one or more controls to be followed by the automated agent. Using a simulated user driven by control-derived scenarios ensures the ensuing conversation data is relevant to the desired scope of operation for the automated agent. The conversation data is evaluated based on the controls to confirm the automated agent actions and responses followed the controls properly. Evaluating the conversation data based on the controls ensures that conversation data associated with properly followed controls is used as subsequent training data.

The invention provides an electric vehicle electric quantity state and remaining mileage prediction method, which comprises the following steps: carrying out regional division on a battery pack, deploying a sensor, collecting electric quantity data of each region in real time, constructing an anomaly detection model to identify an abnormal region, carrying out local data adjustment, and combining user driving behaviors and environmental parameters to predict the electric quantity state and remaining mileage of an electric vehicle. A long-short-term memory network is adopted to dynamically predict the power consumption trend, the remaining mileage is calculated according to real-time road conditions and temperature changes, meanwhile, an adaptive correction mechanism is introduced, and model parameters are dynamically adjusted through comparative analysis with historical prediction records, so that the prediction accuracy is improved. According to the method, accurate monitoring of the electric quantity state of the electric vehicle and dynamic prediction of the remaining mileage can be achieved, the problem that a traditional method is large in prediction deviation in a complex driving environment is effectively solved, more reliable electric quantity and mileage information is provided for a user, and the use experience and safety of the electric vehicle are improved.

The utility model relates to the technical field of fitness equipment, in particular to a motion detection device applied to the fitness equipment, which can acquire the acting condition and the weight of a counter weight in the motion process. Comprising a weight bearing module, a distance detection module and a control electronic watch, the weight bearing module comprises a movable rod, a balancing weight and a plug pin, a user selectively inserts the plug pin into the balancing weight according to exercise requirements, and the user drives the movable rod and the balancing weight to vertically move upwards for exercise; specifically, the distance detection module selects a gyroscope or a pull box to detect the movement distance and the movement speed of the movable rod, and the movement distance and the movement speed are displayed by controlling an electronic watch; the control electronic meter is electrically connected with the bolt and displays the total weight of the corresponding balancing weight according to the magnitude of the passing current; and the user can intuitively obtain own motion parameters.

The invention relates to an electric vehicle V2G scheduling method considering consumption of photovoltaic power and off-peak power, and the method comprises the steps: building an EV disordered charging model based on a user driving behavior in a power distribution network system containing photovoltaic power generation; establishing peak clipping-oriented price excitation; combining the established EV disordered charging model and price excitation to construct a photovoltaic and EV cooperative power generation optimization scheduling model; solving the photovoltaic and EV cooperative power generation optimal scheduling model by adopting an improved multi-target particle swarm algorithm, and outputting to obtain an EV ordered charging and discharging strategy; and correspondingly controlling the charging and discharging behaviors of the EV according to the EV ordered charging and discharging strategy. Compared with the prior art, the method can reduce the load variance of the power grid, achieves the efficient utilization of photovoltaic and off-peak power, and improves the V2G income of the electric vehicle.

The invention relates to the field of intelligent automobile data processing, and discloses an automobile user behavior prediction method based on a data model, and the method comprises the following steps: 1, collecting user multi-modal data which comprises a user driving track, a purchase record, a vehicle-mounted video and a voice instruction; 2, carrying out standardization processing on the multi-modal data, and constructing a data matrix; 3, calculating a covariance matrix of the data matrix, and improving the stability of the covariance matrix through an optimization algorithm; step 4, eliminating noise features in the covariance matrix based on a random matrix theory, and extracting features with relatively high signal intensity; and 5, optimizing the cooperative relationship between the signal features by adopting a feature interaction modeling method. According to the method, the technical scheme of combining multi-modal data acquisition and standardized processing is adopted, and the fusion of high-dimensional and diversified data under the same analysis framework is realized by unifying the scale and distribution of different modal data.

A method for constructing a 3D panoramic view model is provided using a vehicle-mounted device. The method includes identifying a target object in an environment image, and determines first coordinates of the target object in a first coordinate system corresponding to the environment image. The environment image is converted to an aerial view, and second coordinates of the target object are determined in a second coordinate system corresponding to the aerial view. A third coordinate of the target object is determined in a third coordinate system. A fourth coordinate of the target object is determined in a fourth coordinate system, and an initial distance is determined between the target object and a vehicle. A target distance is determined and a target 3D panoramic view model of the vehicle is constructed according to the target distance and the environment image. The method improves the safety of users driving.

The invention relates to a traffic freight employment qualification certificate handling service system and method based on artificial intelligence. The method comprises the following steps: in response to a traffic freight employment qualification certificate service instruction triggered by a user, determining a certificate service type needing to be handled based on the service instruction; collecting identity verification information of the user, and performing identity verification on the user based on the identity verification information; if the identity verification is passed, generating and pushing a service information input interface to the user according to the type of the certificate service needing to be handled; acquiring user driving qualification information uploaded in the service information input interface, and performing service preprocessing on the user driving qualification information by adopting a driving qualification review model; pushing a certificate service confirmation interface to the user, so that the user confirms the to-be-examined information in the certificate service confirmation interface; and in response to a confirmation instruction of the target user for the certificate business confirmation interface, pushing the to-be-examined information in the certificate business confirmation interface to an examination end to complete a business handling process.

The invention provides a vehicle-mounted eye protection lamp and display screen linkage control method, device and equipment and a medium, and relates to the technical field of linkage control, and the method comprises the steps: obtaining user driving behavior data, the external environment illumination intensity of a vehicle-mounted display screen and the current display content type; determining a driving state and a fatigue level based on the user driving behavior data, and determining a day and night mode based on the external environment illumination intensity; based on the driving state, the fatigue level, the day and night mode and the current display content type, generating a display screen control parameter and an eye protection lamp illumination parameter; adjusting backlight of the display screen based on the display screen control parameters; and controlling a projection area of the eye-protection lamp based on the eye-protection lamp illumination parameters. In the mode, the external vehicle-mounted eye protection lamp and the display screen are jointly controlled, the driving state and the fatigue level of the user and the day and night mode of the external environment are considered, light display is completed in public, and a comfortable eye use environment is provided for the user.

The present invention relates to a continuously variable transmission for a bicycle. The continuously variable transmission for a bicycle can automatically shift gears continuously in response to changes in driving force and load according to the bicycle-riding environment without user intervention, recharges, by means of a generator, with power generated during riding and shifting, prevents reverse rotation of the central shaft, and also allows transmission to be manually controlled by means of a load-providing unit when necessary. To that end, the continuously variable transmission for a bicycle comprises: a transmission unit which receives rotational power from the central shaft, which is driven and rotated by a user, and automatically shifts gears in response to resistance when rotating, the rotational power being delivered in the order of a first carrier, a first planetary gear, a first ring gear, a first sun gear, and an output shaft; and a load-providing unit which is installed to engage with the transmission unit and selectively provides a load to the transmission unit. Therefore, the continuously variable transmission for a bicycle facilitates gear changes based on the bicycle-riding environment.

The present invention relates to an aerosol-generating device comprising: a housing having a proximal end and a distal end opposite in a longitudinal direction; the heating element is used for heating the aerosol-generating substrate to generate aerosol; the electric core is used for providing electric power for the heating element; the bottom cover at least partially seals the far end of the shell and is detachably connected with the shell; the bottom cover is configured to be detachable from the shell so as to open the far end of the shell, so that the battery cell is allowed to be taken out from the far end of the shell; the bottom cover can be switched between a locking state and an unlocking state, is prevented from being detached from the shell in the locking state and is allowed to be detached from the shell in the unlocking state; the bottom cover can be driven by a user to move in the transverse direction relative to the shell, and then the locking state is converted into the unlocking state. In the unlocking state, at least part of the bottom cover protrudes out of the shell in the transverse direction, and then a user can operate the part, protruding out of the shell, of the bottom cover to detach the bottom cover from the shell.

The invention discloses a driving parameter acquisition method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a first user driving parameter of a target vehicle in a driving mode; responding to the condition that the target vehicle enters the simulated driving mode, and acquiring a second user driving parameter of the target vehicle in the simulated driving mode; adjusting the first user driving parameter by using the second user driving parameter to obtain a target user driving parameter; wherein the target user driving parameters are driving parameters used for representing user driving preferences. In this way, the target user driving parameters which accurately and truly reflect the user driving preference can be obtained.

The invention discloses an electric vehicle highway energy supplement demand prediction system and method combining a physical model and a neural network. The system comprises a vehicle terminal, a cloud server, a third-party API interface platform, a user behavior monitoring module, a user driving mode setting module and a user behavior monitoring module. The cloud server comprises a model training module, a data storage module, a physical model and neural network combined prediction model and an energy supplement demand judgment module; the physical model and neural network combined prediction model firstly calculates basic energy consumption through the physical model, and then performs error correction on nonlinear factors by using the neural network to obtain final predicted energy consumption; the nonlinear factors comprise environment temperature, wind speed and user driving habits; and the energy supplement demand judgment module is used for comparing the current battery remaining capacity with the final predicted energy consumption, and judging the energy supplement demand of the expressway in combination with a safe endurance threshold. According to the method, the physical model and the neural network are combined, and energy consumption can be accurately predicted.

A modular flow monitoring package (MFMP) is provided for use in an additive delivery system. The MFMP may be manufactured as an add-on to be added to an existing additive delivery system, or may be incorporated into a cartridge or container structure. The MFMP includes a flow sensor for sensing flow of a base fluid and user actuator position sensors for sensing the position of one or more user actuated additive flow adjustment levers. A visual display, which may comprise an array of multi-color LED's may convey information to a user that is relevant to a user's use of the additive delivery system or the user's nutritional needs. Such information may include a current dosage of additive, being delivered, whether a recommended dosage of additive has been consumed, remaining life of a cartridge or supply of additive, and other data relative to health or performance monitoring.

The invention relates to the technical field of lithium battery safety, in particular to an electric tricycle lithium battery charging and discharging management method and system, and the method comprises the steps: obtaining lithium battery state data, environment data, tricycle load data and historical driving data; clustering analysis is carried out on the user driving data, and electro-tricycle scene types are divided; performing health degree evaluation on the battery state, automatically matching a charging mode according to the health degree, generating a charging current limiting value through a multi-objective optimization algorithm, performing dynamic matching on charging parameters, and executing charging operation according to the matched parameters; the scene type is recognized, a discharge current limiting value is generated through a multi-target optimization algorithm, discharge parameter dynamic matching is carried out, discharge operation is executed according to matched parameters, and energy recovery is started during downhill braking; and establishing a battery abnormal state identification model, and triggering graded early warning when an abnormal state is identified. Therefore, the problems of fixed charging and discharging modes, single abnormity monitoring, insufficient scene adaptation and the like in the prior art are solved.

The invention discloses a thermal management method and system of a vehicle, the vehicle and a storage medium. The method comprises the steps that multi-source data collected by a vehicle are obtained, and the multi-source data at least comprise vehicle state data, environment data and driving behavior data; performing clustering analysis on the multi-source data, and determining a user driving behavior portrait; based on the user driving behavior portrait and a multi-objective optimization decision algorithm, generating a thermal management control parameter of the vehicle; and performing thermal management on the vehicle based on the thermal management control parameters. According to the invention, the technical problem of low reliability of the thermal management method of the vehicle in the related art is solved.