50 results about "Target reaching" patented technology

The invention relates to a field picking obstacle avoidance method and system based on active perception. The picking obstacle avoidance method comprises the steps that hardware and a mechanical arm control system are initialized; rGB image data and depth image data of crops are acquired and preprocessed; inputting the preprocessed RGB image data and depth image data of the crops into an improved YOLOv5 network with an attention mechanism; analyzing the pixels of the region of interest based on the color threshold of the crop target, and providing an obstacle avoidance basis; moving a mechanical arm based on the crop target information; if the shielding rate of the crop target reaches a threshold value or the crop target has no obstacle, and the depth information of the crop target meets the picking condition, the mechanical arm executes a picking task. According to the method provided by the invention, the color, the depth information and the spatial position of the crop are sensed in real time, and the target recognition and segmentation of deep learning are combined, so that the shielding, obstacle and target characteristics can be accurately sensed.

The invention discloses a movement detection and feedback intervention system for obese patients, and relates to the technical field of movement intervention for obese patients, the system comprises a data acquisition module, a personalized movement scheme generation module, a movement monitoring module and an interaction module; according to the method, artificial intelligence and big data analysis technologies are deeply fused, multivariate data of a patient is comprehensively and accurately collected, a personalized exercise scheme meeting individual requirements can be generated, the pertinence of the exercise scheme is improved, and during exercise monitoring, the multi-modal data fusion technology is applied, so that the accuracy of exercise monitoring is improved. Various physiological parameters and exercise environment data of a patient are collected in an omnibearing mode, the state of the patient is accurately controlled in real time, once monitoring data deviates from a preset target, parameters such as exercise items, strength, time and frequency in an exercise scheme can be rapidly and dynamically adjusted according to a real-time deviation correction algorithm, the safety of the exercise process is practically guaranteed, and the exercise efficiency is improved. The goal of losing weight is effectively promoted.

The invention provides a real-time simulation method, device and equipment based on multi-domain situation awareness and a storage medium, and the method comprises the steps: firstly obtaining data sources of a plurality of combat domains, and carrying out the preprocessing of the data source of each combat domain; wherein the data source comprises land domain data, sea area data, airspace data, sky domain data and network domain data; fusing the preprocessed data sources of the combat domains to generate unified multi-domain data, and constructing a simulation model based on the unified multi-domain data; experimental factors are obtained, the experimental factors are used for constructing multiple experimental schemes through an orthogonal test, the multiple experimental schemes are input into the simulation model to generate key indexes, and the key indexes comprise combat target achievement conditions, military strength consumption, combat time and resource consumption; and dynamically optimizing the key indexes, and outputting a combat decision scheme which can be used for reference of a command and control system. The problem that the decision of a command and control system is affected due to insufficient simulation precision is solved.

A sensor system according to an embodiment includes: a noncontact sensor module arranged on a display module; and a processor configured to drive the sensor module, wherein the sensor module is configured to detect a first coordinate and a second coordinate of a detection target, the second coordinate is detected before the first coordinate is detected, the processor is configured to calculate move information indicating a moving direction of the detection target in the first coordinate based on the first coordinate and the second coordinate detected by the sensor module, and calculate a correction amount in the first coordinate based on the move information when the detection target approaches the sensor module and a distance between the sensor module and the detection target reaches a correction start distance.

The invention provides a personalized exercise plan generation and management method and system based on user data, and the method comprises the steps: obtaining multi-source user data, and carrying out the data cleaning and feature extraction; on the basis of the extracted feature data, confirming the exercise preference and the exercise target of the user; based on the exercise preference and the exercise target, a machine learning algorithm is adopted to generate a personalized exercise plan, and recommendation is carried out; and tracking user feedback for the personalized exercise plan, performing dynamic analysis on information fed back by the user, correcting exercise preferences and exercise targets, and regenerating the personalized exercise plan. Multi-source data features are extracted and analyzed to obtain a personalized exercise target of a user, a machine learning algorithm is utilized to generate a personalized exercise plan for the personalized exercise target, and finally, based on customer feedback, the goal reaching progress and the sign change of the user are analyzed, the exercise effect is evaluated, and the user experience is improved. And adjusting the motion target and the motion plan in real time, and managing the motion plan.

The invention discloses a self-adaptive software test case generation optimization method, which comprises the following steps of: carrying out structured analysis on service requirements of a target system, extracting multi-dimensional test requirements of performance, resources, risks and coverage rates, and carrying out tagging and normalization processing to form a quantifiable index system; based on a meta-strategy layer decision engine, fusion reinforcement learning and fuzzy reasoning are carried out to realize multi-target weight distribution and dynamic compromise; generating and optimizing a preferred case set by means of a trade-off adaptive algorithm, performing conflict marking and constraint cooperative adjustment, collecting feedback data through automatic testing, correcting weight distribution and conflict detection rules according to actual results, and continuously iterating case generation strategies; the objective achievement degree is periodically evaluated, the strategy model is reconstructed or switched to adapt to scene changes, the accuracy of test requirement expression and the self-adaptability of the use case generation strategy are improved, and efficient collaborative optimization of multi-objective testing and dynamic adaptation of service scenes are achieved.

The embodiment of the invention discloses a measurement report triggering method, a terminal and network side equipment, and belongs to the technical field of communication, and the method comprises the steps that the terminal reports a measurement result of a measurement target under the condition that a first condition is met; the measurement target comprises at least one of a measurement object, a reference signal and a target cell; the first condition comprises at least one of the following: receiving a first indication; generating a first event; the target cell satisfies the first characteristic; the measurement result of the target cell is not reported; the duration in which the measurement result is not reported reaches a first threshold; the measurement result of the target cell is not reported before the first moment; the measurement result is greater than or equal to a second threshold; the measurement number or the measurement time of the measurement targets is greater than or equal to a third threshold; measuring a target for a demand-based SSB; uplink resources can report a measurement result; the timer is invalid or not invalid; the configuration time or activation time of the measurement target reaches a threshold.

The invention provides an intelligent recruitment process control method and system based on a task state and an action type, and the method comprises the following steps: obtaining multi-dimensional input data of a recruitment process, converting the multi-dimensional input data into a standardized task state feature vector, the task state feature vector at least comprises a process progress quantized value, candidate interaction feedback parameters, a resource occupancy rate and a target achievement degree; constructing a collaborative decision-making system of a preset decision-making rule and a reinforcement learning model; according to the method, the multi-dimensional task state features are collected in real time, the execution strategy is dynamically adjusted in combination with the adaptation logic of the candidate action types, various changes in the recruitment scene can be flexibly responded, and accurate matching of the process and the real-time service scene is achieved.

1. The name of the design product: the graphical user interface of the electronic device for recording continuous learning. 2. The use of the design product: an electronic device. 3. The design points of the design product: the graphical user interface. 4. The picture or photo that best shows the design points: design 1 front view. 5. The product carrier is the conventional design, and the rear view, left view, right view, top view, and bottom view of each design are omitted. 6. Design 1 is designated as the basic design. 7. The use of the graphical user interface: for recording continuous learning. 8. The human-computer interaction mode of the graphical user interface: in design 1 front view, click on any position to enter design 1 change state diagram 1 continuous learning main interface (no learning record interface yet), start continuous learning to enter design 1 change state diagram 2 learning record interface, the module in the lower left corner of the interface is "task standard module", when any standard in the module is reached, enter design 1 change state diagram 3, and the task has a "standard reached" status identifier. In design 2 front view, click on any position to enter design 2 change state diagram 1 continuous learning main interface (no learning record interface yet), start continuous learning to enter design 2 change state diagram 2 learning record interface, when the user reaches the target, enter design 2 change state diagram 3 target reached interface. In design 3 front view, click on any position to enter design 3 change state diagram 1 continuous learning main interface (no learning record interface yet), start continuous learning to enter design 3 change state diagram 2 learning record interface, during continuous learning, if the task is not completed all day, enter design 3 change state diagram 3 interface of still not learning all day.

The invention belongs to the technical field of talent management development, and relates to a staged progressive talent growth path planning method and system, and the system collects and integrates the static and dynamic data of talents through a talent portrait construction module to generate an initial talent portrait; the growth stage division module divides progressive growth stages and sets capability thresholds based on the initial talent portraits and the organization development objectives; the stage target setting module is used for disassembling a stage target into quantifiable sub-target schemes with time limit; the resource matching and pushing module is used for matching resources according to the target and the portrait and automatically pushing the resources to the talent end; the capability evaluation feedback module is used for evaluating a stage target achievement condition and generating an evaluation report; the path dynamic adjustment module progressively or triggers path adjustment based on the evaluation report judgment stage; and the data storage and analysis module is used for storing the whole-process data, carrying out multi-dimensional analysis and optimizing parameters. According to the invention, personalized planning, dynamic adjustment and whole-process closed-loop management of talent growth paths can be realized.

The invention belongs to the technical field of robot task planning and execution, and particularly relates to a two-arm robot long-time sequence planning method based on tree-shaped hierarchical decomposition. The method specifically comprises the following steps of: initializing an input task instruction into a root node of a sub-target tree, decomposing the root node by utilizing a sub-target decomposition model, and constructing a first layer of sub-targets; further decomposing the current sub-target based on the current sub-target, the father node information and the current environment to generate a new sub-target; taking the sub-target with the finest granularity as a leaf node, evaluating each leaf node, judging whether the leaf node meets a termination condition or not, and performing further decomposition if the leaf node does not meet the termination condition; according to the primitive action sequence generated by the leaf nodes, the robot executes specific actions, environment feedback is obtained in the execution process, and dynamic adjustment planning of the sub-target trees is carried out; and when the primitive actions corresponding to all leaf nodes are executed and the task target is reached, completing the task.

The application discloses a kind of based on unmanned aerial vehicle's laser cleaning and cladding collaborative control method, device, electronic equipment, readable storage medium and computer program product.The method comprises: determining operation target;When the surface rust depth of operation target exceeds preset depth threshold, the current operation mode of unmanned aerial vehicle is adjusted to cleaning mode;Laser cleaning operation is carried out to operation target in cleaning mode;When detecting that the target metal ion characteristic peak intensity of the surface of operation target reaches preset intensity threshold, the current operation mode of unmanned aerial vehicle is switched from cleaning mode to cladding mode;Cladding operation is carried out to operation target in cladding mode.The method can solve the problem that in the prior art, cleaning and cladding step operation lead to long exposure time of metal surface, easy to occur secondary oxidation, thereby affecting cladding layer combination quality and operation efficiency.

A level completion interface display method and apparatus, a terminal, and a storage medium, belonging to the technical field of human-machine interaction. The method includes: displaying a task completion condition of a current level and a task progress bar in a level completion interface, where the task progress bar includes an ith stage goal and an ith goal achievement reward corresponding to the ith stage goal; displaying a second progress value; and displaying, in a case that the second progress value reaches the ith stage goal, an (i+1)th stage goal and an (i+1)th goal achievement reward corresponding to the (i+1)th stage goal in the task progress bar.

The application relates to a method for intelligently stringing and parallelizing videos through target labels, which comprises the following steps: extracting a label string keyword and a structured feature attribute of a target in a main video; performing algorithm matching weight on the label string keyword and the structured feature attribute; and performing batch matching of the structured feature attribute and the label string keyword similarity in a target information table. As long as the two dimensions of the structured feature attribute similarity and the label string keyword matching degree of any target except a current target reach a certain percentage or more, the target is added to a similar target pool and waits for further inspection. The method can solve the problem that, in video work, because target features cannot be effectively utilized for intelligent comparison and stringing and parallelizing, omission occurs, thereby leading to incomplete stringing and parallelizing videos.

The present invention discloses a low-degree-of-freedom target search and arrival strategy for a mobile robot arm, which is applied to a mobile robot arm including a trolley, multiple swivel joints and swing joints. An image acquisition device is installed at the end of the mobile robot arm, and the two-joint combined motion of the mobile robot arm is selected. The target space is traversed and roughly searched with the maximum field of view angle as the step length until the target object appears in the field of view. By calculating the relative position of the target and the robot arm, the combined motion angle of the two joints is determined, so that the target object is located in the center of the field of view of the image acquisition device, and the precise positioning of the target object is achieved; the trolley is further moved closer to the target object, first the trolley turns to the direction of the target object, the swivel joint rotates in the opposite direction to compensate for the rotation of the trolley, and then the trolley moves toward the target object, during which the swing joint is adjusted to ensure that the target object does not move out of the central area of ​​the field of view, until the distance between the target object and the trolley reaches the set threshold, and the target arrival task is completed.

An object of the system according to the embodiment is to provide progress management and feedback for a user to achieve a goal.SOLUTION: A system according to an embodiment includes an objective setting section, a progress tracking section, an advice providing section, and a reward giving section. The goal setting unit uses the generated AI to find out what the user wants to achieve or improve, and sets an appropriate goal and deadline. The progress tracker tracks the user's progress and provides real-time feedback. The advice providing unit provides advice based on the progress status. The reward giving section gives a reward when the objective is achieved.SELECTED DRAWING: Figure 1

The present invention provides a method, system and storage medium for intelligent decision-making of unmanned aerial vehicles based on reinforcement learning, and relates to the technical field of unmanned aerial vehicles. In the present invention, on the one hand, the decision-making plan of the unmanned aerial vehicle can be updated through the detection results of the unmanned aerial vehicle, so as to real-time dispatch the scale of the unmanned aerial vehicle formation when performing tasks, thereby improving the defense effect. On the other hand, the boundary fence reward obtained based on differential game is designed to ensure that the reward mechanism can accurately reflect the goal achievement of both parties in the game, and through the continuous iterative optimization of reinforcement learning, the unmanned aerial vehicle can gradually learn an effective unmanned aerial vehicle formation defense strategy in a complex environment.

The invention belongs to the technical field of cooperative control, and relates to a multi-target cooperative control method and device, and the method comprises the steps: constructing a saturation pulse controller of each to-be-controlled target through a nonlinear saturation function; constructing a state-space equation of each to-be-controlled target so as to obtain a synchronous target state equation of the cooperative control system; the method comprises the following steps of: constructing an initial state solving model of a to-be-controlled target by aiming at converging an initial state variable of each to-be-controlled target to a synchronous target state under the control of a saturation pulse controller of the to-be-controlled target, thereby solving to obtain an initial state maximum value of the to-be-controlled target and a maximum gain of the saturation pulse controller; setting an initial state variable of each to-be-controlled target and a gain of each saturation pulse controller; and inputting the real-time state variables of each to-be-controlled target and the adjacent to-be-controlled target into each saturation pulse controller to control each to-be-controlled target, so that the state of each to-be-controlled target reaches a synchronous target state to realize multi-target cooperative control.

The application discloses a high-speed camera testing device for a movable target, which comprises a movable target simulation unit, a camera testing unit and an illumination unit. The movable target simulation unit comprises a rotating disc, a calibration plate and a resolution plate as a movable target, and a rotating mechanism. The calibration plate and the resolution plate are arranged on the rotating disc, and the rotating mechanism drives the rotating disc to rotate. The rotating mechanism can be steplessly speed-regulated, so that the movable target reaches a preset linear velocity. The camera testing unit comprises a high-speed camera and a linear motion mechanism. The high-speed camera is mounted on the linear motion mechanism, and the distance between the high-speed camera and the movable target is adjusted through the linear motion mechanism. The high-speed camera is used for recording dynamic images of the movable target, and detecting resolution levels and tailing amounts. The illumination unit comprises first and second light sources with adjustable illumination intensity, which respectively provide sufficient exposure brightness for the camera testing unit and the movable target simulation unit. The application is used for imaging quality evaluation of the high-speed camera under different environmental conditions, and provides guidance for parameter matching in practical application.

The invention discloses a personal holographic self-consistent management method and a servo system based on artificial intelligence, belongs to the crossing field of artificial intelligence, Internet of Things and life science, and is an intelligent self-consistent support system for achieving an autonomous target of a natural person. Physiological, psychological, living environment, life demands and daily behavior data are collected through multi-modal holography, a personal digital twinborn model (quantifying senescence markers and predicting health risks) is constructed based on deep learning, a dynamic personalized intervention scheme is generated in combination with a multidisciplinary knowledge graph, and user compliance is improved in cooperation with an motivation incentive and behavior guide module. And closed-loop servo feedback is formed. The system comprises a data acquisition layer, a model analysis layer, an external tool connection layer and an intervention execution layer, solves the problem that ordinary people cross a digital gap to manage life, overcomes the defects of single data acquisition and the like, improves the accuracy and continuity of target achievement, and can also retain the life process in a holographic digitization manner.

The present disclosure relates to the field of computer graphics technology, and particularly relates to a method, apparatus, storage medium, and electronic device for focusing fire prompts in a game. The method for focusing fire prompts in the game includes: in response to an offensive event targeting a target virtual plot, providing an offensive indication mark in the game terrain scene; wherein, the offensive indication mark is used to prompt that the target virtual plot has been selected as an offensive target by the offensive team corresponding to the offensive event; in response to the number of offensive teams that have selected the target virtual plot as an offensive target reaching a preset threshold, providing a focusing fire indication mark at the target virtual plot; wherein, the focusing fire indication mark is at least used to prompt the number of offensive teams that have not yet reached the target virtual plot and to prompt the degree of focusing fire on the target virtual plot. The method for focusing fire prompts in the game provided by the present disclosure can solve the problem of low information acquisition efficiency in SLG games.

The present disclosure provides an automatic obstacle avoidance method and system for a surgical robot. The method comprises: during the process of controlling the surgical robot to move to a target position, if the surgical robot meets the obstacle avoidance condition, determining a direction vector of the surgical robot to the target position, and determining a unit vector of the shortest distance point of the surgical robot to the target obstacle; calculating the obstacle avoidance direction and speed of the surgical robot according to the direction vector and the unit vector; calculating the attractive speed of the surgical robot according to the direction vector and the pose information of the target position; the attractive speed refers to the speed component of the surgical robot pointing to the target position; calculating the resultant speed of the surgical robot according to the obstacle avoidance speed and the attractive speed, and controlling the surgical robot to realize automatic obstacle avoidance motion and target reaching through the resultant speed. The embodiment of the present disclosure can enable the surgical robot to have autonomous obstacle avoidance capability, and can safely and efficiently realize surgical pose alignment and complete the specified surgical task.

An electronic device, a user terminal, and an operating method for guiding goal setting and goal achievement based on body indicators are disclosed. The operating method of the electronic device may include selecting, from among a plurality of clusters based on body indicators, a target cluster that a target user aims for, based on a user input, determining, based on time series data of body indicators pre-obtained from a plurality of users, a target route that guides the target user from a starting cluster including a body indicator of the target user to the target cluster, determining, based on the time series data, a difficulty level and expected time to be taken for the body indicator of the target user to move from the starting cluster to a most adjacent cluster on the target route, and providing the target route, the time, and the difficulty level to the target user.

The present application relates to the technical field of robot control, in particular to a kind of unmanned mobile target vehicle travel control method and system, comprising the following steps: obtaining path segment information determination acceleration and direction deviation generation uniform instruction sequence execution record and archive control path state completion mark.In the present application, by introducing path length and setting value comparison determination acceleration condition, the angle relationship of current position and path direction is combined to identify motion deviation state, and the unified control instruction is constructed by integrating speed and direction adjustment requirements, which can realize dynamic adaptive scheduling at path segment level, and through execution state record and time mark tracking actual operation process, ensure that each path segment execution condition is real-time controllable, control process has serialization, refinement and closed-loop feedback capability, improve the response speed, running stability and target achievement efficiency of path execution, and have stronger autonomous adaptation and execution guarantee capability when facing environmental uncertainty and path diversity.

This invention relates to a dialogue goal optimization device, method, and program for optimizing goal achievement in user interactions. Based on user utterances and actions, it estimates user states, including emotions, resistance, comprehension, and signs of detachment, as well as goal progress indicating the degree of achievement of primary and sub-goals, and maps these to a state space. After restricting the set of candidate response strategies based on constraints such as compliance and cost applied to the dialogue, it selects a response strategy that maximizes the objective function. Furthermore, it performs a self-correction process that dynamically updates the parameters of the response strategy in response to signs of failure detected during the dialogue. This makes it possible to suppress user detachment while adhering to practical constraints and continuously improve the business goal achievement rate.

To provide a program, electronic apparatus, method and system capable of providing diversified types of nurturing experience.SOLUTION: An electronic apparatus includes a nurturing game execution section that executes, in a turn constituting a nurturing game, a nurturing game based on a nurture command option selected by a player, changes parameters associated with a nurturing game medium and advances the turn. The nurturing game execution section includes a first game execution unit that when the selected nurture command option relates to a first game, executes the first game, and a goal achievement condition determination unit that when the first game and a goal achievement condition are associated with each other, determines whether or not the goal achievement condition has been achieved based on an execution result of the first game. A first processing execution unit changes parameters associated with a player based on the result of determination by the target achievement condition determination unit.SELECTED DRAWING: Figure 3

The present invention discloses a non-smooth three-dimensional cooperative guidance law and system based on an event-driven mechanism, belonging to the multi-missile cooperative guidance technology. First, according to the relative motion relationship between the missile and the target, a relative dynamics equation set is constructed, and a relative dynamics model of the missile and the target is further established; secondly, a finite-time observer is designed to observe the components of the acceleration of the maneuvering target in the line-of-sight, pitch, and yaw directions; then, using the information interaction between the missile groups, a three-dimensional cooperative guidance law in the line-of-sight, pitch, and yaw directions is designed to make the relative distance between the missile and the target reach consistency in a finite time and the line-of-sight angle converge to the expected value; finally, a non-smooth three-dimensional cooperative guidance law based on the event-driven mechanism is designed, taking into account both the completion of the guidance task and the reduction of the control frequency. The simulation results show that the guidance law designed by the present invention can enable the missile groups to hit the target simultaneously with a lower control update frequency, improving the cost-effectiveness of the missiles.

The embodiments of the present application belong to the technical field of communications. Disclosed are a method for triggering measurement reporting, and a terminal and a network-side device. The method comprises: when meeting a first condition, a terminal reporting a measurement result of a measurement target, wherein the measurement target comprises at least one of the following: a measurement object, a reference signal and a target cell. The first condition comprises at least one of the following: a first indication having been received; a first event having occurred; the target cell satisfying a first feature; the measurement result of the target cell having not been reported; a duration within which the measurement result has not reported reaching a first threshold; the measurement result of the target cell having not been reported before a first moment; the measurement result being greater than or equal to a second threshold; a measurement count or measurement time of the measurement target being greater than or equal to a third threshold; the measurement target being oriented to a demand-based SSB; there being an uplink resource which can report the measurement result; a timer having expired or having not expired; and a configuration time or activation time of the measurement target reaching a threshold.

A system is provided.SOLUTION: A system comprising: means for a user to set a goal; means for a AI to generate a message in accordance with the goal; means for managing and displaying a countdown to goal achievement; means for setting an intermediate goal and providing a minor achievement award; means for providing a reward upon achieving a final goal; and means for reporting user progress to family and friends.SELECTED DRAWING: Figure 1

The invention provides a real-time user reach method and device and electronic equipment, and the method comprises the steps: obtaining the to-be-analyzed data of a to-be-reached user, inputting the to-be-analyzed data into a pre-trained target reach analysis model, and obtaining the to-be-analyzed data of the to-be-reached user; and the target reaching analysis model outputs a target prediction triggering result based on the input to-be-analyzed data, gives a specific reaching type and a specific reaching path, and then sends a notification message to a to-be-reached user according to the reaching type and the reaching path given by the target reaching analysis model. By selecting the embodiment of the invention, the problem of poor reaching effect of a traditional user reaching method can be solved, so that the mode that the user is most likely to reach successfully at present is accurately determined based on the to-be-analyzed data of the user on the system side, the probability that the user receives the latest consultation is improved, and the user experience of the user is effectively guaranteed.