40 results about "Function learning" patented technology

The invention relates to the technical field of robot control, and discloses a robot continuous control-oriented triple optimization SAC reinforcement learning method, which comprises the following steps that a robot executes an initial strategy in a real environment to collect empirical data; initializing a strategy network, a value network and a target network, and performing experience playback and training updating on the strategy network, the value network and the target network through a triple optimization SAC reinforcement learning method; and continuously circulating the network updating process to obtain an optimal control sequence of task execution of the robot. The problem of underestimation is relieved by improving a strategy updating mechanism and stable value function learning, the problem that the robot cannot execute the optimal strategy is solved, underestimation deviation in the strategy is effectively relieved, the accuracy of robot action selection is improved, and more accurate guidance is provided for the robot to adopt correct actions.

The invention provides a large model code translation method and device fusing code functions and styles, and relates to the technical field of natural language processing. The method comprises the steps that code pairs composed of source codes and target codes are obtained from an online programming platform, the code pairs are processed according to similarity retrieval, fine granularity scoring and difference testing, and a function consistency data set is constructed; performing functional learning training on the large model according to the functional consistency data set and an instruction fine tuning method to obtain a large model subjected to functional learning training; obtaining a source code, generating positive sample translation and negative sample translation of the source code, and constructing a style-oriented data set; and according to the style-oriented data set, style learning training is carried out on the large model subjected to function learning training, and a trained code translation large model is obtained. According to the method, a low-cost and high-efficiency code translation model is developed around a large-scale language model, and the correctness and readability of translated codes are enhanced.

The utility model relates to the technical field of study desks, and discloses a multifunctional study desk. According to the device, the lower surface of the supporting hollow column is fixedly connected with a connecting flat plate, and the end, opposite to the supporting hollow column, of the connecting flat plate is connected with a plurality of steering shafts, a connecting vertical plate, a concave clamping plate, a roller, a roller rotating shaft and an anti-disengaging nut. An operator uses the supporting hollow column as a supporting structure of the table top and uses the connecting flat plate to bear the moving part at the bottom. The connecting vertical plate and the concave clamping plate are connected through the steering shaft, the idler wheels are connected in series through the combination of the idler wheel rotating shaft and the anti-disengaging nut, and therefore movement of the whole device is achieved. By means of the structure, an operator can drag the whole learning table in any direction through the learning table, stable operation can be kept in the moving process, and the risk that objects on the table top are overturned is avoided.

The utility model discloses a multi-functional study tower, including tower base, tower top, two sets of first flat mouth hasp subassembly and two sets of second flat mouth hasp subassembly, tower base includes two first side plate, seat plate, first front plate and first table board, tower top includes two second side plate, anti-drop pole, second front plate and second table board, tower top is arranged right above tower base, and the first flat mouth hasp subassembly and the second flat mouth hasp subassembly are arranged right above tower top. The tower base is hinged with the tower top; the height of the first side plate is the same as that of the second side plate; the two sets of first flat mouth hasp assemblies are arranged on the transverse outer side of the learning tower and located at the rear end of the combination portion of the first side plate and the second side plate. The two sets of second flat-mouth hasp assemblies are arranged on the transverse outer sides of the multifunctional learning tower respectively, the first parts of the second flat-mouth hasp assemblies are arranged on the lower portion of the front end of the first side plate, and the second parts of the second flat-mouth hasp assemblies are arranged on the upper portion of the front end of the second side plate. The tower base and the tower top are connected in a hanging mode through the four hasp assemblies, the process of mutual conversion between the learning tower and the desk is fast and convenient, and connection is firm.

To provide a device etc. for predicting the number of people using a facility, for predicting the number of scheduled on-site participants and the number of scheduled remote participants with high precision.SOLUTION: A device for predicting the number of people using a facility 10 includes a remote participation rate determining function learning unit 13b that learns a remote participation rate determining function on the basis of information including a result of the number of on-site participants and a schedule result, a schedule information acquiring unit 13c that acquires schedule information including the schedule of a prediction target event, and a scheduled participant number calculation unit 13d that calculates the number of scheduled participants of the prediction target event on the basis of the schedule information, and further includes a scheduled participant number separation unit 13f that calculates the number of scheduled remote participants by multiplying the number of scheduled participants by the remote participation rate, and further calculates the number of scheduled on-site participants by subtracting the number of scheduled remote participants from the number of scheduled participants.SELECTED DRAWING: Figure 2

A method for training and using a machine-learning based model to reduce and troubleshoot incidents in a system may include receiving first metadata regarding a previous modification, extracting a first feature from the received first metadata, receiving second metadata regarding a previous incident, extracting a second feature from the received second metadata, training the machine-learning based model to learn an association between the previous modification and the previous incident, based on the extracted first feature and the extracted second feature, and using the machine-learning based model to determine a risk level for a proposed modification to a system.

The utility model provides a study table with a correction function. It comprises a base, a support plate and a support body are respectively fixed on the top of the base, a seat is fixed on the top of the support body, a first electric push rod is fixed on the top of the support plate, a tabletop is fixed on the top of the first electric push rod, a support block is fixed on the seat, and a backrest is rotatably provided on the top of the support block, a slide rail is fixed on one side of the backrest, and a slider is slidably provided on the slide rail, a fixed block is fixed on one side of the support block, and a second electric push rod is fixed on the top of the fixed block. The study table with a correction function provided by the utility model solves the problem that the existing study table can adjust the height and tilt angle, but the user will feel tired after long-term virtual study and work, and the upper body is prone to unconsciously lean forward, resulting in an incorrect sitting posture and affecting health.

The application provides a large model code translation method and device fusing code functions and styles, and relates to the technical field of natural language processing. The method comprises the following steps: obtaining a code pair composed of a source code and a target code from an online programming platform, processing the code pair according to similarity retrieval, fine-grained scoring and differential testing, and constructing a function consistency dataset; performing function learning training on a large model according to the function consistency dataset and an instruction fine-tuning method to obtain the large model trained through the function learning training; obtaining the source code, generating positive sample translation and negative sample translation of the source code, and constructing a style guide dataset; and performing style learning training on the large model trained through the function learning training according to the style guide dataset to obtain a trained code translation large model. The application develops a low-cost and high-efficiency code translation model around a large-scale language model, and enhances the correctness and readability of translated codes.

The utility model discloses a multifunctional learning machine, which comprises a machine body and a circuit control board arranged in the machine body, the machine body is a metal shell and comprises a display screen shell and a shell body, the display screen shell covers the shell body, the display screen shell is detachably connected with the shell body, and the circuit control board is arranged in the machine body. The circuit control board is positioned in a space formed by the display screen shell and the shell; a camera and an LED lamp are arranged in the machine body, the LED lamp is a light supplementing lamp and supplements a light source for the camera, the camera and the LED lamp are arranged in a camera arrangement area, the camera arrangement area protrudes out of the shell, and a camera protection cover covers the camera arrangement area; the lower portion of the machine body is provided with a scanning and reading device, the scanning and reading device is provided with a protective cover, the protective cover is independent of the display screen shell and located on the front face of the learning machine body, the scanning and reading device is further provided with a microswitch, a spring and a pressing key, and the pressing key is connected with the shell in an up-down sliding mode. And the spring is pressed against the pressing key and is in pressing connection with the microswitch behind the pressing key, and the microswitch is in contact with the bottom of the pressing key.

A learning device (1) uses a model obtained by associating sensor information acquired by an observation unit of a first processing device (3) having an observation unit (33) with a tag corresponding to the sensor information and learning the sensor information in a second processing device (4). The observation unit acquires, as sensor information during machining, either a sensor signal indicating an observation result of at least one of a state of a workpiece and a state of a machining device, or a characteristic quantity of the sensor signal. The first reference information recording unit records, as first reference information, sensor information when machining performed by reference machining parameters is performed in a first machining device. A reference information acquisition unit (12) that acquires, as second reference information, sensor information when machining performed by the reference machining parameters is performed in the second machining device; and a correction function learning unit (13) that learns a correction function (44) used for correction when the sensor information is corrected in the second processing device and then input to the model such that the feature of the corrected second reference information approaches the feature of the first reference information.

A position estimation system with low power consumption is provided. The position estimation system includes a comparison unit, a learning unit, a data acquisition unit, an inference unit, a data conversion unit, and an evaluation unit. The comparison unit has a function of calculating a first parallel movement amount and a first rotation amount on the basis of machine learning data representing geographic information. The learning unit has a function of generating a machine learning model through learning using the machine learning data, the first parallel movement amount, and the first rotation amount. The data acquisition unit has a function of acquiring acquisition data representing environmental information on the vicinity of a position estimation device. The inference unit has a function of inferring a second parallel movement amount and a second rotation amount, with use of the machine learning model, on the basis of the acquisition data and the machine learning data. The data conversion unit has a function of converting the machine learning data to evaluation data on the basis of the second parallel movement amount and the second rotation amount. The evaluation unit has a function of evaluating the degree of correspondence between the acquisition data and the evaluation data.

The invention provides a network attack and defense strategy optimization method based on a random game and a Rainbow algorithm. The method comprises the following steps: constructing a network attack and defense random game model; performing Q function learning and strategy optimization by using a Rainbow deep Q network algorithm; and inputting the current state features into the trained Rainbow deep Q network, calculating Q values corresponding to all defense actions, and selecting the defense action which maximizes the Q values as an optimal defense strategy in the current state. According to the method, game analysis is carried out on the earnings of players by using a Rainbow algorithm, and the two game parties obtain benefit maximization through continuous learning and strategy adjustment. In addition, the Rainbow algorithm is added, so that the defense strategy can be adaptively adjusted, and the Nash equilibrium of the two game parties can be obtained without presetting the state transition probability of the network system.

The utility model discloses a multi-functional learning tower, comprising a tower base, a tower top, two sets of first flat-mouth fastener assemblies and two sets of second flat-mouth fastener assemblies. The tower base comprises two first side plates, a seat plate, and a first desk board. The tower top comprises two second side plates, anti-falling bars, and a second desk board. The tower top is arranged right above the tower base, and the tower base is hinged to the tower top. A height of the first side plate is the same as that of the second side plate. According to the utility model, the tower base and the tower top are connected by the four sets of fastener assemblies, realizing efficient and convenient transformation between a learning tower and a desk and a secure connection.

The invention provides an I / O efficient approximate nearest neighbor search method and device based on function learning, equipment and a medium, and the method comprises the steps: obtaining three billion-scale data sets, carrying out the deduplication and random sampling, and constructing a basic data set and a query set; dividing the data set into a plurality of clusters by adopting a clustering algorithm, training a clustering selection model, and predicting the cluster with the highest probability to which the query point belongs; constructing a Hash model, and mapping high-dimensional data into low-dimensional Hash codes by fusing a composite loss function based on ranking and distance; constructing an index to realize directional retrieval of a target cluster, and obtaining a candidate point set through a priority queue mechanism; training a hash code reconstruction model, reconstructing the hash code of the candidate point set into a vector close to original data, calculating the distance between the reconstructed vector and a query point, and obtaining a top-K approximate nearest neighbor result, so as to solve the problems that index structure optimization is not combined in a hash function learning process, and a large amount of expensive random I / O cost exists.

The invention provides a power load prediction method and device based on multi-scale adaptive feature function learning, and aims to significantly improve the accuracy and stability of power load prediction through deep learning and a feature adaptive mechanism. The method is based on the following core technical means: constructing an adaptive feature function by using historical power load data and multi-time scale features; by learning the feature modes of the load data under different time scales, the data dimension is expanded, and the expression ability of model prediction is improved; by combining characteristic function learning models of different power grid characteristics, various power grid load modes are automatically adapted, and a prediction result is optimized; and finally, through data set training and feedback optimization based on extended features, the prediction precision of the model is improved.

There are provided an apparatus and a method for reconstructing a 3D human object based on a monocular image through depth image-based implicit function learning. A 3D human object reconstruction method according to an embodiment includes: predicting a double-sided orthographic depth map from a front perspective color image of a human object; predicting a signed distance (SD) regarding points on a 3D space from the predicted double-sided orthographic depth map; and reconstructing a 3D human object by using the predicted SD. Accordingly, a human object and details can be naturally reconstructed with respect to not only an area visible through a front perspective color image of the human object but also an invisible area.

The objective is to provide a respondent response estimation system that allows the interviewer to conduct interviews in a natural manner, as if they were actually asking questions to the survey subjects. [Solution] The machine learning device 10 of the survey subject response estimation system 1 is configured to include the following functions: a learning model storage unit 11 that stores and holds a digital clone Ci of each survey subject Pi; a question input unit 13 that inputs question data indicating the content of the question given by the user Q to the required digital clone Cx (=C1, or C2, or ..., or CN) from among the digital clones C1 to CN; and a response output unit 14 that outputs the response obtained from the digital clone Cx according to the question data.

The invention relates to an information security technology, and provides a network attack pattern recognition method based on isometric immersion kernel function learning, which comprises the following steps of: firstly constructing geometric representation for network behavior data by using an isometric immersion kernel function, and then extracting characteristics capable of quantifying a network behavior form from the constructed geometric representation of the network behavior data; the equidistant immersion kernel function model is used for explicitly maintaining an inner product structure of non-Euclidean discrete data in a manifold representation construction process by introducing a learnable tangent space kernel function into the neural network model; according to the method, the most essential geometrical relationship in complex and nonlinear network behavior data is compressed into a low-dimensional space more suitable for machine learning model processing in a lossless or low-loss manner, the essential form of the attack behavior is accurately and stably captured in the complex and confrontation-full data, the sensitivity of attack pattern recognition is improved, and the recognition efficiency is improved. Therefore, the recognition accuracy is improved.

An electronic device and method are disclosed for performing an update of a machine learning model based on unlearning a dataset or features. The electronic device receives a data subset of a first dataset associated with a user. A first machine learning model is trained based on the first dataset. The electronic device trains a second machine learning model based on the received data subset. The electronic device applies a transformation function to the trained first machine learning model based on the trained second machine learning model. The electronic device updates the trained first machine learning model based on the application of the transformation function. The update of the trained first machine learning model corresponds to unlearning at least one of the received data subset or a feature set associated with the second machine learning model.

The application discloses a kind of adaptive modulation coding methods for deterministic low-latency retransmission.In order to optimize average latency under the premise of meeting deterministic latency constraints, the modulation coding scheme of initial transmission queue and retransmission queue is dynamically selected. In order to solve the problem of inter-slot coupling of the queue, a multi-step Q-learning method based on updating system is proposed to reacquire the value function of the system when updating event is triggered. A virtual queue corresponding to the deterministic latency constraint is constructed, and a cost function based on the virtual queue and the actual queue is designed for value function learning. Based on the obtained value function, the system determines the modulation coding scheme to be used according to the current queue length. The adaptive modulation coding scheme proposed can meet the deterministic latency constraint and minimize the average latency. The application can be used for modulation coding scheme design considering retransmission in transmission network to reduce the average latency under the premise of meeting the deterministic latency constraint.

The invention discloses a non-invasive continuous blood pressure prediction method based on multi-dimensional data driving, which comprises the following steps: reading ECG and PPG original signals, and preprocessing the ECG and PPG original signals; wherein the preprocessing comprises filtering, polarity correction, time alignment and normalization preprocessing; time sequence features, amplitude features and waveform morphological features are obtained through calculation based on the preprocessed ECG and PPG signals, and a feature set is constructed in combination with physiological parameters; selecting a deep learning framework, constructing a Transform hybrid model, and designing a loss function; and selecting an optimization function amount learning rate attenuation strategy, setting hyper-parameters including the number of iterations and the batch size, inputting the feature set into the network for training, and testing the model. The electrocardiogram signals, the photoplethysmography signals and the physiological parameters are fused, blood pressure prediction is achieved through an improved Transform architecture, and the adaptability and stability of the model are enhanced while the prediction accuracy is improved.

The present invention discloses an end-to-end autonomous driving control system and equipment based on human preference reinforcement learning. In the pre-training stage, the data collected in the CARLA simulator is used to pre-train the neural network model of the reward function based on the yaw angular velocity and the true value of the existing reward function, providing certain prior knowledge for the reward function model, which helps to accelerate the convergence process of the model. In the reward function learning stage, human preferences are used to correct and optimize the reward function. The cross entropy loss of the reward prediction value and the actual preference is used and L2 regularization is added to the loss function to ensure that the learning behavior is closer to human decision-making and prevent reward hacking, thereby achieving the alignment of the decision-making of the autonomous driving system with human values. In the intelligent agent learning stage, the PPO algorithm and multi-channel BEV are used as environmental inputs, and real-time training is performed in combination with the vector output of the throttle opening and the steering angle to ensure the real-time responsiveness and safety of the autonomous driving system.

The invention discloses an authentication method for high-order function learning of a vehicle system and a related device. The method comprises the following steps: in response to an access request of a driver user to a target high-order function, querying whether the driver user performs learning authentication on the target high-order function, if the driver user has been authenticated and the authentication level is high, allowing access, and if the driver user has not been authenticated, performing multi-level learning authentication strategy; the driver user is guided to actively participate in learning the high-order function, theoretical testing, simulation scene testing and real driving scene testing are combined, the driver user is assisted to conduct step-by-step learning authentication, and after step-by-step authentication is passed, the driver user is allowed to access the high-order function. According to the method, the initiative of the driver to participate in learning the high-order function and the mastering degree of the driver to the high-order function can be guaranteed, driving accidents caused by misoperation due to the fact that the driver does not know or is not skilled to the high-order function are reduced, and the intelligent driving safety and reliability are improved.

The invention discloses a risk-aware automatic driving simulation test case sorting method, and relates to the technical field of software testing, and the method comprises the steps: collecting a label-free automatic driving test set, and the test case comprises a plurality of driving scene features; an optimal projection matrix is obtained by adopting objective function learning embedded with double sparse constraints; projecting the test set into a low-dimensional discriminant feature space by using the projection matrix; selecting two test cases with the maximum Euclidean distance in the discriminant feature space as initial elements of a sorting sequence; constructing a strategy scoring device based on a risk-driven component and a prospective exploration component, and generating scores for the candidate cases; the candidate case with the maximum score is selected to be added to the tail of the sorting sequence; repeatedly executing until all the test cases are sorted; and outputting the sorting sequence. Through utilization of dynamic balance risk driving and prospective exploration, an optimal test execution sequence is iteratively constructed, and the capability of covering diversified risk scenes is effectively enhanced.

The application relates to the technical field of data retrieval, and discloses a cross-modal hash retrieval method and system with consistency, which comprises the following steps: S1. acquiring heterogeneous data; S2. acquiring hash codes of the heterogeneous data, and performing hash code learning on the heterogeneous data; S3. performing hash function learning according to the obtained optimal hash code; and S4. mapping the heterogeneous data to the same low-rank Hamming space through the hash function after the function learning is completed, using an exclusive OR operation to the similarity of the heterogeneous data and a retrieval set, returning a result with high similarity, and completing cross-modal retrieval of the heterogeneous data to be retrieved. The application solves the problems of insufficient retrieval precision and complicated optimization process in the prior art, and has the characteristics of being capable of overcoming the heterogeneity of cross modalities.

The application discloses a risk-aware automatic driving simulation test case sequencing method, and relates to the technical field of software testing, and comprises the following steps: collecting a no-label automatic driving test set, wherein the test cases in the test set contain a plurality of driving scene features; obtaining an optimal projection matrix by using a target function learning with embedded double sparse constraints; projecting the test set into a low-dimensional discriminative feature space by using the projection matrix; selecting two test cases with the maximum Euclidean distance in the discriminative feature space as initial elements of a sequencing sequence; constructing a strategy scorer based on a risk-driven component and a forward-looking exploration component to generate scores for candidate test cases; selecting a candidate test case with the maximum score to add to the end of the sequencing sequence; repeating the execution until all test cases are sequenced; and outputting the sequencing sequence. By dynamically balancing the utilization of risk driving and the forward-looking exploration, an optimal test execution sequence is iteratively constructed, and the coverage capability for diversified risk scenarios is effectively enhanced.

The invention discloses an adaptive spatial crowdsourcing task allocation method based on dynamic task demand prediction, and relates to the technical field of spatial crowdsourcing, and the method comprises the steps: carrying out the dynamic task demand prediction based on a demand dependence learning module and a graph neural network according to the historical task data of a target region, and obtaining the predicted task demand information; and obtaining an optimal task allocation result based on worker dependence separation, task value function learning and an adaptive algorithm according to the predicted task demand information, the current task set and the availability window of the staff. Through innovation in multiple aspects of dynamic task demand prediction, global optimization of a task allocation strategy, reduction of calculation complexity, enhancement of stability and reliability of task allocation and the like, the efficiency, flexibility and fairness of space crowdsourcing task allocation are remarkably improved, and the method has wide application prospects and social and economic values.

The invention belongs to the technical field of electronic measuring instruments, and discloses an intelligent interaction method and system for a signal analysis instrument, and the method comprises the steps: collecting multi-dimensional context data in the operation process of the signal analysis instrument in real time; reasoning a user operation intention through a user intention reasoning model based on the multi-dimensional context data; dynamically screening out candidate function menus from a function menu set of the signal analysis instrument according to the inferred user operation intention, and generating a recommended menu set; and presenting the recommended menu set on a human-computer interaction interface of the signal analysis instrument. The technical problems of deep menu hierarchy, low operation efficiency, difficulty in finding associated functions by a user, high learning cost, poor user experience and the like due to the adoption of a static multi-layer menu in an existing signal analysis instrument are solved.

The invention relates to a belief propagation passive sonar array DOA tracking method based on deep learning likelihood modeling. A belief propagation framework of likelihood function learning fuses deep learning (DL) data driving and belief propagation (BP) multi-frame association capability; a data-driven convolutional neural network (CNN) efficiently maps an array sampling covariance matrix into a sparse power spectrum in a nonlinear manner; according to the likelihood function suitable for Bayes reasoning, a sparse power spectrum is converted into a likelihood function with continuous values by using Gaussian smoothing and cubic spline interpolation technologies; efficiently solving a factor graph of a multi-target tracking problem, and reasoning confidence approximation of target state edge posteriori in combination with a BP algorithm and a constructed likelihood function; the maneuvering target stable tracking and clutter suppression capability is enhanced, and a multi-model interaction algorithm and a time correlation-based target new mechanism are fused. According to the method, the DOA of a plurality of maneuvering weak targets can be stably and continuously tracked at the same time under the conditions of complexity and low signal-to-noise ratio.

The system and methods of the present invention involve estimating model parameters for non-linear systems of Differential Equations (DEs). This includes receiving data from these systems and applying Weak-form Estimation of Nonlinear Dynamics methods to the data. These methods are robust to instances of large measurement noise. The system and methods also involve converting strong form representations of a model to weak forms, solving regression problems to perform parameter inference, and using Errors-In-Variables frameworks and iteratively reweighted least squares algorithms. The system and methods of the present invention can be applied to various models from different fields such as population biology, neuroscience, and biochemistry. The system and methods are highly robust and exhibit computational efficiency when used to estimate parameters in some common models including logistic growth, Lotka-Volterra, FitzHugh-Nagumo, Hindmarsh-Rose, a Protein Transduction Benchmark model and Kuramoto-Sivashinsky.