49 results about "Hierarchical search" patented technology

The invention relates to the technical field of power distribution network consumption, in particular to a power distribution network distributed photovoltaic output prediction and consumption collaborative optimization method, system and device and a storage medium. Aiming at the problems of insufficient prediction precision and poor absorption optimization effect caused by randomness, intermittency and volatility of distributed photovoltaic power generation, a multi-time-scale collaborative optimization model fusing meteorological time sequence characteristics, load dynamic response and energy storage adjustment capability is constructed. A photovoltaic output prediction parameter is determined through a dynamic hierarchical search mechanism of an improved grey wolf optimization algorithm, a dual-drive collaborative threshold is established to realize deep coupling of prediction and consumption, and multiple operation constraints are dynamically processed based on an adaptive constraint processing strategy. According to the method, the photovoltaic consumption capability and the operation economy of the power distribution network are improved, the safety problems of voltage out-of-limit, line overload and the like are solved, the light abandoning loss is reduced, technical support is provided for high-proportion photovoltaic access to the power distribution network, and collaborative optimization of prediction precision and consumption economy is realized.

The invention relates to the technical field of electrolytic aluminum intelligent control, and discloses a compressed air dynamic distribution control method and system based on an electrolytic aluminum technological process, and the method comprises the steps: obtaining electrolytic aluminum technological parameters, air compressor group operation data and historical compressed air demand data; predicting the initial demand quantity of compressed air; dynamically adjusting the initial demand quantity to obtain a target demand quantity; constructing a multi-target optimization control model of the air compressor group, and solving by utilizing a heuristic hierarchical search algorithm based on dynamic priority to determine target control parameters of the air compressor group; and the target demand quantity of compressed air in the electrolytic aluminum technological process is bound with the target control parameters of the air compressor group, a dynamic control strategy is generated in combination with a priority rule, and dynamic distribution control over the compressed air is achieved according to the dynamic control strategy. According to the invention, the accuracy and economical efficiency of compressed air distribution and the system stability in the electrolytic aluminum production process are improved.

The invention provides a semantic search method and system for blood disease medical record big data, and relates to the technical field of medical information processing.The method comprises the steps that firstly, a blood disease medical record semantic association network is constructed, medical record text units serve as nodes, semantic association relationships serve as edges, and related information of the nodes and the edges is marked; analyzing a user search intention to generate a search semantic vector, calling semantic association network information to perform dynamic semantic matching to obtain a matched medical record text unit set, generating a hierarchical search result according to a matching result, dividing and sorting according to a matching dimension, and generating semantic association interpretation; and finally, based on the access behavior feedback of the user to the hierarchical search result, optimizing the semantic association network, recording user clicking, staying and secondary search triggering conditions, and adjusting the node association priority, edge association strength and weight to improve the accuracy and practicability of blood disease medical record search.

Methods and systems for generating content recommendations using AI models are disclosed herein. In some embodiments, the method includes receiving user input. The method includes converting the user input into a high-dimensional embedding using one or more AI models. The method also includes performing a hierarchical search using the high-dimensional embedding to retrieve and refine a search result of recommended items and presenting the recommended items to a user.

This invention discloses a fast beam alignment method based on the simplex method. It achieves rapid beam alignment between communication devices operating on highly mobile platforms through two stages: preprocessing and simplex processing. The preprocessing stage introduces a hierarchical search approach, providing a more reasonable initial solution for the subsequent beam alignment algorithm, effectively reducing the likelihood of the simplex algorithm getting stuck in local optima. Compared to previous beam alignment methods, this significantly reduces the overall algorithm's time complexity and implementation complexity, while maintaining the same order of magnitude of angular error, demonstrating superior performance.

The invention relates to a hierarchical multi-objective optimization method and system for approximate calculation parameter optimization. The method comprises the following steps: constructing a hierarchical search model for approximate calculation commitment optimization; and in the category-type decision-making layer, taking each approximation strategy as an arm, maintaining the arms by adopting a multi-arm tiger machine algorithm, obtaining random sampling values in each round of iteration according to the obtained Beta distribution, and evaluating the target arm corresponding to the maximum value so as to obtain an arm to be optimized. And inputting the parameter point to be evaluated into a numerical decision-making layer to perform parameter iterative optimization, and generating a next parameter point to be evaluated by maximizing a qNEHVI acquisition function, so that a program, corresponding to the parameter point, of the arm to be optimized is executed through a multi-target Bayesian optimization engine, and an optimization evaluation result is obtained. And obtaining the most approximate calculation configuration according to the result and the preset evaluation budget. The method can face mixed and hierarchically dependent variable space, and can improve the tuning efficiency and reduce the cost.

The invention discloses a wartime art element heuristic optimization algorithm inspired by ancient Chinese wartime. The war art algorithm simulates a stratified command structure of commander decision, samson command and soldier execution to solve the complex optimization problem. The warfare art algorithm is mainly characterized in that layering and space division are carried out, wherein a solution space is divided into a plurality of warfare areas, and an optimal individual is selected as a commander and a samson; according to the dynamic strategic decision, the commander is switched between a global exploration strategy (petal blooming) and a local development strategy (petal contraction) according to the dynamic switching probability. And dynamic distribution of military strength: dynamically adjusting search military strength according to the combat work of each legion group so as to balance global and local search capabilities. The soldiers are divided into commander parents, samson parents and ordinary soldiers, and the commander parents, the samson parents and the ordinary soldiers adopt hierarchical step lengths, so that multi-level and high-precision search execution is realized. Experimental results show that the algorithm is superior to various existing mainstream optimization algorithms in the aspects of convergence precision, stability and robustness.

The invention relates to a low-wire-harness multi-laser-radar automatic calibration method and device, electronic equipment and a storage medium. The method comprises the steps that after static point cloud data collected by a preset number of low-wire-harness radars are preprocessed, ground point cloud extraction is carried out based on an improved RANSAC algorithm, and a ground plane is generated; based on a ground plane extracted from the point cloud data of the preset number of low-wire-harness radars, plane matching is carried out to solve an external parameter initial value; and setting a region of interest (ROI), carrying out iterative closest point (ICP) algorithm optimization by a hierarchical search strategy to generate an external parameter matrix, and completing automatic calibration of the low-wire-harness multi-laser radar. According to the target-free on-line calibration method based on the natural scene features, no pre-arranged facility is needed, full-scene self-adaptive calibration is achieved, and the flexibility of a calibration scheme and the convenience of long-term maintenance are remarkably improved.

The invention relates to a particle-ball-based quantum HVS graph KNN method, and belongs to the field of quantum calculation and machine learning. Aiming at the technical problems of low calculation efficiency and large resource consumption when a classical nearest neighbor algorithm is used for processing high-dimensional big data, the invention provides a hierarchical search scheme fusing granular ball reduction and quantum parallel calculation. The hierarchical search scheme comprises the following steps: generating a low-dimensional feature unit through a granular ball compression original data set; constructing a hierarchical Voronoi diagram structure to realize a coarse-to-fine search path; encoding data by adopting a quantum random access memory, and accelerating similarity calculation by utilizing a quantum exchange test circuit; and dynamically screening nearest neighbor nodes in combination with the priority queue. The method significantly improves the classification efficiency, effectively reduces the occupation of quantum bit resources, guarantees the classification precision, and provides technical support for the landing of quantum machine learning in industrial detection and other scenes.

The invention provides a hierarchical retrieval device and method for LLM-driven big data retrieval, equipment and a medium, and relates to the technical field of artificial intelligence and big data retrieval. The method is used for screening out target data query information so as to reduce occupation of LLM context Token and improve cross-domain complex query retrieval efficiency of LLM, and comprises an input module, a strategy planning module, an executable strategy generation module and a scheduler; wherein the input module is used for acquiring and preprocessing user query requirements of LLM input by a user; the strategy planning module is used for generating a structured execution plan through a pre-constructed data capability classification document in combination with the user query requirement; the executable strategy generation module is used for generating an API execution instruction which is compliant and can be directly scheduled based on the structured execution plan; and the scheduler is used for executing retrieval according to the API execution instruction and integrating and executing retrieval results to obtain graded retrieval results.

The invention discloses an artificial intelligence digital science and technology system based on big data analysis, and relates to the technical field of artificial intelligence, and the system comprises a backup early warning module which is used for collecting data in real time through a collector, and comparing whether the task attribute and task configuration of data backup are abnormal or not in real time; the pseudo data monitoring module is used for monitoring whether data artifacts exist in the data backup process or not in real time and extracting the monitored data artifacts in real time to mark pseudo data positions; and the hierarchical search module is used for receiving alarm signals of existence of the pseudo data in real time through the data receiver, searching the pseudo data in real time and tracking a crushing execution result. According to the artificial intelligence digital science and technology system based on big data analysis, it is ensured that whether backup data is abnormal or not can be judged in time and early warned during data backup, the situation of false data monitoring omission is avoided, and the accuracy of data backup of artificial intelligence digital science and technology is improved.

The application provides a multimodal large model compression method and device based on sparse codebook quantization, and relates to the technical field of computer vision, wherein the method comprises the following steps: optimizing a visual encoder to make the weight significance distribution of an arbitrary large-scale visual-language model more concentrated; evaluating the influence of each layer weight of the optimized language model on the output through second-order information, and dynamically allocating the code word quantity of each weight group according to the significance; determining the optimal sparse combination from a large-scale codebook by adopting a two-stage strategy of high-level candidate search and low-level subset refinement; and completing model quantization by combining the combination and sparse coefficients, so as to balance the compression and inference performance. The dynamic code word allocation and hierarchical search method based on sparse coding does not need additional training, can adaptively allocate the optimal sparse code word combination, can keep the model expression ability under extremely low bits, and can improve the quantization compression efficiency and inference performance.

The application discloses a substation mobile operation platform global path planning system and method based on hierarchical search and a medium, relates to the intelligent operation and maintenance technical field of electric power engineering, and constructs an environment map of a substation and carries out pretreatment through an environment modeling and map preprocessing module, generates a safe passage map; through a hierarchical search path planning module, based on the safe passage map, a hierarchical architecture combining topological layer search and metric layer search is adopted to plan a path, so that the complexity of the global search space is greatly reduced, and the planning efficiency and path accuracy are considered. Through the path optimization and smoothing module, the initial candidate path is smoothed and the redundant path segment is removed, and the optimized path is obtained. Through the kinematic constraint checking module, whether the optimized path meets the kinematic characteristics of the mobile operation platform is checked, and when it does not meet, the path optimization and smoothing module is returned for iterative adjustment, so that the execution path meets the motion constraint of the mobile operation platform, and the path executability is improved.

The invention particularly relates to a hierarchical search three-dimensional airspace path planning method and system based on an adaptive resolution grid. The method comprises the following steps: constructing a corresponding multi-resolution grid model based on a three-dimensional grid map; global path planning is carried out on the coarse resolution grids, coarse paths of all coarse grid nodes are determined, and a coarse path sequence is constructed; performing non-overlapping segmentation on the coarse path sequence; planning local windows matched with the fine-resolution grids, and determining window entrance and exit points corresponding to the local windows; performing obstacle recognition on each local window based on the fine resolution grid, calling a corresponding path generation strategy according to an obstacle recognition result of the local window, and determining a local refined sub-path corresponding to each local window; and splicing the path information of each local window in sequence to obtain a path planning result. According to the method, efficient and reliable path planning of a large-scale and complex three-dimensional airspace environment can be realized.

A beamforming design method for intelligent metasurface arrays based on orthogonal time-frequency-space technology includes: aggregating multipath channels under direct illumination into cascaded channels with near-field direction vectors; randomly initializing the phase shift of intelligent metasurface units; establishing an effective channel matrix based on the cascaded channels; then establishing a multi-user and rate objective function; maximizing the objective function through phase shift optimization using a hierarchical search strategy; repeatedly executing the hierarchical search strategy to search and optimize subsequent blocks until the number of intelligent metasurface units in each block reaches a preset value; then performing an exhaustive search in the final block, thus completing one iteration; repeating the iteration until the maximum number of iterations is reached; outputting the final optimal phase shift; and implementing beamforming design based on the final optimal phase shift. This invention can reduce the complexity of beamforming design and ensure reliable transmission of high capacity during high-speed movement.

A method performed by one or more computers. The method comprises receiving a natural language query specifying requirements for a compound; processing the natural language query using a language policy to generate a plurality of representations of candidate compounds that each satisfy at least a subset of the requirements specified in the natural language query. Each representation specifies at least a chemical formula of the corresponding candidate compound. The method further comprises, for each representation in a subset of the representations, using a generative machine learning model conditioned on the representation to generate one or more candidate chemical structures, each candidate chemical structure comprising a respective spatial location for each of the atoms of the corresponding candidate compound; and selecting a chemical structure and corresponding compound from the plurality of candidate chemical structures.

The invention discloses a system and a method for disabling a microphone of a mobile terminal through peripheral simulation. A dual disabling mechanism of system-level microphone occupation and physical-level ultrasonic shielding is realized through a peripheral device connected with a charging interface. The method comprises the steps of collecting a charging interface state, equipment vibration and audio configuration parameters, identifying an equipment type and extracting a mechanical conduction path; registering virtual audio equipment to obtain a system permission, and scanning and positioning the resonant frequency of a microphone; configuring ultrasonic parameters to generate an eddy current interference mode, and constructing a turbulence barrier path; generating a resonance enhancement primitive library based on the mechanical conduction path and the barrier path, and coupling the resonance enhancement primitive library with the focus token to form a directional shielding scheme; constructing a mechanical resonance envelope based on a vibration conduction efficiency peak value, and judging interference coverage to form a shielding effect field; and finally, an optimal parameter combination is positioned in a multi-dimensional interference space through hierarchical search, reliable forbidding of the mobile phone microphone is realized, and power consumption control and equipment compatibility are considered while the forbidding effect is ensured.

The invention discloses a data processing method and device, electronic equipment and a nonvolatile storage medium. The method comprises the following steps: acquiring a user question text, and acquiring a target text tree of original knowledge corpus content corresponding to the user question text; a target node corresponding to a user question text in a target text tree is determined by conducting layer-by-layer searching in the target text tree, and the layer-by-layer searching is used for determining the correlation degree between different nodes and the question text according to summary information and detail information of knowledge text content fragments; and according to the knowledge text content fragment corresponding to the target node, generating an answer text corresponding to the user question text. According to the method and the device, the technical problems that recall is inaccurate and a knowledge structure cannot be effectively utilized when a knowledge retrieval method in related technologies is used for processing a complex hierarchical knowledge base are solved.

The invention relates to the field of artificial intelligence, particularly discloses a high-dimensional evolutionary feature selection method fusing filtering and packaging strategies, and aims at high-dimensional, small-sample and unbalanced complex data to realize minimum discriminant feature subset screening through a multi-stage hierarchical search framework from coarse to fine and from global to local. The method comprises the steps of generating a high-quality initial population by adopting core-marginal probability sampling and preferentially entering evolution based on double filtering type integrated score sorting of symmetric uncertainty SU and ReliefF; an environment-aware unimproved counter is introduced in the global search stage, the feature adding probability and the feature removing number are dynamically adjusted to balance exploration and development, and repeated evaluation is reduced in combination with fitness cache; and when search stops, binary particle swarm optimization neighborhood refinement is triggered, local high-strength discrete search is realized by Sigmoid mapping, and global optimum is backfilled and updated. Experiments prove that the method obtains a high F1-score and a significant compression feature number on a plurality of high-dimensional data sets.

This application discloses a method and system for spot market bidding decisions in combined heat and power (CHP) power plants, relating to the technical field of CHP power plants. The method includes: acquiring operating data of the CHP unit and market data of the electricity spot market; constructing a heat-power coupling and coal consumption characteristic model based on the operating data and the market data, with rigid heat load supply parameters as the primary constraint; inputting the cleaned operating data and market data, along with energy conversion efficiency, energy consumption characteristics, and feasible domain of CHP output under different operating conditions, into a chaotic hierarchical gray wolf optimization algorithm to initialize the population and implement a hierarchical search strategy; defining a fitness function with profit maximization as the objective, solving for the optimal power output or optimal bid price, and guiding the CHP power plant in making bidding decisions regarding power generation or price. This application aims to solve the problems of unscientific bidding decisions and low profitability of CHP power plants in the electricity spot market.

A method performed by one or more computers. The method comprises receiving a natural language query specifying requirements for a compound; processing the natural language query using a language policy to generate a plurality of representations of candidate compounds that each satisfy at least a subset of the requirements specified in the natural language query. Each representation specifies at least a chemical formula of the corresponding candidate compound. The method further comprises, for each representation in a subset of the representations, using a generative machine learning model conditioned on the representation to generate one or more candidate chemical structures, each candidate chemical structure comprising a respective spatial location for each of the atoms of the corresponding candidate compound; and selecting a chemical structure and corresponding compound from the plurality of candidate chemical structures.

Methods and systems for generating content recommendations using AI models are disclosed herein. In some embodiments, the method includes receiving user input. The method includes converting the user input into a high-dimensional embedding using one or more AI models. The method also includes performing a hierarchical search using the high-dimensional embedding to retrieve and refine a search result of recommended items and presenting the recommended items to a user.

A method and system for cable defect detection and identification based on TMR (Transmission Measuring and Reconstructing) is disclosed. The method includes: receiving high-frequency pulse current signals from a power cable using an array rectangular probe integrating an excitation coil and a TMR sensor array; comparing the signal differences between defective and normal locations to obtain differential signals; and performing optimal spatial reconstruction of the differential signals using phase space reconstruction, symbol entropy, and recursive hierarchical search algorithms to obtain a differential reconstruction space matrix. The HIS (Hyperspective of Influence) distribution curve is then calculated and used as input features for a power cable defect identification model with an adaptive activation function, enabling automatic defect identification. This invention employs phase space reconstruction technology to reconstruct the spatial matrix of the differential signals. By calculating the HIS distribution curve of the differential reconstruction space matrix, the signal distribution differences reflected in the reconstruction matrix caused by fluctuations are eliminated, resulting in an overall 12% improvement in recognition rate compared to traditional methods combining statistical features such as peak voltage with models such as SVM and 1DCNN.

The invention provides an OCT (Optical Coherence Tomography) imaging three-dimensional splicing method based on mechanical arm pose priori, which comprises the following steps of: firstly, extracting an edge probability body in an OCT coordinate system of each scanning section by utilizing U-Net, and secondly, extracting an edge probability body by utilizing tail end pose priori output by a mechanical arm controller and combining probe clamping external parameters; each segment of OCT volume data and the corresponding feature body are uniformly put back to the same world coordinate system, and it is guaranteed that multiple scanning segments have uniform space reference; and finally, carrying out hierarchical search by taking the probability body under the same world coordinate system as a registration target, and reducing the influence of original OCT noise, uneven brightness and low contrast on the registration precision from the source.

The application discloses a network positioning method and system based on topological correlation analysis, relates to the technical field of communication network fault positioning, and comprises the following steps: acquiring a receiving optical power sequence, a forward error correction count sequence, a logical topological relationship and physical resource organization data of a network branch, calculating a branch drift sequence, and establishing a membership relationship between the network branch and a candidate physical positioning unit; generating a common mode drift sequence based on a nearest common ancestor, and performing common mode processing to calculate a selective synchronization coefficient; further calculating a selective interpretation degree of the candidate physical positioning unit, and combining a hierarchical search graph and a swarm intelligence algorithm to obtain an optimal physical positioning unit; finally, determining an affected branch set and a relative confidence degree, and outputting a positioning result. The application can realize fine positioning of a local physical abnormal position of a PON tree-shaped optical network.

This invention discloses a hierarchical retrieval method, storage medium, and computer device, belonging to the field of document processing technology. It includes: S100, obtaining the hierarchical paragraph parsing results of the input document; S200, retrieving the title paragraphs in the parsing results according to the user's query, generating a set of title paragraphs based on the retrieval results, determining whether the title paragraph set is empty, and if not, outputting a semantically complete paragraph; if so, proceeding to step S300; S300, retrieving the body text paragraphs in the parsing results according to the user's query, and outputting a semantically complete paragraph or summary based on the retrieval results. This invention, by combining the hierarchical parsing results of the document, can improve the completeness of text retrieval results in large-scale model retrieval and enhance document question answering, thereby improving the correctness and completeness of the generated answers in document question answering.

The invention discloses a robot motion planning method based on a mixed space, which comprises the following steps: generating interpolation nodes according to a given tracking route, constructing a hierarchical search tree, then estimating a motion range of each joint based on the tracking route, screening out an effective joint configuration of a starting point on the basis of the motion range, and forming a root node set. And carrying out downward iterative search from the next planning point of the root node of the search tree, searching a sampling pose meeting a constraint condition, and selecting a node from the hierarchy of the hierarchical search tree corresponding to the previous planning point as a candidate father node pose. Then, detecting the validity of a local path between the candidate father node and the sample node; when the local path meets the task constraint, deriving the joint configuration of the sample node from the joint configuration of the candidate father node, and performing collision detection and joint limit judgment. And if all conditions are met, adding the joint configuration of the sample pose into the search tree. And when successfully expanding to the last planning point, the planning is successful.

The invention provides an azimuth angle estimation system and method, and aims to solve the problems of low angle resolution, large calculation amount and poor adaptability to a sparse array in the prior art. The system adopts a hierarchical search strategy and combines FFT and DBF technologies to realize high-precision azimuth angle estimation. Rough estimation of a large-view-field target is carried out through FFT, and then fine adjustment is carried out on a target area by using DBF, so that the processing efficiency is improved while the precision is ensured. According to the system, the processing flow is divided into a plurality of functional units through modular design, parallel processing of a plurality of targets is achieved through a Dataflow mechanism, and the processing throughput and the real-time performance are greatly improved. Besides, for a non-equal-interval antenna array, an array interpolation and zero padding mechanism is introduced, high-precision angle estimation is ensured, and hardware complexity is reduced. Generally speaking, the precision and the real-time performance of azimuth angle estimation are remarkably improved, and the method is suitable for high-precision target detection in the fields of automatic driving, intelligent transportation and the like.

The invention is applied to the technical field of RDMA, and particularly relates to a multi-QP scheduling method of RDMA and a network card with an RDMA function. The method is used for performing scheduling processing on a QP queue from an RDMA network card to a host, and comprises the following steps: registering a QP with a to-be-processed working queue element by using a record table; the method comprises the following steps: grouping and managing QP based on a record table, maintaining a corresponding state flag for each group, and constructing a layered progressive table structure from the QP to the group to which the QP belongs and then to the state flag of the group; on the basis of a progressive table structure, hierarchical search is firstly performed, and then a positioning-rearrangement-positioning strategy is adopted to complete scheduling tasks of all groups in a traversing manner. By adopting the method provided by the invention, a quick and balanced scheduling effect is achieved.

The invention discloses a microsphere roundness error detection method based on multi-scale hierarchical search and gradient optimization, and relates to the technical field of precision microsphere roundness error detection.The method comprises the steps that S1, after a color microsphere microscopic image is collected, a background-removed target feature image is obtained through preprocessing; s2, acquiring the initial circle center and radius of the microsphere from the target feature image; s3, based on the initial circle center and the radius, performing multi-stage optimization on the initial circle center by adopting a multi-scale search mode to obtain a circle center position I; s4, performing local fine optimization on the circle center position to obtain a circle center position II with the minimum roundness error; and S5, performing multiple times of measurement on the microspheres in different directions by adopting the methods from S1 to S4, and obtaining a final value of the roundness error detection of the microspheres by taking an average value from the plurality of circle center positions II. According to the method, the circle center position of the microsphere is optimized step by step from different scale levels, the roundness error of the precise microsphere is calculated, and the stability and reliability of roundness error calculation are effectively improved.