50 results about "Clustering search" patented technology

The invention discloses an unmanned cluster search and rescue task planning method, system and device and a storage medium, and relates to the technical field of search and rescue, and the method comprises the steps: analyzing a multi-source distress signal of a region to be searched and rescued, and determining accident point information; dynamically updating the target discovery probability of each grid sub-region in the to-be-searched-and-rescued region based on the environment feature information and the target moving feature information of the to-be-searched-and-rescued region; determining a current task planning strategy based on the type number of the unmanned equipment in the unmanned cluster and the accident point information; and based on the current task planning strategy and the target discovery probability of the grid sub-region, determining a region search and rescue priority list of each unmanned device, and performing task allocation on the unmanned cluster. Through the above mode, task planning and path distribution are uniformly carried out on multiple types of unmanned equipment in combination with the environment characteristics and the target movement characteristics, accident points are rapidly covered, the search and rescue efficiency is improved, and the success rate of search and rescue tasks is improved.

In an embodiment, operations include receiving a dataset including a set of graphs, applying a graph explainer model on the dataset to determine explain scores, and filtering graph elements of each graph based on the explain scores to determine a first set of graph elements. Further, another dataset of randomized graphs is generated. The graph explainer model is applied on the other dataset to determine noise scores, which are used determine denoised explain scores from the explain scores. Graph elements of each graph are filtered based on the denoised explain scores to determine a second set of graph elements. Thereafter, feature vectors are determined for the first set of graph elements and the second set of graph elements, and prediction driving graph elements are determined based on the feature vectors. Explainability information associated with the set of graphs is rendered, based on the prediction driving graph elements.

The invention provides a voice recognition method and system based on an AI large model, and belongs to the technical field of voice recognizing.The method comprises the steps that firstly, noise reduction and frequency band enhancement in a noise environment are achieved through a pre-trained anti-noise suppression network, and a basis is provided for follow-up processing in combination with multi-dimensional spectrum quality scores; based on similarity matching of element feature vectors and a pre-constructed dialect thermodynamic diagram library and matching weight adjustment based on frequency spectrum quality scores, accurate modeling of specific dialect pronunciation deviation is achieved, moreover, through an acoustic adaptation matrix and a language model adaptation matrix generated through a super network, the adaptability of the model to different dialects is improved, and in addition, the accuracy of the model is improved. According to the method, a fusion thermodynamic diagram and an acoustic adaptation matrix are jointly injected into a pre-trained acoustic model, the recognition accuracy of dialect phonemes is improved through multi-level attention correction, and finally, accurate speech recognition is achieved by adopting a thermodynamic diagram guided cluster search algorithm and combining verification of an adversarial discrimination network.

The invention relates to the technical field of glue pudding quality detection, and discloses a glue pudding quality intelligent detection system and method based on multi-sensor fusion. The system comprises a data acquisition module, a stability analysis module, a detection parameter search module, a quality detection execution module and a quality judgment module. The data acquisition module acquires a surface image, weight and texture elasticity data set of the glue pudding sample through a multi-sensor array; the stability analysis module evaluates the acquired data to obtain image, weight and texture elastic stability factors; the detection parameter search module takes each stability factor as a joint index, and determines an optimal detection parameter group through density clustering search in a detection parameter space; the quality detection execution module detects the target glue pudding of the production line according to the optimal parameter group to obtain multi-source detection data; and the quality judgment module inputs the multi-source data into a classifier to obtain a quality grade judgment result. The system realizes comprehensive detection of the glue pudding quality, and improves the detection intelligence and automation level.

The invention discloses a gas consumption behavior analysis method and device, and relates to the technical field of gas consumption behavior analys.The method comprises the steps that multiple pieces of historical gas consumption data are obtained, and each piece of historical gas consumption data corresponds to one piece of user identity information and one gas consumption date; performing data preprocessing on the plurality of historical gas consumption data, and adding preset user label information to the corresponding user identity information; based on a preset density clustering search parameter, performing density clustering on the plurality of preprocessed historical gas consumption data to obtain a plurality of user groups; and based on the user tag information existing in each user group, adding the user tag information to the user identity information lacking the user tag information in the user group. According to the method and the device, the users are subjected to density clustering processing on the basis of the plurality of historical gas consumption data in combination with the preset user label information, so that the gas consumption behaviors of the users are quickly and reliably analyzed, and the user groups are clustered.

The invention provides an unmanned aerial vehicle cluster distributed region search method and system based on role differentiation. The method comprises the following steps: initializing an unmanned aerial vehicle collaborative search task environment; the information unmanned aerial vehicle updates a cluster search cognitive map; task allocation modeling of unmanned aerial vehicle cluster collaborative search; unmanned aerial vehicle tasks are pre-allocated based on CBAA information; updating a cluster topology connection state of the information subgroup; relay unmanned aerial vehicle task allocation based on connectivity maintenance; unmanned aerial vehicle waypoint tracking control based on collision time cooperative guidance; adjusting an information-relay subgroup proportion based on a region coverage rate; and outputting an unmanned aerial vehicle cluster collaborative search result. According to the method, the CBAA algorithm supports the communication of the unmanned aerial vehicle cluster to keep a distributed decision through improved strategies such as removal of disconnected individuals, an action selection tabu table and mobile base station switching; meanwhile, heterogeneous cooperation between information-relay subgroups is utilized, the action space of the unmanned aerial vehicle is released, the persistent exploration capability of a later cluster is enhanced, and local optimum of a search process is avoided.

The invention belongs to the technical field of data search, sharing and encryption, and relates to a BK-LSH-based searchable encrypted data sharing method, system and terminal. The sharing method comprises the following steps: processing original data to obtain an abstract and a data ciphertext; the method comprises the following steps: extracting keywords of original data, constructing a hash table represented by keyword vectors, grouping hash buckets in the hash table into a plurality of initial clusters, performing iterative optimization, and taking a clustering result as a search index of the original data; uploading the abstract, the data ciphertext and the search index to a cloud server; configuring a plurality of query keywords, generating query trapdoors, uploading the query trapdoors to the alliance chain, positioning corresponding hash buckets in the hash table, matching the query trapdoors with keyword vectors processed by hash functions in the hash buckets to obtain matching degree scores, sorting search indexes according to the matching degree scores from high to low, and storing the search indexes in the alliance chain. And outputting the abstracts and the data ciphertexts corresponding to the previous plurality of search indexes, and decrypting the data ciphertexts to obtain original data. The method is high in clustering search performance and safety.

The invention relates to the technical field of biological pharmacy, and discloses a messenger ribonucleic acid sequence design method and device, computing equipment and a storage medium. According to the method, on the basis that a given 5 'UTR sequence serves as initial input, new codons are added one by one through a growth method, the overall-length minimum free energy and codon use efficiency of the whole sequence are calculated, scored and sorted, an elimination method is used for excluding sequences containing restriction enzyme cutting sites / poor properties / poorer scores, and finally, the sequences containing the restriction enzyme cutting sites / poor properties / poorer scores are obtained. And selecting representative sequences by using a cluster clustering search method to increase diversity, and finally obtaining the sequences for recommendation synthesis. The invention provides an mRNA sequence optimization design method in an environment with 5 'UTR and 3' UTR, the full-length minimum free energy of an mRNA sequence and the codon use efficiency of a CDS region are considered, the two targets can be optimized at the same time, the stability can be optimized from the perspective of overall molecules, the expressibility of the CDS region is optimized at the same time, and the method has the advantages of being simple in structure, convenient to operate and the like. And the stability and expressibility of the mRNA sequence are ensured.

The invention provides a multi-granularity code clone detection method based on clustering search and a large model, and belongs to the technical field of code clone detection. Comprising the steps that an MGCD analyzes a code library to generate a vector database, and each vector represents a function-level code snippet; the code to be detected is analyzed, and the MGCD identifies function clone candidate items in a database by using a search algorithm; an automatic heuristic method is used as a filter to obtain a highly correlated and accurate function-level result; and the MGCD realizes multi-granularity clone detection. According to the method, the semantic clone recognition capability is remarkably enhanced, and complex code snippets with similar semantics are effectively detected. The clustering algorithm improves the retrieval efficiency in a large-scale code library and reduces the calculation cost. The multi-granularity code clone detection is supported, multiple levels such as a function level, a module level and a project level are covered, a more comprehensive and multi-dimensional code similarity analysis result is provided for a user, the detection efficiency is improved, and the flexibility and expansibility of the system are enhanced.

In an embodiment, operations include receiving a dataset including a set of graphs, applying a graph explainer model on the dataset to determine explain scores, and filtering graph elements of each graph based on the explain scores to determine a first set of graph elements. Further, another dataset of randomized graphs is generated. The graph explainer model is applied on the other dataset to determine noise scores, which are used determine denoised explain scores from the explain scores. Graph elements of each graph are filtered based on the denoised explain scores to determine a second set of graph elements. Thereafter, feature vectors are determined for the first set of graph elements and the second set of graph elements, and prediction driving graph elements are determined based on the feature vectors. Explainability information associated with the set of graphs is rendered, based on the prediction driving graph elements.

The invention relates to a cluster search method and device, electronic equipment and a computer storage medium, and the method comprises the steps: obtaining a translation request of a user for a to-be-translated text of a source language, the translation request comprises words specified by the user, and if the specified words comprise at least two words, the to-be-translated text is translated; generating a first target language combination, a first candidate target language combination and a second candidate target language combination based on the initial word, the at least two words and the to-be-translated text, and determining a target translation result corresponding to the to-be-translated text according to a probability score corresponding to each sentence in an initial candidate sentence set formed based on the first target language combination, the first candidate target language combination and the second candidate target language combination. By means of the method, in the process of translating the to-be-translated text, the specified words can be added into the translation process, and the translation requirement of a user is met.

The invention relates to the technical field of intelligent power grids, and particularly provides a power grid intelligent decision-making method, system and device, a medium and a computer program product, and the method comprises the steps: dividing an intelligent agent cluster suitable for a target power grid; establishing an equivalent model of the agent cluster, and generating a decision model of an independent agent; in response to a power regulation and control instruction issued by the power grid coordination center, the target agent cluster searches a matched candidate agent cluster in the regional hierarchy; and the independent intelligent agent determines a matched target intelligent agent, and performs power adjustment according to the energy output information of the target intelligent agent in a preset historical duration. According to the technical scheme provided by the invention, the overall scheduling flexibility of the power grid system can be improved through the intelligent power grid system.

Methods and apparatuses for automatically generating and displaying clustered search results and contextual recommendations are described. While a user is making edits to an electronic document or within an application, a search system may identify a set of search terms based on information entered by the user and / or the locations of the information entered by the user within the electronic document or application and then generate and display search results based on the set of search terms. The search system may cluster search result documents that have a degree of similarity and display multiple clusters of search results to the user. The search system may allow users to specify personalized keyword links and may return a personalized keyword link as a search result for a given search query even if a document or resource referenced by the keyword link has not been indexed or crawled.

The invention relates to a KAN-based unmanned vehicle trajectory prediction method. The method comprises the steps of 1, screening unmanned vehicle threat distribution diagrams obtained according to unmanned aerial vehicle cluster search information to obtain a target probability distribution diagram; 2, extracting data set features through a high threat region weighted midpoint method or a clustering-based position extraction method to obtain a target position; and 3, selecting a proper activation function, and predicting a target trajectory by using the double-KAN prediction model. Compared with an existing trajectory prediction algorithm, the method has the advantages that feature extraction is carried out on the target threat distribution map, and the explicit expression is obtained through KAN training, so that the interpretability of target and trajectory search of the unmanned aerial vehicle cluster is further improved.

This invention discloses an energy-saving control method for pump sets based on discrete operating point clustering search optimization, belonging to the technical field of pump set scheduling control. It acquires pump set operating data based on sensors, predicts the target flow rate based on historical flow time-series data, and determines the target head. Under the premise of meeting water supply constraints, the frequency of any one or more pumps in the pump set is perturbed, and discrete operating points under different frequency combinations are collected. Clustering search optimization is performed based on the discrete operating points to obtain candidate clusters that meet the target requirements. Within the candidate clusters, a multi-index comprehensive evaluation model is constructed to score the points within the clusters, and the points within the clusters with higher scores are selected as representative points, obtaining a set of representative points. Based on the set of representative points, the representative point that best meets the target requirements and has the lowest adjustment cost is selected as the optimal operating point. This invention directly uses sampled points for optimal solution search, avoiding fitting errors and more closely reflecting actual operating conditions, thus possessing good practicality.

The invention provides an unmanned aerial vehicle cluster distributed region search method and system based on global connection. The method comprises the following steps: initializing an unmanned aerial vehicle collaborative search task environment; the unmanned aerial vehicle updates a cluster search cognitive map; performing task allocation modeling of multi-unmanned aerial vehicle collaborative search; cooperative search pre-distribution based on CBAA is carried out; carrying out collaborative search redistribution based on global connectivity; unmanned aerial vehicle waypoint tracking control based on collision time cooperative guidance; and outputting an unmanned aerial vehicle cluster collaborative search result. According to the method, distributed decision-making among multiple unmanned aerial vehicles is realized by using CBAA, and a suboptimal action strategy of the unmanned aerial vehicle is obtained by relying on the optimal suboptimal solution characteristic of the CBAA in a multi-agent task allocation problem; according to the method and the system, the unmanned aerial vehicle cluster is divided into a plurality of unconnected individuals, an unconnected individual removal and action selection taboo table and a mobile base station switching strategy are introduced, so that the CBAA can effectively exclude action strategies of the unconnected individuals, and the search efficiency and the coverage efficiency of the unmanned aerial vehicle cluster are effectively improved on the premise of ensuring global connectivity by releasing action spaces of decision lagging individuals.

The invention relates to the technical field of target search, in particular to a Bayesian-based multi-AUV (Autonomous Underwater Vehicle) collaborative dynamic target search method, which comprises the following steps of: establishing a target motion model; establishing a detection model of a single searcher; according to a target motion model, a detection model of a single searcher and a decision model of a target confidence construction cluster, expanding the search of the single searcher to a plurality of searchers, namely a searcher cluster; solving an optimal action sequence in the process of searching the dynamic target by the searcher cluster through a maximum discount time income algorithm; and when the distance between the searcher cluster and the dynamic target is smaller than the maximum detection range of the sensor, detecting the target. According to the method, the search behavior is decided based on the perception of the cluster to the environment, and the tracking and estimation of the motion state of the target are synchronously realized in the process of searching the target.

The present application relates to the technical field of photovoltaic power station digital modeling, and more particularly to a photovoltaic string reverse modeling method based on laser point cloud and geometric feature extraction, comprising: collecting high-precision three-dimensional laser point cloud data of a photovoltaic power station, using a deep learning model to perform instance segmentation on the point cloud data, accurately extracting photovoltaic strings and establishing a unique index, identifying the geometric features and contour point set of the photovoltaic strings through vertex extraction, distance-based cluster search and angle-based contour detection methods, calculating the inclination and direction angle of the photovoltaic strings using an interpolation fitting method, calculating the center position of the photovoltaic strings using the contour point set, detecting and calculating the area of the photovoltaic panel shielding or damage using a sliding window method, and finally completing the reverse modeling of the photovoltaic power station. This method significantly improves the anti-interference capability and modeling accuracy of data acquisition, reduces the consumption of computing resources, and is suitable for intelligent management and operation of large-scale photovoltaic power stations under various environmental conditions.

The application discloses a ruled surface and plane approximation method of NURBS surface, comprising: carrying out equal parameter line discretization and surface slicing pretreatment on a target NURBS surface; adopting a straight line cluster search technology based on principal component analysis method to obtain an initial straight line cluster approximating the NURBS surface; utilizing the initial straight line cluster to construct an initial ruled surface, and carrying out overall optimization on the initial ruled surface based on a least square method to obtain one or a group of ruled surfaces meeting the approximation error requirement. The application converts a complex NURBS surface into one or a group of ruled surfaces through three steps of pretreatment, straight line cluster search and overall optimization, and is suitable for efficient rough machining and tool path planning.

The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a method for allocating unmanned aerial vehicle cluster search and rescue tasks based on discrete particle swarms. The method comprises: determining the legal clusters and legal tasks at the current time t and generating multiple task pairs according to the life cycle of the task and the task execution capability of the cluster. The task value of the task pair is calculated according to a preset task value function, and a task value matrix is ​​generated; random particles are generated based on a random particle model, and the random particles are genetically mutated according to the local optimal particles and / or the global optimal particles to obtain the optimal random particles; the optimal random particles are optimized based on the task value matrix to determine the local optimal particles; multiple local optimal particles are optimized to determine the global optimal particles with the maximum sum of task values ​​and the minimum variance between task values; after a preset number of cycles, the global optimal particles are decoded to obtain multiple optimal task pairs, and a task allocation scheme is generated, so as to achieve high adaptability and high completion rate of task allocation.

The invention relates to the technical field of digital modeling of photovoltaic stations, in particular to a photovoltaic string reverse modeling method based on laser point cloud and geometric feature extraction, which comprises the following steps: collecting high-precision three-dimensional laser point cloud data of a photovoltaic station, performing instance segmentation on the point cloud data by using a deep learning model, and obtaining a photovoltaic string reverse modeling result; the method comprises the following steps: accurately extracting a photovoltaic string, establishing a unique index, identifying geometric features and a contour point set of the photovoltaic string through vertex extraction, distance-based cluster search and an angle-based contour detection method, calculating an inclination angle and a direction angle of the photovoltaic string by using an interpolation fitting method, and calculating a central position of the photovoltaic string by using the contour point set. And carrying out detection and area calculation on the shielding or damage condition of the photovoltaic panel by adopting a sliding pane method, and finally finishing reverse modeling of the photovoltaic station. According to the method, the anti-interference capability and the modeling precision of data acquisition are remarkably improved, the consumption of computing resources is reduced, and the method is suitable for intelligent management and operation and maintenance of a large-scale photovoltaic field station under various environmental conditions.

The invention discloses a three-dimensional track reconstruction method and device for muon imaging, and relates to the field of signal detection and ray imaging, and the method comprises the steps: obtaining an original waveform signal of muon imaging, and carrying out the preprocessing of the original waveform signal; performing channel waveform analysis on the preprocessed original waveform signal by adopting a waveform identification technology to obtain a channel waveform analysis result; in combination with a detector-electronics channel mapping table, decoding continuous channel information by utilizing hit continuity characteristic channel clustering; on the basis of the continuous channel information, utilizing a spatial point clustering algorithm to take spatially adjacent electronic signals in the continuous clusters as the same electronic cloud cluster; and based on the three-dimensional barycentric coordinates of the plurality of electronic clouds, completing three-dimensional track reconstruction by using a screening reconstruction algorithm. According to the method, the problem of fuzzy reconstruction of a small-angle incident muon example is solved through channel waveform analysis, hit cluster searching and three-dimensional track reconstruction.

The application discloses an optimal flyby sequence acquisition method based on a parallel architecture and belongs to the field of orbit design and optimization. The application realizes the method as follows: a parallel cluster search algorithm is constructed, and a Lambert problem is solved in parallel; a state of a spacecraft at a starting moment of a task time window is determined, a parallel cluster search is performed to obtain a sub-sequence of target access; then, the sub-sequence is saved to a database, a state and a moment at an end of each sub-sequence in the database are extracted, and the parallel cluster search is performed again from the state; the above process is repeatedly iterated to generate a sub-sequence database; the sub-sequences are spliced to generate a complete target access flyby sequence trajectory; and the total speed increment of the flyby sequence is further reduced by adjusting a transfer time between targets and optimizing a flyby speed. The application can significantly improve flyby sequence planning efficiency, effectively guarantee the optimality of sequence generation for a large-scale target problem, and acquire a high-precision and low-energy-consumption spacecraft flyby sequence.

The invention relates to the field of data processing, and relates to an e-commerce landing page intelligent generation method and system, and the method comprises the steps: obtaining a uniform resource locator of a target commodity, and collecting the multi-modal data of the target commodity based on the uniform resource locator; performing feature extraction on the multi-modal data to obtain structured style feature data including a visual feature vector and a semantic feature vector; a design space generated by the landing page is constructed, the design space is modeled into a directed graph structure, nodes represent page component modules, and edges represent connection relations between adjacent component modules; and performing path search in the directed graph structure by using a cluster search algorithm to obtain an optimal design scheme, and generating a target e-commerce landing page based on the optimal design scheme. By means of the method, the efficiency and quality of landing page generation can be effectively improved.

The invention provides a vector search system for a vector database. A cluster search module and a vector search module receive query vectors input by an application; data transmission is carried out between the cluster search module and the vector capture module, the cluster search module is used for realizing cluster sampling calculation of the FPGA hardware processor, and the vector capture module is used for realizing end-to-end access of the FPGA hardware processor; data transmission is carried out between the vector search module and the global retrieval module, the vector search module is used for realizing vector search calculation of the FPGA hardware processor, and the global retrieval module is used for realizing sorting calculation of the FPGA hardware processor; and the software runtime module is used for assisting the vector capturing module to realize end-to-end access. The end-to-end approximate nearest neighbor search speed of the system is 1.41-171.28 times faster than that of an existing system, and meanwhile, more than 90% of CPU computing resources are saved.

The invention discloses a multi-user-oriented soft resource online process collaborative service method and system, and belongs to the technical field of multi-user collaboration. The method specifically comprises the steps that multiple users send access requests to a system, and the access requests are transferred to an application layer through firewall filtering, reverse proxy server distribution and gateway node analysis processing; performing cluster search of the business application through the search cluster, operating on a business application page according to request content, caching the business application page in a distributed database, and sending a business application request; the method comprises the following steps: performing cluster search of business service on a service layer through a search cluster, caching the business service in a distributed database, sending a business service request, calling a data access layer, and returning a calling result to a user, thereby realizing multi-user-oriented soft resource online process collaborative service. According to the invention, service collaboration in a multi-user environment is displayed, and the service quality of the system is improved through efficient distributed collaboration and resource optimization.

The present invention relates to the field of biopharmaceutical technology, and discloses a method, device, computing device and storage medium for messenger ribonucleic acid sequence design. Based on a given 5' UTR sequence as the starting input, the method adds new codons one by one using the growth method, and calculates and scores the full-length minimum free energy and codon usage efficiency of the overall sequence for sorting. The elimination method is used to exclude sequences containing restriction enzyme sites / undesirable properties / or poor scores, and then the clustering search method is used to select representative sequences to increase diversity, and finally the sequences are obtained for recommended synthesis. The present invention proposes an mRNA sequence optimization design method in the environment of 5' UTR and 3' UTR, taking into account the full-length minimum free energy of the mRNA sequence and the codon usage efficiency of the CDS region, which can optimize these two objectives simultaneously, can optimize its stability from the perspective of the overall molecule, and at the same time optimize the expressibility of the CDS region, ensuring the stability and expressibility of the mRNA sequence.

The application provides an AI image recognition front-end code generation method and system and a computer storage medium. The generation method includes three main steps of image recognition, layout analysis and code generation. The original webpage prototype and its configuration information are processed by a convolutional neural network, an optical character recognition technology and a target detection algorithm to extract interface elements and determine the hierarchical structure. Then, attribute information extraction and rendering tree generation are performed. Finally, data tokenization processing is performed to map into HTML, CSS or JavaScript code, and a greedy search or clustering search strategy is flexibly selected according to user requirements to generate the final front-end code. The system supports multiple front-end frameworks, ensures efficient and accurate code generation, and allows user interaction to enhance the individuality and adaptability of code generation. The application relates to the field of artificial intelligence technology.

The invention provides an unmanned aerial vehicle cluster distributed hybrid collaborative search method and system. The method comprises the following steps: judging a search stage of an unmanned aerial vehicle cluster search task; in the dispersed search stage, each unmanned aerial vehicle is responsible for searching a sub-region; correcting the information graph; performing single machine decision-making to obtain an optimal decision-making path; in the cluster collaborative search stage, all the unmanned aerial vehicles search the task area together; forming one or more connected subnets by the unmanned aerial vehicle cluster according to the communication range of the unmanned aerial vehicles; information graph correction is carried out based on the Bayesian criterion; evaluating the cognitive error level of each unmanned aerial vehicle; performing information fusion in the connected subnet by considering a cognitive error level; each unmanned aerial vehicle generates a pre-decision path through single-machine decision in advance; the unmanned aerial vehicles in the subnet perform cluster coordination decision making to obtain an optimal decision path of each unmanned aerial vehicle; according to the rolling planning architecture, each unmanned aerial vehicle executes one step according to the optimal decision path of the unmanned aerial vehicle and then enters the next planning step.