25 results about "Search problem" patented technology

The invention provides an interactive command line tool-oriented intelligent task planning and execution method and system, and the method comprises the steps: S1, generating a corresponding command sequence template for each operation of a target tool through a first large language model, and constructing an executable knowledge base; s2, calculating the semantic similarity between the task description and each command sequence template to obtain a candidate set, and selecting the most relevant template as a retrieval context by using a second large language model; s3, modeling a task execution process as a state diagram search problem, selecting candidate nodes from reachable nodes of a current node based on an algorithm, and selecting an optimal node according to a current state and a retrieval context by utilizing a second large language model; s4, executing an execution action corresponding to the optimal node, and analyzing tool output by using a second large language model to adjust a heuristic value of the corresponding node and execute a corresponding rollback strategy; and S5, repeating the steps S3 to S4 until the reasoning result shows that the task reaches the target node or the number of attempts exceeds a preset threshold.

The invention provides a cue word processing method and device, equipment and a storage medium, and relates to the field of artificial intelligence, in particular to the fields of large models, big data, intelligent search and the like. According to the specific implementation scheme, multiple pieces of sample data are obtained, wherein the sample data comprise search problems belonging to a target field and target categories of the search problems; based on the multiple pieces of sample data, determining classification standard information conforming to each preset category in the target field; based on the plurality of candidate categories of each search question and the classification standard information of the candidate categories, splicing to obtain an initial cue word of each search question; the initial prompt word is used for indicating a category which the search problem conforms to is determined from a plurality of candidate categories; the plurality of candidate categories are at least partial categories in a plurality of preset categories; detecting the initial cue word of each search question to obtain a total detection result which is used for evaluating the cue effect of the initial cue word of each search question so as to adjust the initial cue word based on the total detection result.

The invention relates to the technical field of artificial intelligence, in particular to an extensible deep neural network channel pruning method and system. According to the method, a channel pruning problem is converted into a structure search problem, and an artificial bee colony algorithm is provided to find an optimal pruning structure. A coupled model structure is mapped into a non-coupled search structure through structure mapping, and an optimal pruning structure is searched and fine-tuned based on an artificial bee colony algorithm, so that the search space of the deep neural network is reduced, and the pruning problem of the coupled structure is solved.

The application discloses a two-dimensional full coverage path planning method for a mobile robot and related equipment, and belongs to the technical field of robot full coverage path planning. In a complex two-dimensional environment model, for example, a two-dimensional map in which irregular obstacles and concave-convex polygon obstacles exist, firstly, Maklink lines generated by Maklink graph theory can effectively divide the map into multiple sub-regions, which is helpful to simplify the path search problem and improve the search efficiency; then, the order in which the robot visits each sub-region is calculated, and the optimal path for the robot to switch between each sub-region is calculated; finally, the Boustrophedon path is used for "bow" shape traversal, which can ensure that the robot efficiently covers the entire sub-region, reduces the possibility of omission and repeated cleaning, and moves between sub-regions according to the optimal switching path and the visiting order, which is helpful to reduce the repeated path and invalid movement of the robot when traversing the sub-region.

The application provides an intelligent task planning and execution method and system for an interactive command line tool, comprising the following steps: S1, using a first large language model to generate a corresponding command sequence template for each operation of the target tool, and constructing an executable knowledge base; S2, calculating the semantic similarity between the task description and each command sequence template to obtain a candidate set, and using a second large language model to select the most relevant template as a retrieval context; S3, modeling the task execution process as a state graph search problem, selecting a candidate node from the reachable nodes of the current node based on an algorithm, and using the second large language model to select the optimal node according to the current state and the retrieval context; S4, executing the execution action corresponding to the optimal node, using the second large language model to parse the tool output, adjusting the heuristic value of the corresponding node and executing the corresponding rollback strategy; and S5, repeating steps S3 to S4 until the reasoning result shows that the task reaches the target node or the number of attempts exceeds the preset threshold.

The application discloses a control law automatic design method based on a long short-term memory network. The method draws on the experience of network architecture search method in deep learning, utilizes the advantage of a recurrent neural network in time sequence correlation exploration, converts a control law structure design problem into a directed acyclic graph topological relation automatic search problem, realizes automatic generation of a flight control law control structure, and realizes automatic setting of parameters under a given control law structure based on a genetic algorithm. The method aims at overcoming the limitation that current control law automatic optimization can only utilize a heuristic algorithm to automatically set controller parameters for a known controller structure, reducing the artificial design workload, and improving the control effect under complex design input conditions.

A neural network channel number searching method and device can realize a differentiable search technology to search network channel numbers, reduce the calculation complexity of the network while ensuring the network performance. The method comprises the following steps: determining the output channel number N of a convolutional layer, wherein N is a positive integer (S301); dividing the feature tensor output by the convolutional layer into n sub-feature tensors, wherein the channel number of each sub-feature tensor is N / n, n is an integer that can be divided by N, and n is greater than or equal to 2 (S302); determining n sets of weighting coefficients, wherein each set of weighting coefficients comprises a plurality of weighting coefficients, and the plurality of weighting coefficients correspond to a plurality of sub-feature tensors in the n sub-feature tensors one by one (S303); determining the sub-feature tensor corresponding to the maximum value in each set of weighting coefficients (S304) to obtain the sub-feature tensors corresponding to the n maximum values; and re-determining the output channel number of the convolutional layer according to the sub-feature tensors corresponding to the n maximum values (S305).

Technical ProblemTo provide a time efficient Neural Architecture Search for the Backbone block of Computer Vision task.Solution to ProblemA neural architecture searching apparatus comprises building means (11) to build a supernetwork, wherein a target layer of the supernetwork to be optimized is replaced by a plurality of candidate layers, and the supernetwork comprises a plurality of fully-connected layers; training means (12) to train the supernetwork, wherein the plurality of candidate layers are trained part by part, and the plurality of fully-connected layers are trained correspondingly to the part of the plurality of candidate layers; and selecting means (13) to evaluate the trained supernetwork and select a part of the plurality of candidate layers which corresponds to the best performing part of the plurality of fully-connected layers.

The present invention discloses a method for automatic wiring and optimization of superconducting quantum chips, belonging to the field of automated design of superconducting quantum chips. In the modeling phase, the method adopts a "combined wiring template" model under a fine-grained grid. The combined wiring template is used to discretize the problem, avoiding the complex geometric operations in the arc wiring problem solution process and significantly reducing the algorithm's search space. In the legal solution search phase, a one-sided wiring algorithm is adopted. Based on the wiring result characteristics of the algorithm, the line sequence search problem is extended and a line sequence tree search framework is designed. On this basis, the blocking relationship between lines is explored and a series of search optimization strategies are designed. An exchange winding action is adopted to meet the special line sequence requirements of the read line. In the wiring optimization phase, an iterative optimization wiring scheme based on space constraints is adopted. Based on the legal solution, the overall wiring result is optimized at multiple levels of objectives to ensure that the wiring result meets the design requirements.

The invention discloses a graph indexing method oriented to maximum inner product vector retrieval, which utilizes query vector scaling to prove that a maximum inner product search problem can be equivalently converted into a nearest neighbor search problem, so that an efficient Euclidean graph indexing structure is reused on the premise that a vector space does not need to be changed; according to the method, a graph structure based on a spherical path is constructed, a cross-norm connecting edge is introduced on the basis of a traditional sparse graph to relieve norm bias, and a normalized clustering and high norm screening strategy is adopted to generate an entry point to improve search coverage. Meanwhile, the invention provides a self-adaptive termination mechanism based on search process features, and whether the search is ended in advance is judged through a lightweight decision tree model, so that the search overhead is effectively reduced. Experiments show that the retrieval efficiency is remarkably improved on the premise of ensuring the accuracy, and the method is suitable for high-performance vector retrieval scenes such as recommendation systems and e-commerce search.

The embodiment of the invention discloses a shopping guide method and device based on artificial intelligence, electronic equipment and a storage medium, belongs to the technical field of artificial intelligence, and solves the problem of insufficient shopping guide personalization. Comprising the steps of obtaining a search question which is input by a user and is related to a target commodity, obtaining user preference information of the user in preset multiple dimensions, and generating a user preference feature vector based on the user preference information in each dimension; performing serialized splicing processing on the search question and the user preference feature vector to obtain target data, and inputting the target data into a trained large language model; and based on the trained large language model, outputting a target shopping guide answer of the search question, so as to determine a target commodity based on the target shopping guide answer.

The invention discloses a classifier-assisted neural network architecture search multi-target multi-level learning optimization method, which comprises the following steps of: modeling by taking a neural network architecture search problem as a multi-target optimization problem, and constructing a search space; constructing a test network for training; screening a Pareto optimal solution through non-dominated sorting, and constructing a special search space based on a Pareto leading edge reserved operator; performing a classifier-assisted hierarchical learning-based multi-objective evolutionary optimization algorithm, selecting an updated population after evolution based on a candidate solution screening strategy, performing objective function evaluation based on a screened solution, updating an archive library, outputting a Pareto optimal solution in the archive library after iterative training, and performing multi-objective evolutionary optimization on the basis of the Pareto optimal solution in the archive library. And selecting a network in the optimal Pareto frontier of the last generation of population as an optimal neural network architecture. According to the method, efficient search of the neural network architecture is realized through the classifier-assisted hierarchical particle swarm optimization algorithm, and a solution meeting the double targets of classification accuracy and reasoning delay is obtained.

The invention provides a graph reasoning task-oriented topology enhancement prompting method, and belongs to the technical field of artificial intelligence natural language processing. The method comprises the following steps: S1, inputting graph data, and constructing basic prompt information and question information of a graph reasoning task; s2, node attribute enhancement prompt information is constructed according to the node degree attribute information of the graph data; s3, constructing path connection enhancement prompt information according to the path connection of the graph data; s4, splicing the basic prompt information, the node attribute enhancement prompt information, the path connection enhancement prompt information and the question information of the graph reasoning task in sequence to obtain topology enhancement prompt information; and S5, inputting the topology enhancement prompt information into the large language model API to generate a topology enhancement prompt response, namely obtaining a graph reasoning result. According to the method, the blind search problem caused by information loss of LLMs in graph reasoning is effectively solved, and the deep understanding and reasoning ability of a large language model to a graph structure is improved.

The present application relates to the technical field of electric digital data processing. Disclosed are a large model-based enterprise-level search result optimization method and device, and a medium. The method comprises: by means of an enterprise search engine, returning a search result list consisting of a plurality of search results corresponding to a search query requested by a user; performing semantic analysis on the search query by means of a large language model, so as to obtain an answer corresponding to the search query; on the basis of the query answer, adjusting the search result list to obtain an adjusted fusion search result list; on the basis of a preset weighting calculation model, allocating corresponding search matching weightings to the fusion search result list; for each search result in the fusion search result list, acquiring user operation data fed back by the user for the search result, and, on the basis of the user operation data, calculating a user operation weighting corresponding to the search result; and, on the basis of the user operation weightings and the search matching weightings, re-adjusting the fusion search result list to obtain a target search result.

The invention provides a high-dimensional information enhancement perception method based on chain decomposition, relates to the technical field of information enhancement, considers a single-station radar system working under a millimeter wave frequency, comprises an MIMO antenna array of a uniform rectangular array at a transmitting end and a receiving end, and comprises the following steps: establishing global correlation among different dimensions of a high-order signal; establishing a conversion relation between chain decomposition and CP decomposition, and introducing a minimum description length criterion to determine a chain decomposition rank number; correcting the ray tracking simulator based on the corner reflector; expanding a simulation scene, and generating a sensing environment and a sensing echo under a calibration physical condition; constructing a Riemannian manifold structure, and optimizing statistical distribution in combination with multiple geometric metrics; a retrieval problem is converted into a geometric mean value optimization problem, and the difference between a target and interference is maximized. According to the method, the perception echo performance is enhanced from the distance-speed-angle dimensions of the target object, so that the target object is clearer, and target object detection and parameter estimation are facilitated.

Provided is an information processing device that provides support for the creation of an Isin model for solving an optimal solution search problem for a composite material provided with a mixing restriction condition by an annealing optimizer, the information processing device comprising: an input receiving unit that receives an input from the annealing optimizer; an input unit configured to receive an objective function in which characteristics of a composite material corresponding to the mixing are formulated, and input of a mixing restriction condition; and a data creation unit configured so as to create an Isin model for an optimal solution for mixing that satisfies a constraint condition formula in which a mixing constraint condition is formulated and that optimizes the solution characteristics of the annealing-type optimizer, the amount ri of the substance i being represented by bits among the substances mixed with the composite material, and the amount ri being represented by bits among the substances mixed with the composite material. The composite material is characterized in that the material i is contained in the composite material, and whether the material i is contained in the composite material is also represented as a bit, the constraint condition formula includes conditions satisfying the following formula (1) and formula (2), and the constraint condition formula is formulated so that when at least one of formula (1) and formula (2) is not satisfied, the optimal solution of the mixture is not calculated.

The invention discloses an intelligent music creation auxiliary method based on a music theory, and belongs to the technical field of music creation. According to the method, intelligent assistance of a music creation process is realized by fusing multi-modal intention input and a structured music theory rule base, a pre-constructed structured music theory rule base is utilized to dynamically map a user intention into a computable constraint parameter, and on the basis, a problem modeling technology is satisfied through constraint, so that the problem modeling efficiency is improved. A music creation problem is converted into a feasible solution space search problem in mathematics, a music fragment conforming to the intention of a user is efficiently searched in a solution space by means of a constraint propagation and backtracking algorithm, a result is output in a multi-mode form, and meanwhile interpretable feedback of the creation process is provided. By means of the method, music theoretical knowledge and user personalized requirements can be effectively integrated, the accuracy and usability of the generated result are improved, meanwhile, dependence on professional literacy of the user is reduced, and efficient and intelligent music creation assistance is achieved.

The present invention discloses a method, system and computer-readable storage medium for locating the root cause of a fault with the minimum necessary cause based on a causal graph. The method comprises the following steps: initializing parameters to configure a neural network; receiving a causal graph and a corresponding data set, dividing the data set into a test data set and a training data set, and using the test data set to initialize intervention data; using the training data set to construct and train an encoder and a decoder according to a preset method; converting the data in the test data set into masks in batches, splicing them with the test data itself and inputting them into the encoder for encoding to obtain the encoded data; splicing the encoded data with the mask calculated using the intervention data and inputting them into the decoder for a counterfactual process to obtain the counterfactual target result; using the result to calculate the minimum necessary cause of the system according to a preset method. The present invention formulates the search problem as a continuous optimization problem, encapsulates the method in a unified likelihood function, and provides an end-to-end framework for the task.

The invention discloses an NSCRO-SL-based double-cable model collaborative vibration reduction multi-objective optimization method, which mainly comprises the following steps of: carrying out finite element modeling on a double-cable model and a collaborative vibration reduction system based on a vibration reduction system consisting of VD and TMD-CT; mathematical modeling is carried out for a parameter design problem of a double-cable system, two design indexes (a dynamic characteristic index and a vibration reduction performance index) are provided, and then a non-dominated sorting algorithm (NSCRO-SL for short) suitable for multi-objective function optimization is provided on the basis of a CRO-SL algorithm. And finally, performing parameter design solution on a multi-target problem based on two design indexes in the VD and TMD-CT double-cable model parameter design process by using NSCRO-SL. According to the method, the problem of multi-objective optimization in the VD and TMD-CT-based double-cable model parameter design process is effectively solved, the performance of a multi-objective algorithm in optimization and search problems is improved by adopting multiple different matrix layers, and excellent parent parent corals are reserved by adopting an elite algorithm, so that excellent parents in previous iterations are reserved.

The invention discloses a hexagonal lattice path finding method for discrete event simulation. On the basis of a traditional A star algorithm, firstly, the operation of judging and cutting (namely pruning processing) is put forward when six nodes adjacent to a current node are cyclically traversed, and then the slope value between a reserved node and a target node is calculated; and finally, selecting the node of which the slope value is closest to the slope value between the starting node and the target node to enter the next round of path finding process. According to the method, the problem that many useless nodes are searched when a traditional heuristic A star search algorithm faces obstacles is solved, the calculation time and the storage space used for searching are reduced in the aspect of space calculation such as way finding in the field of discrete event simulation based on aviation, navigation, ground and the like, and the calculation efficiency of the A star algorithm is greatly improved; the problem of low calculation efficiency of way-finding calculation and the like in the simulation deduction process in the discrete event simulation field based on aviation, navigation, ground and the like is solved.

An adaptive robotic grasp planning technique for bin picking. Workpieces in a bin having random positions and poses will be grasped by a robot and placed in target positions and poses. The workpiece shape is analyzed to identify a plurality of robust grasp options, each grasp option having a position and orientation. The workpiece shape is also analyzed to determine a plurality of stable intermediate poses. Each individual workpiece in the bin is evaluated to identify a set of feasible grasps, and if such direct movement is possible, the workpiece is moved to the target pose. If direct movement is not possible, a search problem is formulated, with each stable intermediate pose being a node. The search problem is solved by evaluating the feasibility and optimality of each link between nodes. The feasibility of each link is evaluated in accordance with collision avoidance constraints and robot joint motion constraints.

The application discloses a kind of based on time series anomaly detection's unsupervised fast radio burst searching method, this method includes: to radio telescope observation data is dispersed and is handled to obtain signal intensity time series;Signal intensity time series is embedded into low-dimensional space and constructs graph structure, based on graph structure calculation sequence anomaly divides to obtain fast radio burst pulse signal candidate body;Using bucket counting method to the fast radio burst pulse signal candidate body is screened, confirms the arrival time of fast radio burst pulse signal and its corresponding dispersion value.The application innovatively solves the searching problem of fast radio burst from the angle of time series anomaly detection, with the characteristics of strong robustness, low false alarm rate, greatly reduces the number of candidate body, improves searching efficiency;Using coarse-grained grid dispersion, greatly reduce the consumption of computing resources;Not dependent on signal shape related prior knowledge, can be extended to detect more unknown cosmic signals.

The present application relates to the field of artificial intelligence, automatic control and robot technology, and particularly relates to an asynchronous multi-agent collaborative decision-making method and system based on probability decomposition. The present application uses a filling mechanism to align the team decision-making timeline through a generalized value function approximation (G-VFA module), and after obtaining the value of the agent team, the individual value function is obtained through probability value function decomposition; the strategy network of each agent is updated by using an asynchronous policy gradient update (A-PG module) method; at the same time, the training process integrates off-policy learning, soft update mechanism and entropy regularization enhancement technology. The present application overcomes the idle waiting problem under the synchronous framework, can more efficiently utilize the time budget; has strong robustness, can adapt to different task requirements and environmental uncertainty; at the same time, has good training ability, through the integration of enhancement technology, the stability and efficiency of the training are ensured. The present application can effectively solve the problem of efficient search of asynchronous multi-agent under time constraints.

The invention provides a password cracking method, a quantum mixing system, a storage medium and electronic equipment, and the method comprises the steps: generating target data corresponding to a key value based on the key value of a key bit of a preset key; obtaining intermediate value data generated by key encryption; performing distributed splitting on the intermediate value data serving as a search problem to obtain a plurality of sub-problems, splitting the target data based on each sub-problem to obtain a first quantum state, and performing quantum coding on each sub-problem to obtain a second quantum state and coding information; based on whether the second quantum state corresponding to each sub-problem is matched with the first quantum state, obtaining a search result of each sub-problem; the global search result is obtained based on the coding information and the search result of each sub-problem, and the key value of the key bit is obtained according to the global search result, the probability of error results is reduced through the search results of the sub-problems and the global search result, the private key corresponding to the key is obtained, and quantum hardware resource consumption of a quantum search algorithm is reduced.