173 results about "Computational problem" patented technology

The invention discloses a retrieval enhancement generation method based on token-level word embedding, and relates to the technical field of artificial intelligence and natural language processing. The method specifically comprises the following steps of: segmenting a text block, namely segmenting a document into paragraphs; enhancing the document information; the text coding is used for converting a text into a numerical vector; segmenting the problem to obtain a character array, encoding the character array, and converting the problem into a numerical vector; calculating the similarity between the problem and the text block by adopting the average maximum similarity to obtain a related text block; performing Prompt construction on the question and the related text block to obtain a prompt text; the prompt text is input into a large language model LLMs, and question answers conforming to the answer format are output; and in combination with the question answers and the related text blocks, quoting and marking the question answers to obtain answers with quotations. According to the method, a token-level text embedding method is utilized to vectorize questions and text blocks, so that the accuracy of RAG retrieval is improved, and the confidence of LLMs answers is increased.

The invention relates to a multi-knowledge-base retrieval and answer integration optimization method, a retrieval enhancement generation system, equipment and a medium, and the method comprises the steps: respectively sending questions input by a user into N knowledge bases, and converting the questions into question vectors suitable for the specific semantic space of each knowledge base by using an embedding algorithm corresponding to each knowledge base; obtaining the first M most relevant results in each knowledge base by calculating the similarity between the problem vector and the document vector of each knowledge base; integrating the results of all the knowledge bases to obtain M * N results; and reordering the merged results by adopting a Rerank algorithm, and selecting the first m results with the highest scores as final recall results. Compared with the prior art, the method has the capability of improving the information retrieval efficiency and quality, and provides better query service for the user.

The invention provides a large-scale satellite task dynamic constraint conflict resolution method and system based on heterogeneous graph learning, and the method comprises the steps: carrying out the mathematical description of a task planning problem, and designing an optimization objective function; carrying out characteristic analysis and mathematical expression on the constraint; constructing a satellite task static constraint conflict graph model for the static constraint; constructing a satellite task dynamic constraint conflict graph model for the dynamic constraint; solving the static constraint conflict graph model; solving the dynamic constraint conflict graph model to obtain a satellite task selection probability; and performing decision optimization on the satellite task to finally obtain a satellite task planning result. According to the method, efficient scheduling and allocation decision-making of the multi-satellite large-scale intensive tasks are realized, the problem of efficient calculation of constraint investigation and conflict resolution in the multi-satellite task planning process under the intensive tasks is solved, and the conflict resolution frequency in the multi-satellite task planning solving process is greatly reduced.

A method and system for solving a computational problem using a hybrid data processor comprising a classical computer and quantum computer the method comprising receiving or determining information on one or more quantum circuits defining operations of a parameterized quantum model of a target function, the target function representing an approximate solution to the computational problem, preferably one or more differential equations and one or more associated boundary conditions, the one or more quantum circuits comprising one or more quantum feature maps for encoding one or more classical input features associated with the target function into the Hilbert space of the quantum register, wherein the one or more feature maps include one or more unitary operators defining a time evolution over a Hamiltonian, preferably a generator Hamiltonian, applied to quantum elements of the quantum register, the Hamiltonian evolution being parameterized by a first set of variational parameters and the one or more classical input features; and, determining the target function based on the parameterized quantum model and a loss function associated with the computational problem, the determining including varying the first set of variational parameters to determine a set of eigenfrequencies of the Hamiltonian which is optimized for the computational problem, the set of eigenfrequencies defining quantum modes, which the parameterized quantum.

A method and system for solving a computational problem using a hybrid data processor comprising a classical computer and quantum computer the method comprising receiving or determining information on one or more quantum circuits defining operations of a parameterized quantum model of a target function, the target function representing an approximate solution to the computational problem, preferably one or more differential equations and one or more associated boundary conditions, the one or more quantum circuits comprising one or more quantum feature maps for encoding one or more classical input features associated with the target function into the Hilbert space of the quantum register, wherein the one or more feature maps include one or more unitary operators defining a time evolution over a Hamiltonian, preferably a generator Hamiltonian, applied to quantum elements of the quantum register, the Hamiltonian evolution being parameterized by a first set of variational parameters and the one or more classical input features; and, determining the target function based on the parameterized quantum model and a loss function associated with the computational problem, the determining including varying the first set of variational parameters to determine a set of eigenfrequencies of the Hamiltonian which is optimized for the computational problem, the set of eigenfrequencies defining quantum modes, which the parameterized quantum.

The invention discloses a large model reasoning ability enhancing method and system based on semantic execution, and the method comprises the steps: obtaining problem description information, adding computable guide part information, and inputting a large language model to output cue words; analyzing and outputting a problem solving step by the large language model according to the cue word; transmitting the problem solving step to a calculation container, and outputting a correct execution step; and integrating all the correct execution steps to generate a reasoning result. According to the method, the problem description input by the user is converted into the computable content, the problem solving efficiency is improved, the computable content is decomposed into a plurality of steps for solving, the feasibility of each solving method is verified through the middleware, the correct execution steps of problem solving are calculated through the semantic model and the calculation container, and the problem solving efficiency is improved. And the problem solving accuracy is improved.

An embodiment sends, at a first time, from a boundary server to a client system in response to a challenge request, a challenge specifying a computational problem to be solved by the client system, the boundary server specified in a challenge list sent to the client system. An embodiment receives, at a second time, at the boundary server, a challenge response from the client system, the challenge response comprising a solution to the computational problem. An embodiment generates, at the boundary server, a certificate encoding an elapsed time between the first time and the second time, the certificate usable by the client system to prove a location of the client system. An embodiment sends, from the boundary server to the client system, the certificate.

A method of performing a quantum computation includes providing a quantum system comprising constituents; encoding a computational problem into a problem Hamiltonian of the quantum system; determining a constraint Hamiltonian of the quantum system; the constraint Hamiltonian a sum of summand constraint Hamiltonians; a ground state of a total Hamiltonian encodes a solution to the computational problem, the total Hamiltonian includes a sum of the problem Hamiltonian and the constraint Hamiltonian; determining a first subset S1 of the summand constraint Hamiltonians of the constraint Hamiltonian and a second subset S2 of the summand constraint Hamiltonians of the constraint Hamiltonian; performing N rounds of operations, wherein N≥2, each round includes preparing an initial quantum state and evolving the quantum system according to a sequence of unitary operators where the sequence includes problem-encoding unitary operators, constraint-enforcing unitary operators and unitary driver operators; and outputting a result of the quantum computation.

The invention relates to the technical field of electrical engineering, and particularly discloses a multi-section power transmission limit calculation method based on multi-target migratable reinforcement learning, and the method comprises the following steps: considering a transient power angle and voltage stability constraint, and building a reverse search model for power transmission limit calculation; decomposing a multi-section coupling quota calculation problem of the reverse search model into sub-problem models by adopting a decomposition strategy; different sub-problem models are converted into a Markov decision process, and solving is carried out in combination with a neighborhood-based parameter migration strategy and an improved DDPG algorithm; and the end-to-end output of the Pareto frontier of the multi-section coupling quota is realized by training the model. Compared with a traditional multi-target meta-heuristic algorithm, the method has the advantage of better convergence and diversity.

The invention discloses a course intelligent question-answering method and system based on retrieval enhancement generation and a large model, and the method comprises the steps: processing a to-be-answered artificial intelligence course knowledge field question, obtaining a question sequence, and obtaining a text representation vector of the question; obtaining a similarity score based on the text representation vector and the paragraph representation vector, and calculating a BM25 score between the question and the paragraph; based on the similarity score and the BM25 score, calculating to obtain a mixed score corresponding to each paragraph, and sorting the paragraphs from high to low according to the mixed scores to obtain a topN document; paragraphs in the topN document are reordered, and a topK document is obtained; and taking the topK document as the context of the question, taking the topK document and the question as input by the large language model, and outputting the answer of the question. According to the method, intelligent question answering of artificial intelligence course knowledge in the education field is realized, the learning efficiency of students is improved, and the teaching burden of teaching assistance of teachers is reduced.

The invention relates to the technical field of radio communication, and discloses an XL-RIS-assisted near-field multi-beam design method and system, and the method comprises the steps: constructing an XL-RIS-assisted near-field communication multi-user receiving signal model; constructing a near-field multi-beam optimization model; the near-field multi-beam optimization model is solved, so that an XL-RIS beam reflection matrix can be obtained; and iteratively solving the near-field multi-beam optimization model to obtain a reflection matrix of a base station transmitting signal to the XL-RIS, and completing XL-RIS assisted system multi-beam optimization. Compared with the existing calculation, the beam optimization method provided by the invention does not need a complicated calculation problem, overcomes the problems of low convergence speed and high calculation complexity in large-scale array processing of the traditional method, and improves the optimization efficiency. The operation speed can be increased under the condition that the system performance is guaranteed.

The invention relates to the technical field of large-scale language models, and discloses a method for converting a natural language to an SQL (Structured Query Language) task by combining fine tuning and Prompt. According to the method, the database mode knowledge learning module is constructed, so that the database mode can be efficiently understood and memorized, the length of input tokens is remarkably reduced, and the token efficiency is improved. Meanwhile, the module utilizes a LoRA model to carry out fine adjustment on a large language model, the performance of the model on text-to-SQL tasks is optimized, and the model can generate SQL statements more accurately; besides, an example selection module is also constructed, and the most similar example is selected as a prompt by calculating the similarity between the problem and the candidate example, so that the accuracy of generating the SQL statement by the model is further improved. According to the method, the generalization ability of the model is improved, and the model can more flexibly cope with natural language queries in different fields.

The invention discloses a ChatGPT-python programming method, particularly relates to the field of artificial intelligence, and comprises three steps of problem definition, algorithm design and code implementation. According to the method, project situations are described in detail through question definition, and ChatGPT is guided to generate project schematic diagrams; through a design algorithm, a calculation problem is elaborated, and ChatGPT is required to provide an effective solution; by implementing codes, generating a feasible programming solution according to a calculation theory, providing intelligent suggestions in each process, ensuring theoretical accuracy and engineering feasibility of a result through manual examination, and comparing by taking three-dimensional slope stability analysis as a case and combining with a calculation result of commercial software, a calculation result of the three-dimensional slope stability analysis is obtained. It is verified that the Python algorithm obtained through ChatGPT programming has good calculation precision, an innovative auxiliary means is provided for engineering calculation, and the huge application prospect of artificial intelligence in the field of civil engineering is shown.

The invention belongs to the technical field of electric power automation, and discloses a DTS intelligent interaction method and system fusing a large language model and a vector database, and the method comprises the steps: obtaining the text data of an electric power regulation and dispatcher training simulation system DTS field, and constructing a semantic vector knowledge base; based on the constructed semantic vector space mapping and knowledge base, performing problem reconstruction representation on the proposed problem, and then converting the problem reconstruction representation into a vector through an embedded network; retrieving in the constructed semantic vector knowledge base based on the converted vector, calculating the comprehensive similarity between the problem vector and the vector in the knowledge base, and retrieving the most relevant knowledge fragment; and driving a large language model to generate a final intelligent question and answer response by taking the most relevant knowledge fragment and a dialogue context provided by a memory mechanism as input. Efficient, accurate and intelligent questioning and answering of complex dispatching business problems are achieved, and a new artificial intelligence interaction tool is provided for training of a digital intelligent novel power system dispatcher.

The invention discloses a processing method and device for big language model problem prompting and a medium, and relates to the technical field of natural language processing. The method comprises the steps of obtaining an original text, extracting an entity of the original text, and extracting a logical relationship according to the entity, the logical relationship including a causal relationship and an employment relationship; performing question reconstruction according to the entity and the logical relationship, and generating a redescribed question prompt; based on the question prompts, calculating semantic similarity and task types of the question prompts and preset vocabularies by adopting a self-adaptive random replacement strategy, dynamically selecting a replacement mechanism, and generating a plurality of candidate prompts; and calculating global entropy values of the candidate prompts, performing multi-source knowledge base verification on the candidate prompt with the minimum global entropy value, and outputting the minimum candidate prompt under the condition that the verification is passed. By means of the method, the generation process of optimizing the large language model when the error precondition or the fuzzy problem is processed is achieved, and therefore illusion output is effectively reduced.

The invention particularly relates to a cache, migration and unloading collaborative optimization method in a satellite-assisted ocean network, which comprises the following steps: constructing a satellite-assisted ocean network architecture, mapping task completion delay to system utility according to the satellite-assisted ocean network architecture, and constructing a target function with the purpose of maximizing the system utility under multi-dimensional constraints; converting an objective function optimization problem into a partially observable Markov decision process; and solving an objective function optimization problem based on attention-enhanced multi-agent reinforcement learning to obtain an optimal solution. According to the method, the problem of low-delay and efficient task calculation under the satellite-assisted ocean network architecture is solved.

Aspects of the present disclosure are directed to fabrication methods for analogue quantum systems (AQSs). Further aspects of the present disclosure are directed to methods for solving computational problems using an AQS. Methods for fabricating an AQS include generating a Hamiltonian based on a computational problem, which may be an optimization problem or a simulation problem. Further, the method includes identifying AQS fabrication parameters based on one or more identified measurement methods and the Hamiltonian. Lastly, an AQS can be fabricated based on the identified fabrication parameters. An AQS may be used inter alia to simulate a battery or interfaces.

The invention discloses a GPU parallel solving method and system for linear equations of a power system, and relates to the field of power system automation. In order to solve the defects that an existing GPU parallel solving method for the system of linear equations of the power system has an overlapping calculation problem and is low in calculation result accuracy and low in parallel load flow calculation execution efficiency, an initial node is defined in all nodes of the power system, other nodes are divided into different hierarchies according to the distance between the other nodes and the initial node, and the calculation efficiency is improved. Establishing a sparse decomposition thread tree; child nodes with the same father node in the same hierarchy are called as brother nodes, and a brother node set is established; threads are distributed in the GPU according to the brother node set; and sparse matrix parallel solving calculation is carried out on each node of the same level. The method is mainly used for optimizing the GPU parallel solution of the system of linear equations of the power system.

The invention discloses an intelligent agricultural intelligent monitoring system and method based on big data, relates to the technical field of agricultural intelligent monitoring, and aims at the core defect of a terrace monitoring scene, through curvature analysis and a microclimate attenuation model, the monitoring of a physically unreachable area is converted into a computable problem of a digital twin space, and the real-time monitoring of the terrace monitoring scene is realized. The sensor deployment requirements of abrupt slopes and ridges are obviously reduced; the terrain continuity coefficient accurately depicts the integrity of the stepped structure, and the humidity gradient quantifies the environment propagation rule of the adjacent plots, so that the virtual sensor network can dynamically generate blind area soil moisture content data, and the terrain adaptability defect of an OODA closed loop is overcome; besides, physical nodes and virtual nodes are integrated by adopting a heterogeneous topological graph, effective neighborhood information is dynamically screened by a graph attention mechanism through spatial attenuation and microclimate similarity, and strong dependence of traditional federal learning on data homogenization is avoided.

The invention relates to the technical field of geographic information analysis, and discloses a rapid space-time road network K function graph generation method and system based on a range tree and a prefix counting array, a terminal and a storage medium, and the method comprises the following steps: aiming at the calculation problem of a single space-time road network K function and the calculation problem of generating the space-time road network K function graph; the problems are solved through data structures of a range tree and a prefix counting array, different methods are selected according to the structure of each edge, and the selected structures are used for calculating the space-time road network K function of multiple thresholds. According to the method, different data structures are selected for calculation according to different calculation problems, and the time complexity is remarkably reduced under the condition that the space complexity and the precision are not changed.

The invention belongs to the technical field of artificial intelligence, and particularly discloses a deep neural network accelerator based on in-memory calculation and an acceleration method thereof. According to the application, the universal processor is used to determine the output data of the deep neural network in the forward propagation process for the to-be-solved problem, and the in-memory calculation module is used to determine the first gradient parameter of the first weight parameter of each network layer according to the first error information between the output data and the expected output; and the general processor updates the first weight parameter according to the first gradient parameter, so that the method does not depend on the network model type of the deep neural network, accelerates the pre-training process of the deep neural network, and improves the training efficiency of the deep neural network. Meanwhile, the deep neural network can be widely applied to solving of scientific calculation problems, such as solving of linear / nonlinear equation sets, solving of curve least square fitting problems and solving of steady-state partial differential equations, so that the deep neural network accelerator has certain universality.

The invention provides a management, modeling and simulation method and system for heterogeneous computing task scheduling, and the method comprises the steps: generating a global logic task identifier set according to the input parameters of a computing problem, and dividing the set into a plurality of logic task blocks based on the internal attributes of logic task identifiers; mapping each logic task block into an atomic computing unit, and packaging a computing attribute for each atomic computing unit; based on a preset screening rule and the resource constraint information, the atomic computing units are recombined, and schedulable task instances are formed; and allocating the schedulable task instances to the computing resources for execution, and monitoring performance data of the execution to update the quantifiable computing attributes of the atomic computing units by using the performance data. According to the method, the problems that the utilization efficiency of heterogeneous computing resources is low and simulation prediction is distorted due to the fact that a traditional task scheduling scheme lacks a quantifiable task abstraction and dynamic recombination mechanism across hardware platforms are solved.

An embodiment sends, at a first time, from a boundary server to a client system in response to a challenge request, a challenge specifying a computational problem to be solved by the client system, the boundary server specified in a challenge list sent to the client system. An embodiment receives, at a second time, at the boundary server, a challenge response from the client system, the challenge response comprising a solution to the computational problem. An embodiment generates, at the boundary server, a certificate encoding an elapsed time between the first time and the second time, the certificate usable by the client system to prove a location of the client system. An embodiment sends, from the boundary server to the client system, the certificate.

The invention belongs to the technical field of large model application, and relates to an enterprise technology demand prediction method and system based on large model driving, and the method comprises four parts: enterprise problem deep analysis, problem technology essence identification, technology knowledge base intelligent retrieval and multi-granularity technology demand prediction. In the deep analysis of enterprise problems, the problem description is subjected to structured processing, an entity relationship graph is constructed, and domain knowledge is aligned. The problem technology essence identification utilizes large model semantic understanding to analyze core challenges, and classifies technical problems through a multi-label classification model. And the technical knowledge base intelligently retrieves and calculates the similarity between the problem semantic vector and the knowledge graph, fuses multi-source data expansion, and screens candidate technologies according to the technology maturity. And performing multi-granularity technology demand prediction analysis on the core technology field and the subdivision direction to form a multi-level demand result. According to the invention, through systematic analysis and intelligent prediction, enterprise technology demands are accurately identified, and the method is suitable for scenes such as industry-university-research cooperation, technology transfer and innovative resource configuration.

The invention discloses a closed region identification method of a plane multi-connected domain, and belongs to the technical field of automatic search of closed regions. According to the method, the inclusion relation of the closed areas does not need to be judged, all the closed areas can be searched out directly and concisely through traversal of the edges in the two directions, and the enclosing points of the closed areas are sequentially output in the anticlockwise direction. The problem of tedious calculation caused by the fact that closed areas contained in layers need to be additionally recognized in the prior art is solved. In practical engineering application, the preprocessing steps are more concise, and the recognition efficiency and precision are improved at the same time.

Provided in the present application are a quantum circuit construction method and apparatus, and a device, a storage medium and a product. The method comprises: preparing, on the basis of a modulus N, a first quantum register that comprises 2n first quantum bits and a second quantum register that comprises n first quantum bits, n being the binary expansion length of the modulus N; obtaining an equal-probability quantum superposition state of the first quantum register by constructing a Hadamard gate; constructing a first modular multiplication module and 2n-1 second modular multiplication modules on the second quantum register; sequentially using a plurality of first quantum bits as control bits, sequentially using the first modular multiplication module and the 2n-1 second modular multiplication modules as controlled parties, and constructing 2n controlled unitary gates; and performing inverse Fourier transformation and measurement on the first quantum register to obtain a phase estimation result corresponding to a modular function period r. The solution of the present application provides support for solving the problem of larger-scale computation.

The invention belongs to the technical field of intelligent question answering, and particularly relates to a table question answering method, a question answering system and a storage medium. The table question and answer method comprises the following steps: judging whether an imported file is a table or not, if so, generating a table abstract and judging a table type, and otherwise, outputting'format non-support '; after a first decision big model is used for judging the table type, the current table is converted into corresponding intermediate data according to the table type to be stored; calculating the similarity between the question and each table abstract, and obtaining intermediate data of a table of which the similarity with the current question is greater than a first threshold value to form a related data set; using a large language model to obtain corresponding table answers based on intermediate data in the related data set, and forming an answer set; and the question and answer model integrates the answers in the answer set based on the current question and then outputs a corresponding query result. The method and the device can adapt to various forms, and improve the accuracy of answer expansion based on the forms.

One or more systems, devices, computer program products and / or computer-implemented methods of use provided herein relate to an intelligent and automated system to solve quantum computing related problems. The computer-implemented system can comprise a memory that can store computer-executable components. The computer-implemented system can further comprise a processor that can execute the computer-executable components stored in the memory, wherein the computer-executable components can comprise a recommendation component that can employ a machine learning model to generate, based on an input, a recommendation comprising a combination of entities comprising, one or more quantum circuits, one or more algorithms, one or more quantum hardware units, one or more error mitigation or error correction techniques, and one or more quantum procedures, to solve a defined problem comprised in the input.

The invention discloses a massive virtual power plant flexible collaboration method and system fusing mechanism knowledge, and the method comprises the steps: processing global information through Encoder and Decoder, and integrating all Agent data; each virtual power plant Agent inputs local and global integration information, the local information comprises adjustable capacity and cost, and the global information is an adjustment value. The adjustment value calculation is fused with next-day load data predicted by the front Encoder and Decoder, the value of each time period is determined based on a load center value, an adjustment threshold value is set to guide VPP actions, value functions of different time periods are defined, a capacity cost function is constructed in combination with a power market bidding result, a total value function is decomposed to each VPP according to the capacity cost function, the capacity value coefficient and the adjustment value of each VPP are determined, and the capacity value coefficient and the adjustment value of each VPP are calculated. And finally, learning a VPP adjustment strategy by using a full-connection neural network, and training an Agent by taking the minimum total peak-valley difference and total cost of the system as targets to achieve flexible collaboration of the virtual power plant. According to the method, the rewards are distributed and adjusted in real time, and centralized Critic is replaced to solve the calculation problem.

The invention relates to method (200) and computing device (101) for decomposition of one or more computational problems The method (200) comprises obtaining (201) performance information of the one or more network nodes, the performance information comprising idle time of the plurality of tasks hosted on the one or more network nodes, and resource capability of the one or more network nodes. Upon determining (204) that a threshold condition on the idle time of one or more tasks is fulfilled, determining (203) one or more re-deploying configurations for a subset of the plurality of the tasks, based on the idle time information of the plurality of tasks, and on the resource capability of the one or more network nodes; and re- deploying (205), based on one of the one or more re-deploying configurations, the tasks of the subset associated with the one of the one or more re-deploying configurations.