1092 results about "Round complexity" patented technology

The invention relates to a code generation method and system based on heterogeneous multi-agent collaboration and electronic equipment. According to the method, a special commentator agent instantiated by a heterogeneous large language model is added into a multi-agent collaboration process; according to the method, consistency and feasibility verification is carried out on a demand document given by an analyst agent by adopting a commentator agent, a modification suggestion is proposed in an early stage, deviation and problems are found in time in the early stage of a task, the cost and complexity of later correction are reduced, the robustness and reliability of codes are improved, and the method is suitable for large-scale popularization and application. And the generated result can still maintain high-level correctness under extreme conditions or specific boundary conditions. And the method has practical significance in improving software development efficiency, reducing project risks and improving the quality of an intelligent automatic solution.

The invention discloses an integer programming automatic modeling method based on a large language model, and the method comprises the steps: obtaining an integer programming problem data set, carrying out the processing through employing a data enhancement and dynamic complexity balance method, and obtaining a balance data set of multi-modal representation; processing by adopting a model architecture search and combinatorial optimization method to obtain an optimized neural network model structure; processing by adopting a dynamic sparse training and self-adaptive difficulty course learning method to obtain a model subjected to first-stage training; processing by adopting hierarchical reinforcement learning and a multi-target Pareto frontier exploration method to obtain a final model subjected to second-stage training; processing by adopting a dynamic neural symbol inference method to obtain an integer programming model with enhanced logic consistency; and processing by adopting a self-adaptive antagonism test generation method to obtain a comprehensive evaluation result. According to the method, the modeling efficiency, accuracy and adaptability of the integer programming problem are improved.

The invention relates to the technical field of artificial intelligence and natural language processing, in particular to a key value cache compression and sparse attention calculation method and system for large language model reasoning, and the method comprises the steps: an offline calibration stage; the online reasoning stage comprises the following steps: a pre-filling step; an autoregression generation step: for each newly generated lexical element, projecting a current query vector Q and a key vector K in a key cache to a low-dimensional space to obtain Q'and K '; calculating an approximate attention score based on Q'and K ', and selecting an index I of the first k most relevant lexical elements which are ranked from high to low; and calculating an accurate attention score based on Q and K [I], and calculating with the value vector V [I] to obtain the output of the current lexical element. According to the scheme, the memory and calculation bottleneck of large model reasoning in a scene of long text sequence input are solved, and the method has the advantages of reducing video memory occupation and calculation complexity at the same time.

The invention discloses a process automation execution method based on a large language model, and belongs to the technical field of artificial intelligence and process automation. User intention is analyzed through multi-modal input, and a structured task definition is constructed; the semantic reasoning layer is used for performing task layering, complexity evaluation and sorting optimization; the task execution layer completes subtask scheduling and execution; and the feedback and optimization layer performs performance evaluation and model updating based on execution data to realize closed loop and continuous optimization of the process, so that the technical problems of dynamically analyzing unstructured instructions, automatically optimizing a complex task dependency relationship and adapting to business changes in real time by a process automation tool are solved; according to the method, end-to-end conversion from an unstructured instruction to a structured task is realized, a subtask execution path is dynamically optimized, cross-platform tool calling is supported, the existing system integration cost of an enterprise is reduced, visual display task decomposition logic and prediction and execution time consumption comparison are provided, and the system credibility is enhanced.

A park-factory-coordinative optimized scheduling method based on a Jacobi iteration method, which belongs to the technical field of energy scheduling optimization. A park-factory hierarchical game model is established, and by means of coordination and optimization between energy scheduling under a complex production constraint and production management and control that takes profit optimization as the goal, an optimal price regulating strategy and an optimal production scheduling strategy are obtained, such that a lower industrial park energy consumption and a higher factory production profit are achieved. A coordinative optimized scheduling model for a park control center and a factory management and control center is a multi-variable multi-constraint complex optimization issue; the solution of a high-order partial differential equation set involved in the model is calculated, and a cyclic iterative optimization algorithm is designed on the basis of a Jacobi iteration matrix, thereby greatly reducing the operation complexity; moreover, such a cyclic iterative algorithm requires a smaller storage capacity of a computer, and is thus suitable to be applied in practice by an engineer.

The invention relates to the technical field of large model application, and discloses a code generation task adaptive reasoning method, device and equipment. The method comprises the following steps: obtaining a problem description of a code generation task, and converting the problem description into a pseudo code based on a large language model; according to the problem description and the corresponding pseudo code, based on a pre-trained complexity evaluation model, performing complexity evaluation on the code generation task; the complexity evaluation model is obtained through training by taking problem description and pseudo codes as input and task complexity as output; a reasoning mode is matched according to the complexity evaluation result, a set reasoning model is adopted, and a code generation task is executed based on the matched reasoning mode; wherein different complexities correspond to reasoning modes of different reasoning depths. According to the method, the dynamic perception of the large language model on the task complexity is realized, so that the reasoning depth and the resource allocation can be adaptively adjusted according to the actual demand of the task.

The invention relates to a method for obtaining a hint injection attack test case for a large language model, which combines a conditional variation auto-encoder cVAE and a Markov chain, and obtains a large language model test case through data generation and context modeling, gradual exposure of malicious instructions and simulation of multiple rounds of dialogue attacks in reality. Realizing multiple rounds of dialogue attacks on the large language model, and challenging the defense capability of the large language model; the design scheme introduces a concealment technology, role play attack, state transition and other technologies, improves the complexity and concealment of attacks, has the core advantages of automation, higher concealment, wide coverage, batch testing and the like, can evaluate the security defense capability of the large language model more truly and comprehensively, and improves the security defense capability of the large language model. The defects of an existing defense mechanism are found, and research on multi-round prompt injection attacks and improvement of a security defense mechanism are promoted.

The invention discloses a domain-specific language compiler optimization method and system based on multi-layer intermediate representation, and the method comprises the steps: S1, defining a DSL to simplify the representation and operation in an MMIR, classifying operators in the MMIR, and enabling all kinds of operators in the MMIR to correspond to keywords in the DSL; s2, analyzing the target MLIR code, extracting input, output and control flow semantics of each operation, mapping an operator in the MLIR code into a corresponding expression in a DSL (Digital Subscriber Line), and converting each optimization strategy into the DSL expression; and S3, generating a DSL code according to the DSL representation, and continuously simulating and evaluating the performance of different optimization strategies by adopting a Monte Carlo tree search algorithm to find an optimal optimization strategy so as to realize compiler optimization. The method has the advantages of being simple in implementation method, low in programming complexity, high in program performance, high in flexibility and the like.

The invention provides an SQL (Structured Query Language) generation and error correction method based on multi-stage feedback, which comprises the following steps: S1, collecting user demands, and greatly improving the accuracy of generating SQL while keeping quick response by introducing an expert thinking model and by means of a mode of demand disassembly and task gradual combination, so that the user experience is improved; and it is ensured that effective query statements can be quickly generated in the face of simple or medium-complexity tasks. Common requirements can be efficiently processed, so that the query requirements of the user can be quickly met. And secondly, aiming at a task which is complicated or has a high-precision requirement, through a multi-round interaction and error correction mechanism, the accuracy of a generated result is ensured. When the SQL execution statement is generated for the first time, if an error occurs or a user is not satisfied, multiple rounds of error correction processes can be started, the SQL execution statement is corrected step by step, and finally high-precision output meeting the requirement is achieved. Through the double-link design, the speed and the accuracy are both considered, and the requirements in different scenes are met.

The invention discloses a software development task intelligent allocation method and system based on a multi-dimensional capability portrait, and the method comprises the following steps: 1, obtaining multi-source development data generated by a developer in a development process and demand description data of a to-be-allocated software development task, and carrying out the preprocessing, and forming a structured data set; according to the method, a multi-dimensional ability portrait covering technical ability, project experience, collaboration attributes and performance is constructed, a privacy-protected distributed learning mechanism is adopted for dynamic updating, dominant and implicit requirements of tasks are analyzed in combination with natural language processing, complexity and dependency are calculated, and the performance of the performance is improved. A dynamic task feature vector corresponding to a capability feature vector dimension is constructed, and meanwhile, a self-adaptive adjustment mechanism based on real-time data monitoring and online learning is designed to form data closed-loop feedback, so that the problems of one-sided capability evaluation, staticizing task demand analysis and lack of the self-adaptive adjustment mechanism are comprehensively solved; and accurate and intelligent distribution of software development tasks is realized.

The invention provides a robot intelligent path planning method based on K-value adaptive multi-algorithm cooperation, and belongs to the field of robot path planning. The robot path planning method mainly comprises the following steps: preprocessing an environment map, and constructing a three-layer data structure of a quadtree, a Voronoi graph and a connected graph; generating an initial path based on an improved fast extension random tree algorithm, and extracting key points; establishing a K value evaluation system including five dimensions of obstacle density, local complexity, channel characteristics, path curvature and topology complexity, and realizing accurate quantification of the environment; carrying out adaptive region division based on the K value, and dividing the environment into an open region, a narrow channel region and an obstacle dense region; aiming at the characteristics of different regions, an improved bidirectional A algorithm and an improved fast expansion random tree algorithm are respectively adopted to carry out collaborative planning; and finally, smoothing the path through a Bezier curve. According to the method, the quality and the planning efficiency of path planning in a complex environment can be improved, and higher robustness is achieved.

The invention discloses a lightweight natural language processing large model training method. Comprising the following steps: obtaining processing language data; a labeled enhanced data set is obtained; a sparse mechanism of the sub-network is dynamically activated through semantic complexity, and an activation mask is obtained through calculation; generating a quantization bit width by activating the parameter sensitivity of the mask; performing cross feedback adjustment on the mixing precision quantification strategy; and evaluating the trained student model. According to the method, through dynamic sparse activation, mixing precision quantification and collaborative optimization, the core problems of static strategy stiffness, quantification precision loss, low knowledge migration efficiency and the like in large model lightweight are solved; dynamic sparse activation replaces traditional static pruning, and semantic loss is reduced; in order to realize optimized feature extraction of the enhanced data set, fusion optimization features are adopted; the mixing precision quantification effectively reduces the complexity of calculation.

The invention relates to a standardized project management and intelligent professional scheduling system, and belongs to the technical field of project management and human resource intelligent scheduling. The project standardization module is disassembled into standardization task steps through a business process association rule mining algorithm, and project complexity and resource tensity are adapted by using a task attribute dynamic weight algorithm; the archive matching module constructs professional archives, extracts feature vectors through a multi-criterion decision-weighted bipartite graph matching algorithm, and generates optimal matching pairs in combination with adaptive weight adjustment and an integer linear programming model; the dynamic scheduling module plans a task execution scheme according to a resource constraint scheduling mechanism, and realizes efficient scheduling in combination with a skill supply and demand prediction algorithm and calendar integration; and the quality optimization module adopts a deliverable anomaly detection algorithm to monitor compliance, feeds back an iterative matching and scheduling strategy through a time sequence prediction optimization algorithm, and perfects a skill map based on a map increment updating algorithm. The system realizes a project full-process closed loop.

The invention discloses a configurable flexible job shop scheduling method based on a multi-agent game model, and the method comprises the steps: mapping a scheduling problem into a dynamic disjunction graph model to describe the relation between a process and equipment, representing process nodes, equipment nodes and the mutual relation through a node set and an edge set, and combining the flexibility of a dynamic disjunction graph to obtain a flexible job shop scheduling model. And matching of equipment and processes is dynamically adjusted according to changes of production requirements, so that the equipment utilization rate is optimized. And a clustering method based on structure entropy is adopted, and process nodes are clustered into sub-graphs, so that the search space of a scheduling problem is reduced, and the calculation complexity is reduced. Construction of an order agent and an equipment agent and a game and cooperation process between the order agent and the equipment agent are covered. And each agent optimizes a decision through a deep Q network, and cooperates or competes according to a respective target. An automatic optimization configurator is used for optimizing hyper-parameters and a network structure of a deep Q network in a multi-agent system, and scheduling performance and adaptability are further improved.

Using complexity metrics to assess code generated using artificial intelligence includes generating, by an artificial intelligence (AI) language model, output source code based on input source code; identifying respective complexity scores for the input source code and the output source code using one or more complexity metrics; and generating, based on an evaluation of the respective complexity scores, a validation score for the output source code.

The invention discloses a hybrid optimization method and system assisted by incremental multi-fidelity machine learning. The method mainly comprises the steps of initial setting and initial sample acquisition, training of a global low-fidelity proxy model # imgabs0 # and a residual model # imgabs1 #, global optimization, training and optimization of a local proxy model, low-fidelity full-wave simulation, re-prediction of an updated proxy model # imgabs2 #, high-fidelity simulation and the like. According to the method, a multi-fidelity model and adaptive incremental learning are introduced in the process of training and updating the proxy model, the calculation complexity of sampling and training can be effectively reduced, meanwhile, a global multi-target and local single-target hybrid optimization algorithm is adopted in the optimization process, and the algorithm search efficiency can be improved. The method can be used in the field of optimization design of multi-target electromagnetic devices such as medium-scale antennas, arrays, filters and the like with design parameters in 20-50 dimensions.

The invention discloses an automatic business travel itinerary optimization method, and relates to the technical field of intelligent itinerary planning, and the method comprises the steps: integrating the multi-source heterogeneous data of enterprise policies, personal preferences and real-time traffic through a federated learning framework, and achieving the cross-domain knowledge sharing; the method comprises the following steps: constructing a staged optimization engine by adopting an attention mechanism to dynamically balance cost, time, comfort and sustainability targets: in the first stage, modularly disassembling a travel through sparse constraint linear programming, and quickly generating a Pareto frontier candidate set; in the secondary stage, on the basis of a multi-agent reinforcement learning framework, complex interaction is simulated through a Markov decision process, and strategy iteration is driven through a special reward function for quantifying a comfort index; in order to cope with real-time disturbance, event-driven edge computing nodes are deployed, flight delay and traffic jam emergencies are responded in real time, an incremental topology updating algorithm is triggered, and only affected sub-modules are reconstructed to reduce computing complexity. According to the invention, the bottleneck of dynamic adjustment efficiency and multi-target balance capability is solved.

The invention discloses a method and device for detecting code quality, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: acquiring a code file of which the quality is to be detected, and matching an analyzer according to attribute information of the code file; processing the code file by using a parser to obtain an abstract syntax tree; traversing the abstract syntax tree, and determining the circle complexity of the code file through a strategy of counting and judging the number of nodes; and counting the code line number of the code file, determining a quality analysis result of the code file according to one or more of the circle complexity and the code line number, and triggering an alarm in response to the condition that the quality analysis result is greater than or equal to a preset threshold value. According to the implementation mode, the abstract syntax tree aiming at the code characteristics can be generated, the code quality is systematically evaluated from multiple dimensions, and developers are helped to quickly identify complexity and potential problems in the codes, so that subsequent continuous improvement and optimization of the codes are facilitated.

The invention relates to the field of nonlinear system control, and provides a preset time reinforcement learning method and system of a continuous nonlinear system, and an electronic device, and the method comprises the steps: constructing a zero-sum game framework based on a kinetic model and a performance index of the nonlinear system; determining a value function and a Hamiltonian function based on a zero-sum game framework; applying a preset neural network model to carry out approximation on the value function, and determining an approximation error; based on the Hamiltonian function and the approximation error, an approximate optimal control strategy and a worst interference strategy are determined; constructing a Lyapunov function based on the value function and the weight error of the value function; and based on a Lyapunov function, an approximate optimal control strategy and a worst interference strategy, a reinforcement learning result is verified. The method and the device are used for overcoming the defects that convergence time cannot be dynamically adjusted, parameter complexity is high and robustness is insufficient in the prior art, and the scheme of the invention can meet dual requirements of a continuous nonlinear system on dynamic convergence and anti-interference performance.

The invention discloses a modular function extension and dynamic task scheduling service robot system, which relates to the technical field of robots, and comprises the following specific steps: step 1, task feature extraction, step 2, machine learning prediction, step 3, dynamic priority calculation, step 4, heuristic task allocation, and step 5, load balancing scheduling. And step 6, task execution and feedback, in the method, the execution time and the resource demand of the task are predicted by using a machine learning model, and an optimal task scheduling scheme is calculated by using dynamic priority calculation, heuristic task allocation and load balancing scheduling. In the first step, tasks are fragmented, then pass through calculation and then are combined, the calculation complexity can be reduced, and the algorithm operation efficiency can be improved. In the fourth step, multiple iterations are carried out after randomization operation, and the scheduling scheme is optimized step by step, so that the global optimality of the scheduling scheme is improved, and falling into a local optimal solution is avoided.

The invention belongs to the technical field of communication, and particularly relates to a multiplication active code decoding method based on an SO-ORBGRAND decoder. The SO-ORBGRAND decoder outputs soft information by calculating a correct posterior probability of a conjecture code word sequence, and high-performance decoding is realized through soft information exchange and optimization processing between the row decoder and the column decoder. In the iteration process, a method for judging the validity of the code word through the check matrix is designed by utilizing the polarization characteristic of the multiplication active code, so that the iteration is supported to jump out in advance to reduce the complexity. The invention provides a multiplication active code decoding algorithm based on an SO-ORBGRAND decoder, and compared with various non-system multiplication active code decoding algorithms and the performance of traditional long-code polarization codes, the method has remarkable advantages in error correction performance; a method for judging the validity of the code word through the check matrix by utilizing the polarization characteristic design of the multiplication positive code is provided, the complexity is reduced while the judgment success rate is improved, and the implementation overhead is reduced.

The invention discloses a reservoir group multi-target game scheduling model based on space-time collaborative dimensionality reduction and a solving method thereof, and the method comprises the steps: taking the water level of each reservoir as a decision variable, calculating each interest related party and constraint condition of a reservoir scheduling system for reservoir group scheduling, and constructing a reservoir group multi-target game scheduling model; a long-medium-short term layered nesting mechanism is constructed, and month, day and hour scale reservoir group target water levels are obtained based on a reservoir group multi-target game scheduling model to generate month, day and hour scale dynamic constraint intervals; returning a daily scale based on a deviation feedback mechanism at an hour scale to carry out iterative optimization on the model; reservoir key indexes serve as the basis for judging the importance of reservoirs, high-importance reservoirs are reserved, and low-importance reservoirs are clustered into equivalent virtual reservoirs. The method has the advantages that the problem of dimensionality disaster caused by space-time dual-dimension coupling in large-scale reservoir group multi-target scheduling of a traditional scheduling model is solved, and the calculation complexity is reduced on the premise that the scheduling precision is guaranteed.

The invention provides a design method of a low-complexity and high-precision variable fractional delay filter, which comprises the following steps of: 1, realizing a variable fractional delay filter VFD by adopting a Farrow architecture, and acquiring related parameters of the variable fractional delay filter VFD; 2, pre-designing a sub-filter coefficient matrix, designing a sub-filter by adopting a window function with adjustable parameters, and adjusting the frequency resolution of a variable fractional delay filter VFD under different orders; 3, least square optimization solution is carried out, and polynomial fitting is carried out on a coefficient matrix obtained through solution; and step 4, applying the coefficient matrix obtained by fitting to the Farrow architecture so as to obtain the coefficient of the variable fractional delay filter VFD based on the Farrow architecture. According to the method, the group delay precision is ensured, mathematical operations such as partial derivatives and double integrals are avoided, the complexity of coefficient solving is reduced, and the parameter calculation efficiency of the Farrow architecture variable fractional filter is improved.

The embodiment of the invention provides a long text processing method and device, equipment and a medium. The method comprises the following steps: performing word segmentation on a long text to be processed to obtain a token sequence; the token sequence comprises a plurality of tokens; performing prediction processing on the token sequence by adopting a pre-acquired language processing model to obtain a processed token sequence; the processed token sequence comprises the token sequence and at least one prediction token behind the token sequence; the attention layer of the language processing model is obtained based on fusion of a state space model SSM and a self-attention mechanism, the SSM is used for obtaining global attention of the input token, and the self-attention mechanism is used for obtaining local attention of the input token. According to the method, when the long text is modeled, the effects of reducing the calculation complexity of the model and ensuring the semantic integrity and coherence of model text modeling are achieved.

The invention relates to the field of software engineering and computer science, in particular to an intelligent code optimization and reconstruction system based on a large model, which adopts a comprehensive code analysis module to perform static and dynamic analysis and identify potential problems and complexity indexes in codes. Through an optimization suggestion generation module, personalized optimization suggestions are generated by using a neural network algorithm, and automatic code reconstruction is realized for different programming languages. And the system ensures the functional integrity of the reconstructed code through a reconstruction verification module, and provides a user feedback mechanism to optimize a subsequent strategy. Finally, the readability, maintainability and execution efficiency of the codes are remarkably improved, and the intelligent code optimization effect is achieved.

The invention relates to an embedded operating system platform related code generation method based on an AADL model, and belongs to the field of automatic code generation. According to the method, the AADL model is traversed, acquired and analyzed through a writing algorithm, a mapping rule from the AADL model to an embedded operating system code is designed, and components, interfaces, performance attributes and connection information between the components in the model are automatically converted into the embedded operating system platform code. According to the method, the codes can be automatically generated, the complexity and uncertainty of manual writing are reduced, the reliability and platform adaptability of the codes can be improved, and a powerful tool is provided for development of an embedded system in the aerospace field.

The invention belongs to the field of distributed multi-energy complementary system planning and operation optimization, and particularly discloses a distributed multi-energy complementary system design and operation hybrid optimization method considering electric vehicle energy storage. According to the building load clustering method and device, the DBSCAN density clustering algorithm, the fuzzy C-means algorithm, the fast elitist multi-target genetic algorithm (NSGA-II), the mixed integer linear programming algorithm (MILP) and the entropy weight method are combined, building load clustering is achieved based on the DBSCAN density clustering algorithm and the fuzzy C-means algorithm, and the complexity of the optimization calculation process is reduced. By combining NSGA-II and MILP, integrated optimization of capacity planning and an operation scheme of the distributed multi-energy complementary system considering energy storage of the electric vehicle is realized; and based on an entropy weight method, screening an optimal solution in a Pareto frontier solution set of capacity planning, and obtaining an optimal operation scheme of the system under the planning. The method provided by the invention fills the blank of the planning and operation optimization technology of the distributed multi-energy complementary system considering the energy storage of the electric vehicle.

The invention relates to the technical field of natural language processing and financial science and technology, and particularly discloses a question answer obtaining method and device based on a distillation model, computer equipment and a storage medium. The initial answer sequence of the to-be-answered question is obtained through the distillation model corresponding to the initial question and answer model, the distillation model can significantly reduce the parameter quantity and the calculation complexity, and then the obtaining efficiency of the initial answer sequence is improved. And secondly, the initial answer sequence is verified through the target question and answer model corresponding to the initial question and answer model, the target answer is obtained, errors in the initial answer sequence can be corrected, and the accuracy of the answer is ensured. Moreover, the target question and answer model only needs to verify the sequence, the whole sequence does not need to be generated, the task load is low, and the efficiency of obtaining the question answer is improved.

The invention relates to a Chinese grammar error correction method and system based on large model fine tuning. According to the method, a Qwen2-7B model is used for generating an error correction instruction data set; screening the instruction data set according to complexity, quality and diversity; performing supervised fine tuning on the Qwen2-7B model by adopting an LORA method, and emphatically optimizing a self-attention layer and a feedforward network layer so as to enhance the processing capability of the model on long-distance dependence and context information; then, a Qwen2-72B model is used for scoring the error correction data set, preference tags are generated, and the Qwen2-7B model is further optimized by using the tags, so that the response quality of the Qwen2-7B model is improved; a direct preference optimization method is used, a preference data set is combined to train the model, and parameters are adjusted to minimize a loss function, so that the tendency of the model to preference response is enhanced. According to the method, the accuracy of Chinese grammar error correction is effectively improved through a multi-level optimization strategy.

The invention belongs to the technical field of low-code development platforms, and particularly relates to a low-code platform model construction and dynamic execution method and system based on a hybrid DSL (Digital Subscriber Line), and the method comprises the steps: describing static model information in an application by using a structure DSL in a declarative grammar; defining a behavior DSL in a mounting mode under a corresponding element of the structure DSL; analyzing the structure DSL into a meta-model object tree in the platform, and converting the behavior DSL into an executable expression tree / intermediate representation; jointly driving the meta-model object tree and the expression tree / intermediate representation by utilizing a template engine, and automatically generating at least one application code in a front-end page, a back-end interface and a database script; a common structure DSL and a behavior DSL are combined and packaged into a scene template, and the scene template is stored in a template library so as to be reused by different service scenes, and modularization and templating of service modeling are realized. The complexity of the system is reduced, and the development efficiency and quality are improved.