889 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 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.

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 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 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 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.

The invention discloses a regional distributed energy storage optimization scheduling method, which comprises the following steps: S1, model construction: constructing a mixed integer nonlinear programming model containing a multi-objective optimization function according to physical characteristics, operation constraints and economic objectives of a regional power distribution network, a micro-grid, an energy storage system and renewable energy; s2, scene generation and processing: adopting a Latin hypercube sampling method to generate a multi-scene data set of renewable energy output, load demand and electricity price fluctuation, performing clustering analysis on scene data, and screening out representative typical scenes so as to reduce calculation complexity; and S3, carrying out optimization solution. In the application, multi-dimensional constraints such as energy storage life attenuation, network loss, carbon emission and the like are added in constraint conditions, the practicability of the model is improved, and the limitation of traditional single-target scheduling is broken through through multi-target optimization and multi-constraint coordination.

The invention discloses a virtual space multi-person interaction synchronous control method oriented to an end-cloud collaborative architecture. The invention relates to a computer graphics and three-dimensional modeling technology, and discloses a cross-format lightweight and geometric consistency maintenance method based on a three-dimensional model. Through format-independent geometric representation and a self-adaptive lightweight strategy, efficient compression and precision maintenance of three-dimensional model cross-format conversion are realized. The method specifically comprises the following steps: performing format analysis and geometric feature extraction on an input model, and establishing a unified internal representation; adaptively selecting a multi-level LOD lightweight strategy based on the complexity of the model; the accuracy of key information is ensured through geometric feature keeping and topology consistency detection; the geometric consistency is dynamically maintained by combining error monitoring and an iterative correction mechanism; and generating a target format lightweight model and carrying out quality verification. According to the method, adaptive precision control, multi-level consistency maintenance and format irrelevant processing are combined, the model size and conversion errors are effectively reduced, and cross-platform compatibility and geometric fidelity are improved. The method can be widely applied to the fields of industrial design, game development, virtual reality and the like.

The invention discloses an intelligent foundation treatment scheme generation system and method based on a rule engine and a large language model, and belongs to the technical field of civil engineering. According to the method, the accuracy of a rule engine, the professionality of RAG and the flexibility of a large language model are combined, a hierarchical processing mechanism is adopted, tasks with different complexities are subjected to corresponding technical layer processing, verification is carried out in combination with a multiple verification mechanism, and therefore an optimal foundation processing scheme is obtained; and training a large language model by adopting a large model training method based on a structured reasoning process, and dynamically updating standard terms and expert knowledge. According to the method, the accuracy of the rule engine, the professional property of the RAG and the flexibility of the large language model can be combined, safety is ensured, intelligence and efficiency are improved, and quality is guaranteed.

The invention discloses a power system optimization method based on topology compression, and the method comprises the following steps: 1) constructing a power system topological graph: abstracting a power system into a weighted graph, representing power equipment by nodes, representing power transmission paths by edges, distributing electrical attributes and weights for the nodes and the edges, and providing a basis for subsequent topology compression and optimization; 2) analysis and implementation of topological compression: identifying redundant nodes and edges through cut point and bridge edge algorithms in a graph theory, and simplifying a topological structure by merging or removing redundant parts; 3) power flow analysis and optimal scheduling: performing power flow analysis on the compressed topological structure, and realizing power scheduling and load distribution by using an optimization algorithm to improve the operation efficiency of the system; and 4) dynamic adjustment and fault recovery: updating a topological structure and node attributes based on real-time data, and quickly responding to load fluctuation and equipment faults of the power system through an optimization algorithm. The method has the beneficial effects that the calculation complexity can be remarkably reduced, and the optimization effect and the scheduling efficiency are improved.

The invention belongs to the technical field of polarization codes, and discloses a large nuclear polarization code BP decoding algorithm based on a pruning permutation factor graph, and the algorithm comprises the steps: firstly, randomly generating a permutation factor graph; secondly, deleting nodes with low contribution degree and non-contribution degree to decoding through pruning operation; and when the stop condition is not met, replacing the factor graph to execute BP decoding of the pruned and permutated factor graph until the stop condition is met. For a large nuclear polarization code, a permutation factor graph can improve the decoding performance, and a pruning factor graph can reduce the decoding complexity. A simulation result shows that compared with a BP decoding algorithm, the algorithm provided by the invention can ensure that the complexity is not too high and the decoding performance is improved at the same time.

The invention discloses a Text2SQL (Structured Query Language) data set generation method based on dynamic difficulty adjustment. According to the method, a complexity quantification method is provided, and the complexity of SQL statements and Text texts is evaluated. A Text2SQL data set is generated based on a cue word generation template by using a large language model, and a dynamic constraint part is introduced into the cue word generation template. And performing complexity evaluation on data generated by the large language model through a complexity quantification method, comparing the data with preset difficulty target distribution, modifying dynamic constraints, and guiding the model to generate data conforming to expected target distribution. Meanwhile, a verification and correction template is also set, so that the execution correctness and semantic correctness of the generated data are ensured, the efficiency and quality of data set construction are improved, the diversity and pertinence of the data set are ensured, more comprehensive training data better fitting practical application is provided for the model, and the training efficiency is improved. And the generalization ability and the performance of the Text2SQL model in different scenes can be improved.

The invention discloses an underwater acoustic processing CPU-GPU dynamic load balancing method based on a task flow model, and belongs to the technical field of underwater acoustic processing. The method comprises the following steps: deconstructing an underwater acoustic processing application into a task flow model represented by a directed acyclic graph; establishing a feature portrait including calculation complexity, parallelism and data throughput for each task node, and constructing a cost prediction model; the CPU / GPU utilization rate and the data transmission performance are monitored in real time; a processor is distributed to each task node by using a dynamic programming algorithm in combination with a cost prediction model and a real-time system state with the goal of minimizing the total task flow completion time; and dynamically scheduling tasks through a central scheduler according to a decision result, and periodically updating a strategy. According to the method, the defects that static task division lacks adaptability and neglects task dependence and communication overhead are overcome, dynamic and efficient utilization of CPU and GPU resources is achieved, and the efficiency and real-time performance of underwater sound processing are remarkably improved.

The invention relates to an RIS auxiliary enhanced communication method based on an evolutionary guidance strategy gradient in the field of wireless communication, and provides an evolutionary guidance strategy gradient (EGPG) algorithm for joint optimization of transmitting end precoding and an RIS reflection phase shift matrix in an RIS auxiliary communication system. In combination with a strong fitting characteristic of deep learning, a gradient characteristic of reinforcement learning and a strong exploratory property of evolutionary learning, an idea of evolutionary learning is adopted to carry out iterative optimization on intelligent agent actions, so that sample diversity is increased for deep reinforcement learning, and strategy network optimization of deep reinforcement learning is guided. Compared with a traditional optimization algorithm, the method has a simple and clear optimization framework and low calculation complexity, and meanwhile, compared with a gradient-based deep reinforcement learning algorithm and an evolutionary reinforcement learning algorithm, the method has faster convergence and better system performance.

The invention relates to the technical field of code generation, and provides a code generation method, a power distribution network fault monitoring method, equipment, a medium and a product, and the code generation method comprises the steps: responding to a received code generation instruction input by a user, and carrying out the semantic analysis of the code generation instruction; according to a semantic analysis result, decomposing the code generation task to obtain a plurality of sub-tasks; aiming at each subtask, determining a code generation mode for executing the subtask according to the task complexity of the subtask so as to generate a code of the subtask; and generating the code of the code generation task based on the code generated for each subtask. The problem that a traditional code generation scheme is difficult to deal with a complex code generation task can be solved, the complex and multi-dimensional code generation task can be dealt with, and the code generation efficiency is improved.