161 results about "Combination strategy" patented technology

The invention relates to the field of multi-modal large models, and discloses an optimization method and system for a self-adaptive multi-stage fine-tuning multi-modal large model. The method comprises the following steps: constructing a multi-modal data set; coding modal data in a single group of samples based on a pre-trained multi-modal basic large model to generate feature representation; calculating a task correlation score, a feature information amount score and a gradient scale score of each modal data feature to generate a single-modal score; calculating a modal alignment degree score, an information complementation degree score and a collaborative gain degree score among different modals to generate a cross-modal interaction score; constructing a depth adjustment demand index and an interaction strength demand index according to the two scores, selecting a combination strategy of depth fine adjustment / shallow fine adjustment and strong interaction / weak interaction according to index values, and performing adaptive optimization on the multi-modal basic large model; and verifying whether the model performance meets the requirements or not so as to iteratively optimize to meet the requirements. According to the method, computing resources are saved, and the representation and generalization ability of the model is improved.

The invention discloses a cold station multi-equipment combination energy efficiency optimization method and system, relates to the field of cold station energy efficiency optimization, and aims to solve the problems of low energy efficiency and response lag caused by manual adjustment. The method comprises the following steps: S1, acquiring key operation data (power, state, temperature, flow and frequency) of a water chilling unit, a cooling tower and a water pump and external environment data (temperature and humidity, wind speed and load prediction) in real time; s2, constructing an equipment energy efficiency model based on historical data, and quantifying the change of the equipment efficiency along with the load rate, the temperature difference and the environment temperature; s3, according to the current load and environment prediction, simulating and traversing the energy consumption of the equipment start-stop combination and the water pump frequency combination by applying a Monte Carlo algorithm, and screening a combination strategy with the lowest total energy consumption of the system; s4, converting the optimization strategy into a control instruction, and issuing the control instruction to equipment for execution; and S5, comparing the actual energy consumption with the predicted value, and if the deviation exceeds 5%, correcting model parameters by adopting a least square regression algorithm to realize closed-loop optimization. And the energy efficiency and the response speed of the cold station are obviously improved.

The invention discloses a multi-knowledge-base scheduling routing method based on intention recognition and feedback optimization, and the method comprises the steps: S1, receiving multi-modal input from a user, carrying out the deep semantic analysis of the input content through natural language understanding and multi-modal analysis, and outputting a standardized intention label; s2, constructing a capability portrait for each knowledge base, and then generating a route matching score matrix according to a similarity relationship between the user intention tag and the capability portrait of each knowledge base; s3, screening out one or more most relevant candidate knowledge bases according to the scoring matrix and a set matching threshold value, and selecting a retrieval combination strategy to realize information recall; s4, information retrieval is executed based on the selected knowledge base, recall results and original user input are submitted to a large language model for content generation, and answers or suggestions are formed and output; and S5, user feedback collection and strategy optimization are carried out. According to the method, a more accurate, efficient and self-evolutionary knowledge base scheduling mechanism can be realized.

The invention provides a multi-mode authority management and record tracing method and system for an intelligent lock. The method comprises the following steps: step 1, obtaining the intelligent lock, performing initialization setting on the intelligent lock, connecting the intelligent lock to a home local area network, and establishing secure communication connection with a cloud server; according to the invention, multiple identity recognition modes are supported, multiple permission types are provided, and a permission type combination strategy can be formulated, so that the flexibility of permission management is greatly improved, and diversified use requirements of modern families are met; according to the method, unlocking information of each time is automatically recorded, and a user behavior model is constructed in combination with a big data analysis technology, so that potential safety risks and abnormal behavior modes can be quickly and accurately identified, and the efficiency and accuracy of troubleshooting are improved; the intelligent lock can be quickly and automatically switched to the emergency mode when facing a complex environment or a special condition, so that the malicious attack resisting capability of the system is effectively improved, and the safety and the stability of the intelligent lock in the complex environment are enhanced.

The invention discloses a disease prevention management and monitoring system design method based on an adaptive algorithm. The method comprises the following steps: S1, obtaining health data of a user; s2, performing feature extraction and fusion on the health data by using a hypergraph neural network; s3, constructing a disease risk prediction model based on the generative reasoning network, and introducing an anti-fact generation module to generate a health change hypothesis scene; s4, adaptively adjusting a personalized intervention strategy through a nested game model, and adjusting the intervention intensity in the first layer; s5, in the second layer, generating an optimized intervention combination strategy based on a Nash equilibrium driven multi-target adaptive game; s6, risk weighted scoring is carried out on the health data through a structured clustering algorithm, and a feedback event is generated; and S7, dynamically optimizing a disease prevention management strategy through a chained feedback mechanism, and managing node permission. According to the method, the self-adaptive algorithm is combined with the multi-layer game and the distributed anomaly detection, so that personalized disease prevention management and monitoring are realized.

The invention discloses a data-driven learning model combination optimization method based on edge cloud collaboration, and the method comprises the following steps: constructing a collaborative computing framework based on cloud nodes, edge nodes and equipment nodes, and distributing distributed tasks and computing resources; constructing a plurality of micro-service interfaces including a platform service interface, an evaluation service interface and a model training service interface of edge nodes, and a model upgrading service interface and a candidate solution evaluation service interface of cloud nodes; a multi-round model combination strategy and a model online enhancement combination training strategy based on integrated learning are constructed, a plurality of micro-service interfaces are packaged into Docker mirror images to be stored in a cloud mirror image warehouse for version management and distribution, and a communication mechanism between cloud nodes and edge nodes is constructed. According to the method, through cooperative work of the cloud and edge computing, the solving efficiency of a complex distributed optimization problem is remarkably improved, and the resource utilization efficiency and the data processing intelligence are improved.

The invention provides a software development data management method and system based on cloud service. The method comprises the following steps: acquiring code version difference data generated in a multi-version development process from a cloud service environment, and allocating the code version difference data to a corresponding storage position according to a version sequence identifier; a version relation graph is constructed based on the calling relation between the version branches, and the data flow direction and the logic dependency relation between versions are dynamically recorded; carrying out sorting and logic dependence verification on conflict contents in combination with the conflict state and the merging strategy, and generating a traceable merging operation instruction set; and finally, executing feedback data according to an instruction set to update a graph conflict state, synchronously triggering storage data update and redistribution of version identifiers, and realizing full-link closed-loop management of development data. According to the technical scheme provided by the invention, the efficiency and accuracy of software development data management can be improved.

The invention relates to a user operation risk dynamic monitoring method and device based on data consanguinity and a medium, and the method comprises the following steps: obtaining operation behaviors of all users in real time, and extracting a segment of continuous operation behaviors of each user as a group of behavior fragments with semantic relevance; a plurality of continuous behavior segments of each user are matched with a preset behavior template, so that a plurality of intermediate behavior blocks are obtained through dimension reduction; according to a time sequence, traversing and extracting a predetermined number of intermediate behavior blocks from the plurality of intermediate behavior blocks, and respectively combining to generate a behavior fragment sequence; and respectively inputting the behavior fragment sequences into a pre-trained neural network model to obtain a risk classification result or a risk probability distribution result corresponding to each behavior fragment sequence. The method has the advantages that each operation behavior can be subjected to structured expression, the potential behavior chain can be reconstructed through the combination strategy, and the high-risk behavior path hidden in the data noise is recognized by means of the deep model.

The invention relates to the technical field of software engineering and artificial intelligence crossing, in particular to an API test case rapid generation method and system based on an AI large model.The method comprises the following steps that joint analysis and semantic fusion are conducted on an API document and a demand document through a multi-modal data analysis layer, and a complete test context is constructed; generating a test case based on the pre-trained large model by using a hybrid inference engine; the method has the beneficial effects that the association constraint of the API document and the demand document is automatically extracted through semantic understanding; a parameter combination strategy is optimized through reinforcement learning, and the problem of combination explosion is solved; constructing a self-adaptive test case maintenance mechanism, and responding to API version iteration; an executable test code that can be directly integrated into the CI / CD pipeline is generated.

The invention discloses an intelligent item selection recommendation system of a live broadcast room based on AI digital people, relates to the technical field of intelligent item selection recommendation, and solves the technical problems of generating a dynamic and high-confidence matching scheme based on highly matched commodities and adjusting a combination strategy in combination with a real-time scene and user feedback. Through the multi-dimensional weighted calculation of the feature matching score, the crowd matching score and the scene association score, the hidden integrating degree of the commodity and the user demand is quantified, the highly matched commodity is screened out, the invalid recommendation is reduced, the comprehensive confidence degree of the commodity combination is calculated based on the association rule algorithm, the personalized matching scheme conforming to the real-time scene is generated, and the user experience is improved. A high-potential scheme is screened through a self-adaptive threshold value, the matching rationality and transformation potential are improved, a comprehensive feedback processing module is introduced, a user is supported to customize combined commodities, and optimization suggestions are provided through system evaluation; and for user change feedback, generating hidden collocation based on a user portrait, and realizing real-time iteration of a recommendation scheme.

The invention discloses a cooperative control and disturbance suppression method for a multi-axis servo system, and relates to the technical field of cooperative and disturbance control of servo systems, position and speed signals of each servo axis are acquired in real time, a cooperative error vector is calculated based on a graph theory model, the vector reflects the deviation between the state of each axis and an expected cooperative trajectory, and the cooperative control and disturbance suppression of the multi-axis servo system are realized. And synchronous movement is ensured. The collaborative error is used for generating a preliminary control signal, and a proportional, differential and integral term combination strategy is adopted to quickly correct the error and eliminate the steady-state error. Meanwhile, disturbance vectors are estimated through an observer, and external interference or internal changes are compensated. And after the preliminary control signal and the disturbance compensation are added, amplitude limiting processing is carried out to prevent saturation of the driver. The control parameters are adjusted through an off-line optimization algorithm to minimize errors and disturbance influences, so that the tracking precision, the anti-interference capability and the adaptability of the multi-axis servo system are improved, and the method is suitable for the fields of high-precision manufacturing, robot control and the like.

The invention provides a multi-source complementary intelligent power supply management method and system in a mobile square cabin. The method comprises the following steps: collecting real-time state data of multi-type energy supply equipment, and generating a comprehensive energy management data set; based on the comprehensive energy management data set, dynamically evaluating real-time efficiency by adopting an interval optimization algorithm based on an evolutionary strategy, and generating an energy combination strategy report by applying a Markov decision process; based on the energy combination strategy report, adopting a gradient descent optimization algorithm to adjust working parameters of the multi-type energy supply equipment, and applying a real-time energy balance technology to generate an optimized energy configuration scheme; and based on the optimized energy configuration scheme, monitoring the operation condition of a power supply system, optimizing working parameters, and generating an intelligent power supply management parameter set. According to the technical scheme, the intelligent power supply management effect can be effectively improved.

The invention relates to the technical field of natural language processing, and provides a multi-granularity text compression method and system for large-model multi-round dialogues, and the method comprises the steps: carrying out the semantic coding of historical question and answer pairs and a current dialogue question through a pre-training model, obtaining a semantic vector, generating a historical dialogue semantic representation through a self-attention mechanism, and carrying out the semantic representation of the historical dialogue. A semantic vector of a current dialogue problem is combined, a correlation enhancement vector is obtained through a target attention mechanism, weighted fusion is carried out on the correlation enhancement vector and historical dialogue semantic representation, a fusion vector is obtained, a feature vector is generated through a maximum pooling and average pooling combination strategy, clustering is carried out, positive and negative sample pairs are constructed, and semantic similarity loss calculation is carried out. Iteratively training the classification model; and based on the trained classification model, screening question and answer pairs related to the current dialogue question, and generating a structured abstract. Redundant content is remarkably reduced while key semantic information is reserved, and efficient context representation adaptive to large model reasoning is formed.

The invention discloses a table collaborative editing method and system, and relates to the technical field of artificial intelligence, and the method comprises the following steps: during multi-user collaborative editing, receiving user editing operations, packaging each user editing operation into an independent operation sequence, summarizing all the operation sequences, and performing unified operation on the operation sequences, the operation sequence comprises content information and parameter information of user editing behaviors; performing operation conflict detection based on the operation sequence, and if an operation conflict is detected, dividing the conflict into a direct conflict, a structure conflict, a style conflict and a dependency conflict through a conflict classifier; corresponding strategies are matched and executed for different conflict types through the intelligent conflict solver, the strategies comprise the automatic merging strategy, the user selection strategy and the delay processing strategy, and the problems that in the prior art, cell merging intelligent verification cannot be achieved, and conflict solving cannot be achieved during multi-user collaborative editing are solved are solved.

The invention relates to the technical field of computer system performance and security testing, in particular to a computer performance security testing method and system. The method specifically comprises the steps that performance indexes, behavior characteristics and security event data of a target system are obtained in real time and subjected to standardization processing, clustering modeling is conducted on the behavior characteristics subjected to dimension reduction through a Gaussian mixture model so as to establish a normal behavior pattern cluster, and time sequence analysis is conducted on a behavior sequence in combination with a hidden Markov model so as to recognize a system state transition path; adopting a weighted combination strategy to mix and inject a normal load and an aggressive load, and adjusting an abnormal behavior chain through a disturbance function; constructing directed weighted association between the abnormal event and the performance index based on an event-driven causal performance diagram, quantifying a system risk index and triggering an alarm; outputting performance bottlenecks, security vulnerabilities and optimization suggestions, and updating the knowledge base to optimize subsequent models. According to the invention, deep coupling of performance and safety testing, intelligent scheduling of dynamic loads and interpretable positioning of risk paths are realized.

The invention relates to the technical field of AGV path planning in an intelligent manufacturing workshop, in particular to a multi-AGV path planning method with collision detection in a matrix workshop. Comprising the steps of initializing algorithm parameters; using a hybrid initialization strategy to initialize the population; in the hive bee employment stage, for each individual in the population, a vehicle merging strategy is adopted, and a local search operator is selected based on a self-adaptive selection strategy to carry out individual evolution; in the bee observation stage, enhanced evolution is carried out on individuals with good ranking, vehicle position information is updated, collision detection is carried out on the running process of the vehicle, and a vehicle running path is re-planned based on a collision avoidance strategy for possible collisions; in the reconnaissance bee stage, for the individuals failed in continuous evolution, a ranking-based restart strategy is used, and the global exploration ability is enhanced; and judging whether a termination condition is met, and finally outputting an optimal solution. On the premise of an actual production application scene, the production safety is improved, and the AGV operation cost is reduced.

The invention discloses a resource optimization configuration system of an intelligent supply chain, and relates to the technical field of supply chain resource optimization, and the system comprises a manufacturing production module, a supply replenishment module, a distribution demand module and a logistics service module, formulates a manufacturer prediction distribution strategy, obtains raw material inventory data, formulates a supplier replenishment strategy, and carries out the resource optimization of the supply chain. According to historical sales data and consumer preference data, a demand prediction model is established, temporary order adding goods data is acquired, a manufacturer temporary distribution strategy is formulated, a transportation tool distribution strategy and a multi-order combination strategy are formulated, and through integration of technologies such as the Internet of Things and big data, accurate productivity evaluation, demand prediction and rapid response are realized. Through hierarchical manufacturer management and an intelligent distribution strategy, the resource utilization efficiency is improved, the operation cost is reduced, meanwhile, logistics transportation and order processing are optimized, rapid delivery is ensured, the transparency and controllability of a supply chain are enhanced, the customer satisfaction is improved, and sustainable development of the supply chain is promoted.

The invention relates to a tail end constant-pressure water supply strategy adjusting method and system based on AI, and belongs to the technical field of secondary water supply.The constant-pressure water supply strategy adjusting method comprises the steps that the flow of a header pipe and real-time health state data of each running pump are periodically collected; according to the header pipe flow, the dynamic demand lift is calculated, and all feasible pump set combination strategies are generated in combination with the dynamic demand lift and the real-time health state data; the score of each candidate strategy is calculated, the candidate strategy with the highest score is used as a pump set scheduling strategy, the pump with the most matched performance is selected from candidate pump sets corresponding to the pump set scheduling strategy to serve as a frequency conversion main guide pump, and the other pumps serve as frequency conversion auxiliary pumps; according to the set minimum service pressure and the dynamic demand lift, the target pressure of a pump outlet is calculated; and according to the target pressure and the actually-collected pump outlet pressure, the rotating speed of the variable-frequency main guide pump is adjusted. The method has the beneficial effects that the power of the pump set is matched with the actual requirement, so that the operation cost is reduced.

The invention discloses a self-service door opening method for a store, and relates to the technical field of self-service stores. The system carries out intelligent matching according to a pre-stored user file, calculates a similarity threshold value through an algorithm, judges that a user is a legal user if the matching degree exceeds a preset value, or rejects access; a dynamic combination strategy is adopted to allow an administrator to configure weights and combination modes of different fields according to the security requirements of the store, so that the user experience is optimized and the privacy leakage risk is reduced on the premise of ensuring the security; a background management system flexibly sets a weight value and combinatorial logic of each verification element, the matching efficiency is dynamically optimized based on a preset similarity threshold, if a comprehensive score after element combination reaches a security level score configured by the system, rapid door opening is automatically authorized, otherwise, secondary verification or manual auditing is triggered, and the safety of the system is ensured. The false rejection rate is reduced, the safety protection capability is improved, the verification modes are automatically switched according to regions or time periods, and the door opening speed is high when the operation is successful.

The invention relates to a supply chain modeling method based on a platform operation mode and a carbon transaction policy, and belongs to the technical field of supply chain design. According to the method, carbon emission data of each link of a supply chain is collected in real time through a multi-source sensor, the law of conservation of energy is used as a constraint condition to be embedded into a Transform-XL neural network model, a multi-link nonlinear coupling model is constructed, and a nonlinear coupling relational expression of carbon emission and sales is output. And in combination with a carbon quota distribution mechanism, solving a QUBO matrix by using a quantum annealing algorithm to obtain an optimal scale combination strategy of each link scale of the supply chain, and realizing collaborative optimization of carbon emission intensity reduction and profit improvement. According to the method, the problems of poor adaptability, low calculation efficiency and the like of a traditional supply chain optimization model under a dynamic carbon transaction policy are solved, and an efficient solution is provided for supply chain decision making.

The invention relates to a risk management and decision support method, system and platform for the pharmaceutical industry. The method comprises strategic investment portfolio management, supervision affair, clinical drug development, pharmaceutical economics, investment strategy optimization, risk management, merger and purchase full-duty investigation and stock markets. The system uses artificial intelligence and diverse data from public and private sources, including clinical trials, regulatory decisions, economic data, pharmacological data, and company data. The system integrates a plurality of decision modules for clinical development, such as clinical risk, supervision risk, pharmacological risk and economic risk. This risk factor network generates predictive and normative information for strategic decisions.

The invention discloses a production scheduling prediction method, a production scheduling prediction device, a storage medium and equipment, and relates to the technical field of pipe piles. The method comprises the steps that the predicted delivery amount of the pipe piles with the pile length of the current specification is determined based on the delivery amount of the pile length of the specification of historical pipe piles; and determining an optimal production strategy based on the predicted delivery quantity of the pipe piles with the pile length of the current specification and a pile length combination strategy. According to the invention, the predicted delivery amount of the pipe pile with the pile length of the current specification is determined through the delivery amount of the pile length of the specification of the historical pipe pile, so that the optimal production strategy is determined based on the pile length combination strategy, the production is closer to the trend of the sales market, the finished product inventory of the enterprise is reduced, the cash flow of the enterprise is increased, and the cash flow pressure of the enterprise is reduced.

The invention discloses a system for improving item recommendation accuracy based on space-time diffusion and information bottleneck. The system comprises the following modules: a normalization processing module, a space aggregation module, a time aggregation module, a time diffusion module, a space diffusion module, an information bottleneck module and a prediction module. The system can effectively model an error behavior which is not solved by a current next basket recommendation technology, and through an innovative spatial diffusion module, the system does not depend on strong association among commodities or historical preferences of users any more, but focuses on learning of article spatial combinatorial logic in a shopping basket, so that the system is more intelligent. Therefore, the system can identify the targeted and hidden combination strategy of the user, thereby improving the understanding of the real purchase intention of the user, and achieving the purpose of improving the article recommendation accuracy.

The invention discloses a service combination method based on a colored Petri net and a deep reinforcement learning agent. The method comprises the following steps: S1, constructing a colored Petri net model for manufacturing a service combination system; s2, constructing a deep reinforcement learning environment based on the model, and defining a state space, an action space and a reward function; s3, interacting the intelligent agent with the environment, dynamically generating an action mask by using a Petri net model to constrain an action space, and training the intelligent agent to converge by using a near-end strategy optimization algorithm; and S4, taking the strategy obtained by training as an optimal service combination strategy, and triggering transition in the Petri network to generate a final manufacturing service combination scheme. According to the method, the formalized modeling capability of the colored Petri network and the self-adaptive decision-making capability of deep reinforcement learning are deeply coupled, so that the problem that in a dynamic complex industrial interconnection environment, the formalized modeling capability of the colored Petri network and the self-adaptive decision-making capability of the deep reinforcement learning are influenced is solved; the problems of low decision-making efficiency, poor adaptive ability and opaque optimization process caused by huge decision-making space and complex logic constraints in a manufacturing service combination method are solved.

The invention discloses a cloth warehouse-out scheduling method and system based on multi-strategy cooperation, and the method comprises the steps: constructing a warehouse three-dimensional coordinate model, and building the precise mapping of a warehouse space code and a three-dimensional coordinate; the order priority is quantified by adopting an analytic hierarchy process-fuzzy comprehensive evaluation (AHP-FCE) model, and resource allocation in an idle period and a busy period is adapted through dual-mode scheduling; a shortest order picking path is planned based on a Dijkstra algorithm; based on a reinforcement learning deep Q network (DQN) dynamic decision order combination strategy, invalid movement and resource waste are reduced. The method can remarkably shorten the order processing time, improve the resource utilization rate, balance the personnel efficiency, effectively relieve the operation bottleneck in cloth delivery, and is suitable for various cloth storage scenes.

The present invention relates to the technical field of operating system memory management, and discloses a real-time container memory management method and system for an operating system. By solving the system user combination strategy and the system memory allocation strategy to guide the memory management of the operating system, different minimum management cycles of several system users in the target memory management period are combined, and overall memory allocation is performed for each system user group instead of individual memory allocation for each system user, which can provide redundant memory allocation for each system user, avoid the problem of program running delay caused by calling data from the disk due to insufficient memory allocation accuracy. At the same time, when the memory resources are sufficient, the memory can be released as much as possible for users to use, and when the memory resources are tight, the memory can be utilized maximally, improving the rationality and intelligence of memory management in the multi-user scenario of the operating system, and while meeting the memory requirements of more users as much as possible, improving the fineness of memory allocation.

The embodiment of the invention provides a strategy determination method and device. The method comprises the following steps: acquiring real-time index data and a real-time prediction load of a Serverless function; determining a plurality of target optimization functions according to the real-time index data and the real-time prediction load; the multiple target optimization functions comprise a first target function and a second target function, the first target function is used for minimizing the cold start delay of the function, and the second target function is used for minimizing the resource cost of the function; the candidate solution of each target optimization function indicates a combined strategy of a resource allocation strategy and a cold start strategy; a plurality of target optimization functions are processed by utilizing a multi-target evolutionary algorithm, and a target combination strategy is screened out from numerous candidate solutions by simulating the principle of survival of victims and inferior and continuous optimization of populations in a biological evolution process, so that the resource cost of the functions is reduced on the basis of ensuring cold start low delay of the functions; and the resource allocation efficiency is improved.

The invention provides a page loading method and device and related equipment.The method comprises the steps that a client side responds to loading operation of a page of an application, M loading requests of M services needing to be loaded on the page are obtained, then a merging strategy configured by a user is obtained, N loading requests in the M loading requests are merged according to the merging strategy, and N is a positive integer; a merging request is generated, and N services corresponding to the N requests are provided by the same server side. The client side sends a merging request to the server side to indicate the server side to execute the merging request, then receives an execution result of the merging request returned by the server side, analyzes the execution result into a request result corresponding to each loading request in N loading requests, and sends the request result to the server side; and displaying the request result to the position of the service corresponding to each loading request in the N loading requests in the page. Based on the method provided by the invention, the number of times of interaction between the client and the server can be reduced, and the page loading speed can be improved.

The present application relates to a kind of multi-stage self-defined combination strategy warehouse picking optimization method, device and medium, wherein, method includes collecting order data to be picked and preprocessing generation structured data set;Support user self-defined configuration wave division dimension and weight, complete order clustering and generate picking wave with unique identification;Divide the whole process of picking into four core stages, provide each stage strategy selection and combination interface, generate compatible multi-stage strategy combination scheme;Correlation scheme and wave task are executed in stages, real-time acquisition of field data and dynamically correct abnormal strategy;After completing picking, the core index is counted, report is generated and review output optimization suggestion, the present application solves the problem that traditional picking strategy is poor in adaptability, low efficiency, can be flexibly adapted to multiple warehouse scene, improve picking efficiency and accuracy, reduce resource consumption, and the practical value is remarkable.

The invention discloses an intelligent flight route planning method and system based on big data. The method comprises the steps of multi-source flight route data acquisition, obstacle cluster construction, high-density obstacle area identification, hierarchical planning cost function design, flight planning route parameter optimization and intelligent flight route planning. The invention relates to the technical field of data processing, in particular to an intelligent flight route planning method and system based on big data, according to the scheme, a multi-dimensional high-density obstacle area recognition mechanism is innovatively proposed, a hierarchical planning cost function collaborative technical scheme is designed, the flight safety is enhanced, and the obstacle avoidance efficiency is improved; introduction of a density perception initialization strategy and a double-layer particle ball merging strategy is innovatively proposed, a clustering algorithm is improved, and clustering accuracy and stability are improved. An optimization algorithm is improved by adopting a self-adaptive exploration strategy and a quadratic interpolation strategy, the efficiency of route parameter optimization and the quality of an optimal solution are improved, and accurate optimization of flight planning route parameters is realized.