22results about How to "Achieve self-optimization" patented technology

This invention belongs to the interdisciplinary field of artificial intelligence and geological resource assessment, specifically relating to a method and system for predicting the energy storage potential of salt caverns based on multi-source geological information. It aims to address the problems of low prediction accuracy and difficulty in balancing breadth and precision in existing technologies due to single-source data, static models, and lack of adaptive capabilities. The method includes: acquiring multi-source data such as seismic, well logging, core, and geostress data; constructing a geological feature fusion vector containing seven core parameters; establishing a high-dimensional nonlinear mapping model driven by a deep neural network; dynamically adjusting the prediction range based on data coverage density and confidence level; and achieving continuous model iteration through online incremental learning. The system integrates data quality assessment, anomaly handling, and distributed computing modules. By adopting the above technical solutions, this application can achieve a significant improvement in prediction accuracy and adaptive intelligent adjustment of the prediction range.

The invention provides a comprehensive testing method and device for an agricultural machine microcontroller and a storage medium, and relates to the technical field of microcontroller testing. The method comprises the steps of firstly building a bidirectional data transmission link with a microcontroller to be tested, then converting a user test demand into a corresponding test instruction, issuing the test instruction, collecting original test data after a test is executed, carrying out standardization processing on the original data, evaluating a test state, if a result is abnormal, creating a correction response flow according to an abnormal type, and if the result is abnormal, completing the test. Re-establishing a link or evaluating to obtain a new result; according to the invention, automation and integration of the whole testing process are realized through a closed-loop process, a splitting link is not needed, manual equipment switching is not needed, comprehensive testing is completed in a one-stop manner, operation is greatly simplified, and efficiency is improved; the abnormality correction mechanism can optimize the process automatically, avoids test interruption, guarantees test continuity and reliability, and provides an efficient and stable solution for factory detection and regular maintenance of the agricultural machine microcontroller.

The invention discloses a multi-task optimization method for solving a simultaneous goods taking and delivering vehicle path problem with a time window. The multi-task optimization method comprises the following steps: initializing populations of all tasks; the total operation cost of the vehicle path problem is used as an evaluation function, the adaptive value of each individual is calculated, and the path of each vehicle meets the vehicle capacity constraint, the client time window constraint and the simultaneous delivery demand constraint; calculating an accumulated average survival rate of offspring individuals generated by cross-task crossing in environment selection, and controlling knowledge migration between tasks; calculating compatibility scores of the candidate individuals under target task distribution, screening knowledge migration objects, and adjusting a compatibility screening threshold according to a historical migration success rate; and screening out a new generation of population based on a selection mechanism in a genetic algorithm, and selecting an individual with the optimal fitness from the final population to correspond to a final vehicle path scheme. According to the method, the opportunity, frequency and quality of knowledge migration can be more intelligently regulated and controlled, and stable search performance can be kept in a complex problem space.

The present application relates to the field of science and education display, and particularly relates to a display control method of a multi-axle three-dimensional dynamic pseudo-motion phenomenon display device, which comprises the following steps: S1, setting up a three-dimensional dynamic pseudo-motion phenomenon display device; S2, representing the pseudo-motion phenomenon effect of the display device by a control function G; S3, establishing a target function library, selecting the best function from the target function library, and obtaining the optimal solution of each coefficient in the control function G by using the least square method; S4, determining the rotation angular velocity range of the control function G; S5, combining the control function G to establish an input parameter database, constructing a machine learning control algorithm, and thus self-adjusting the associated parameters affecting the control function G. The present application can present the best display effect for different people in different environments.

The application discloses a kind of vehicle-mounted Ethernet dynamic flow scheduling method and system, it is related to vehicle communication field, comprising: T1, the data stream feature registration and global view management of the equipment of access vehicle-mounted network are carried out;T2, time window is taken as scheduling unit, multiple time slots are divided in time window, and hierarchical time slot scheduling model is constructed;T3, based on flow quota, network data is monitored and flow shaping in real time, and burst flow is inhibited;T4, according to the trigger of high priority emergency data stream, time slot preemption and time window dynamic reconstruction are executed;T5, according to network transmission quality feedback, the bandwidth quota of each data stream is adaptively adjusted.Through the above scheme, time window and three-level time slot physically isolate burst flow, ensure that safety data bandwidth such as braking, steering is monopolized, significantly reduce the packet loss rate, realize key business strong guarantee.

This invention discloses a semantic understanding method and engine based on multi-model collaborative reasoning and self-supervised learning, belonging to the fields of natural language processing and artificial intelligence. The method includes preprocessing input data to extract semantic features; intelligently scheduling at least two models from a large language model, task-oriented model, and rule engine for collaborative reasoning through a dynamic routing module based on multi-level policies and meta-learning networks; using a multi-model fusion module to perform hierarchical fusion and conflict resolution of the reasoning results, outputting the final semantic understanding result; and continuously optimizing the system through feedback learning. A self-supervised pre-training task is used to learn a general semantic representation from unlabeled data to enhance the model's generalization ability. The engine includes core modules such as input processing, dynamic routing, multi-model fusion, feedback learning, model repository, and monitoring and security, which work together to implement the above method. This invention achieves high-precision, high-efficiency, and adaptive semantic understanding.

The application discloses an industrial decision support system and method based on a large model and artificial intelligence, and belongs to the technical field of industrial intelligent decision-making.The system comprises the following steps: collecting industrial field data streams in real time and preprocessing to generate a structured time series dataset; using an industrial state analysis large model to extract a characteristic vector sequence, combining a sliding time window division and a neural Granger causality test algorithm to generate a causality knowledge rule set; using a neural differential equation framework to predict equipment state data prediction values; performing risk benefit assessment based on the prediction values to generate a structured decision instruction; after executing the instruction, comparing the prediction values and measured value deviations by using a sliding window cumulative error statistical method to dynamically optimize the model; and through the degenerative modeling and dynamic prediction of the causality rule constraint, and the closed-loop verification of the sliding window cumulative error statistical method, high-precision prediction of the equipment state, risk tracing and model self-adaptive optimization are realized.

This invention relates to the field of spectral data processing technology and discloses a Raman spectral processing method based on adaptive baseline correction, comprising the following steps: S1: acquiring the Raman spectrum of the sample to be tested; S2: performing adaptive Kalman filtering on the Raman spectrum to estimate the initial baseline, and using a real-time constraint mechanism to ensure that the baseline during the estimation process closely follows the lower edge of the signal; S3: performing multi-stage extreme smoothing processing based on the initial baseline, and combining the real-time constraint mechanism to extract the baseline trend and obtain an extremely smoothed baseline; S4: performing independent SG fine smoothing based on the extremely smoothed baseline to confirm the final baseline; S5: performing baseline correction based on the final baseline to obtain the corrected spectrum; S6: performing denoising based on the corrected spectrum; S7: extracting key feature peaks based on the denoised spectrum, and calculating the coefficient of variation based on the peak area of ​​the key feature peaks; judging data consistency based on the coefficient of variation, and triggering a feedback mechanism when consistency is abnormal; this invention can significantly improve the signal-to-noise ratio and feature fidelity of Raman spectroscopy.

The application relates to the technical field of cloud-edge collaborative computing, in particular to a charging facility resource allocation method and system based on cloud-edge collaboration; the method comprises the following steps: time alignment and fusion of multi-source operation data are carried out on the edge side of a charging station; service tension reflecting real-time pressure of the station is constructed through a load evolution rate, power constraints and queuing density; a user charging request is converted into a packet elastic scheduling unit, so that the demand has the characteristics of migration and extension; service tension and elastic units uploaded by each edge node are converged on the cloud side; a cross-site tension difference collaborative potential field is established; global optimization is carried out with the overall tension balance as the target; structured instructions containing priority, migration suggestion and time correction are generated; charging resources are abstracted into time service slots on the edge side; queues are dynamically reconstructed and local migration is executed according to the instructions; meanwhile, execution deviation is collected and fed back to the cloud side to realize closed-loop optimization. The application realizes efficient self-adaptive allocation of charging facility resources through cloud-edge collaboration.

This invention discloses a data acquisition and visualization processing system based on big data analysis, belonging to the field of data processing technology. It includes a resource allocation component that collects system load data and business demand data in real time, and weights and fuses system load, business demand, and resource elasticity coefficients to generate dynamic resource quantities. A visualization quality assessment component monitors resource utilization efficiency and data loading efficiency in real time, and dynamically adjusts the visualization rendering quality score by combining the error degree between the quantified visualization results and the original data. A dynamic threshold adjustment component analyzes visualization quality and system resource status in real time, adjusts the data hierarchy division threshold through a closed-loop feedback mechanism, and generates an adaptive threshold adjustment strategy based on differences in visualization quality and resource elasticity. This invention continuously optimizes resource allocation and data processing strategies based on visualization quality and resource status by improving resource utilization, enhancing visualization quality, strengthening system stability, and improving self-optimization capabilities.

The invention belongs to the field of new energy, relates to a charging pile energy efficiency optimization technology, is used for solving the problem that in the prior art, power control logic based on isolated voltage sensing has fundamental defects when coping with group interaction behaviors in a multi-pile coexistence scene, and particularly relates to a charging pile energy efficiency self-optimization system based on multi-modal AI. Comprising a data acquisition module, a feature calculation module, an intermediate state mapping module, a dynamic modulation module, a power adjustment amount calculation module and an execution and broadcast module. According to the method, the linear fitting in the preset time window is carried out on the real-time power sequence of each neighbor charging pile, the power change rate of each neighbor charging pile is accurately calculated, the number of the charging piles with the power change being the positive value and the negative value is further counted, and the consistency of the neighbor charging pile group in the power adjustment direction can be accurately quantified.

The invention is suitable for the field of automatic monitoring of a power system, and provides a power transmission line fault detection and positioning method and system based on a sensor network, and the method comprises the steps: continuously collecting multi-dimensional monitoring data through a sensor; each sensor independently judges abnormity, marks abnormal nodes and generates an abnormal information packet; the abnormal node broadcasts information, and the neighbor node verifies and generates verification information containing coordinates, voting types and confidence weights; the verification information is integrated, and a fault consensus is achieved if the sum of confidence weights exceeds a dynamic threshold value; and if consensus is reached, calculating and correcting the fault position, and if not, discarding data and processing false alarms. The system comprises corresponding acquisition, judgment, broadcasting, consensus judgment and positioning processing modules. The method improves the fault detection reliability and positioning precision, reduces the false alarm, and is suitable for a complex environment.

The application discloses a network security operation system and method based on security arrangement automation and self-adaptation, and belongs to the technical field of network security. The system comprises an adapter management module, a data access module, a script arrangement module and a self-adaptive base module. The method comprises alarm noise reduction, threat response, attack tracing, review analysis and vulnerability hunting. The application realizes the evolution of security operation from automation to autonomy by constructing a rule+AI double-layer noise reduction mechanism, a self-adaptive threat response mechanism and an attack tracing mechanism, and effectively improves the efficiency and accuracy of threat detection and disposal.

The application relates to the technical field of spectral data processing, and discloses a Raman spectrum processing method based on adaptive baseline correction, which comprises the following steps: S1: acquiring the Raman spectrum of a sample to be measured; S2: performing adaptive Kalman filtering estimation on the Raman spectrum to obtain a preliminary baseline, and adopting a real-time constraint mechanism to make the baseline in the estimation process close to the lower side of the signal; S3: performing multi-stage extreme smoothing processing based on the preliminary baseline, combining the real-time constraint mechanism, extracting a baseline trend, and obtaining an extreme smoothing baseline; S4: performing independent SG fine smoothing based on the extreme smoothing baseline, and confirming a final baseline; S5: performing baseline correction according to the final baseline, and obtaining a corrected spectrum; S6: performing denoising based on the corrected spectrum; S7: extracting key characteristic peaks based on the denoised spectrum, and calculating a coefficient of variation according to the peak area of the key characteristic peaks; judging the data consistency according to the coefficient of variation, and triggering a feedback mechanism when the consistency is abnormal; and the application can significantly improve the signal-to-noise ratio and characteristic fidelity of the Raman spectrum.

The invention discloses a comprehensive improvement control system and method for the frequency modulation performance of a coal-fired unit. The system comprises a first delay module, a first pulse module, a first AND module, a first signal quality judgment module, a first inertia delay module, a first switching module, a first function module, a second function module, a first addition module, a second switching module and a second function module. The method comprises the following steps: when the output results of the first delay module and the first pulse module are 1, the output end of the first AND module is 1, otherwise, the output end of the first AND module is 0, and the final result of the first AND module acts on a primary frequency modulation action and then is delayed and triggered to obtain a final switching value output result signal. According to the method, the performance index calculated in real time is compared with the standard value or the expected set value in real time, a predictive control and rolling correction method is adopted, the qualification of the frequency modulation index is comprehensively ensured, and a foundation is laid for economical operation of a unit.

The present application relates to the technical field of computer, in particular to a kind of job flow closed loop dynamic control system and method, system includes: job flow control engine module, for generating initial job flow;Perception module, for real-time collection runtime data;Evaluation module, for generating evaluation result based on runtime data;State monitoring module, for monitoring execution state and generating state update signal when detecting preset state transition condition;History state cache and retrieval module, for maintaining the historical operation record of target object and supporting relevant record retrieval.Job flow control engine module responds to state update signal and / or evaluation result, dynamically adjusts the sequence or transition condition of unexecuted sub-job node, and uses the adjusted job flow to control subsequent execution, forms adaptive control closed loop.The present application can adjust job flow online according to real-time state and historical memory, improve the flexibility of job processing and resource utilization efficiency.

This invention proposes an integrated touch display testing device and system, belonging to the field of automated testing technology for flat panel displays and touch modules. The system includes: a network construction module: identifying multiple interface protocols of the touch display module and generating interface compatibility data; dynamically configuring LVDS, MIPI, and EDP multi-channel transmission links based on the interface compatibility data to construct an adaptive interface communication network; this integrated touch display testing method significantly improves the compatibility of the testing equipment with multi-protocol modules such as LVDS, MIPI, and EDP through multi-interface adaptive transmission technology, eliminating test interruption problems caused by interface incompatibility.

The application relates to the technical field of mobile terminal application testing, and specifically discloses a cloud real-machine driving element knowledge base automatic construction and version evolution method for mobile terminal UI testing, which comprises the following steps: step S1, cloud real-machine UI element automatic scanning; step S2, locator confidence calculation and sorting; step S3, incremental version difference; step S4, cross-platform element alignment; and step S5, knowledge base storage and version management: storing the data generated in each step into a distributed database to realize version management, history tracing and version rollback of the knowledge base. The application realizes full-process automatic construction, intelligent optimization and version synchronous evolution of the element knowledge base, solves the core problems in the prior art, such as low manual maintenance efficiency, blind locator selection, high version update cost and poor cross-platform compatibility, can improve the executable rate of the test script by more than 30%, reduces the version update scanning cost by more than 70%, and the cross-platform element automatic alignment accuracy is more than 95%.

This invention discloses an intelligent control system for data acquisition and processing of a digital operation platform, belonging to the field of data acquisition and processing technology. It includes a sensing terminal, an edge terminal, and a cloud terminal. The sensing terminal acquires multi-source data to obtain terminal-sensed data, evaluates the contribution of each unit's categorized data, obtains the contribution degree of each unit's categorized data, adjusts the acquisition parameters based on the contribution degree, and transmits the terminal-sensed data to the edge terminal according to the contribution degree. The edge terminal then distributes the categorized data of each unit to the cloud terminal based on the contribution degree. The cloud terminal analyzes the terminal-sensed data based on a preset cloud analysis method to obtain cloud analysis results. It identifies the contribution degree of each unit's categorized data and analyzes control link information, classifies the analysis control link information according to the contribution degree, obtains the security protection classification corresponding to each link's step information, and performs dynamic differentiated security protection processing based on the security protection classification.

The invention discloses a man-hour management system and method for AI confidence evaluation and adaptive approval. Comprising a data acquisition module for acquiring a demand text and a code submission record; the confidence evaluation module is used for outputting predicted working hours and confidence by adopting Monte Carlo Dropout; the grading examination and approval module is used for executing automatic passing, manual rechecking or automatic rejection according to the confidence coefficient, and allocating rechecking persons according to dominant uncertainty; the deviation monitoring module calculates the deviation between the actual working hours and the predicted working hours; the threshold value self-adaptive module is used for performing Pareto optimal threshold value search by adopting an NSGA-II algorithm and taking an automatic passing rate and a re-checking accuracy rate as double targets; and the model self-optimization module analyzes a positioning deviation root cause through an anti-fact root cause, and performs directional increment updating by adopting an elastic weight consolidation algorithm. Through five-layer closed-loop cooperative control, the problems of low prediction credibility, poor examination and approval efficiency and incapability of continuously optimizing the model are solved, and intelligent closed loop of man-hour management is realized.

This invention discloses a device operation process optimization system and device based on interactive behavior data, belonging to the field of human-computer interaction technology. The invention performs facial recognition on a designated device for the user to be operated on, recording all identified users as potential users. If several potential users exist, user filtering is performed to determine the primary user to complete the device operation; otherwise, the operation is directly performed based on the potential user. If user filtering is performed, multiple interaction judgments are conducted using camera interaction behavior data to determine whether to execute the human-computer interaction operation, thereby identifying the primary user. During the execution of the human-computer interaction operation, a simultaneous human-computer interaction operation judgment is performed to select the issued interaction behavior command. Based on the response of the potential users to the interaction behavior command, the corresponding primary user is determined to complete the device operation. This solves the problem in existing technologies where systems struggle to accurately identify target users, leading to incorrect identity matching and potential payment errors.

The application relates to the technical field of network live broadcast compliance supervision, and discloses a live broadcast competition compliance policy pushing method based on behavior main promotion, which comprises the following steps: S1, acquiring multi-dimensional behavior data flow of a user in a live broadcast process; S2, generating a budding period risk score; S3, judging when the budding period risk score exceeds a preset risk threshold; S4, processing a strategy scheme; and S5, generating a compliance competition strategy for the user based on a compliance policy guidance scheme. By acquiring the multi-dimensional behavior data flow of the user and constructing a time sequence feature vector, the Mahalanobis distance of an individual behavior baseline model and the Euclidean distance of a competition ecological compliance behavior paradigm are innovatively combined to calculate double deviation degrees, and then a quantitative budding period risk score is generated. The method is free from the dependence on illegal keywords or post-event, and realizes early, active and highly personalized and accurate identification effects of potential compliance risks.