243 results about "Decision function" patented technology

The invention discloses an underground construction decision-making method based on three-dimensional geological modeling and risk hot area identification, and relates to the field of fusion of artificial intelligence and geological engineering. The method comprises the following steps: firstly, acquiring drilling data, geological radar images and seismic reflecting layer information, constructing a three-dimensional geological voxel model with spatial topology constraints, and accurately describing a geological unit structure by adopting an irregular grid mode; and then, extracting a time sequence characteristic index under construction disturbance, forming a continuous time sequence characteristic vector, inputting the continuous time sequence characteristic vector into a convolutional recurrent neural network model with a space attention aggregation mechanism and a deep memory unit, and predicting a risk heat value of each space position. And on the basis, through heat gradient clustering and neighborhood consistency analysis, a dynamic high-risk hot area is identified, and a risk hot area map is constructed. And finally, in combination with the construction stage, the equipment plan and the sensor feedback information, constructing a multi-target auxiliary decision function, and generating a construction decision result including operation path reconstruction, rhythm adjustment and power limit and control suggestions.

The invention discloses a broadband oscillation identification method and system based on a multi-band Nyquist criterion, and the method comprises the steps: dividing the frequency of broadband oscillation into a low frequency band, a middle frequency band and a high frequency band with overlapped frequency bands, and obtaining the oscillation signals of a monitoring node in a power grid in different frequency bands; respectively calculating the equivalent impedance of the non-overlapped frequency band of each frequency band and the equivalent impedance of the overlapped frequency band in the two adjacent frequency bands so as to construct the equivalent impedance of the low frequency band, the middle frequency band and the high frequency band with the overlapped frequency bands; establishing a Nyquist criterion of each frequency band based on a transfer function of dynamic characteristics of each frequency band in an open-loop state of the system; a generalized Nyquist criterion of the overlapped frequency bands is constructed by using the multi-frequency-band coupling matrix; constructing a comprehensive decision function according to the recognition result of the generalized Nyquist criterion on the system stability, the broadband oscillation comprehensive characteristic quantity and the change rate of the high-frequency-band impedance module value along with the frequency; and according to the value of the comprehensive decision function and a threshold value, a broadband oscillation identification result is determined, and the broadband oscillation identification capability is improved.

The invention provides a multi-sensor fusion and environment feature recognition method and system for digital twin equipment, and the method comprises the steps: constructing a digital twin model of the equipment in a visual platform, and setting a self-updating mechanism; deploying a multi-sensor array at a key installation part of the equipment physical entity, collecting multi-source sensing data and uploading the multi-source sensing data to a twin platform; carrying out noise reduction processing on the multi-source sensing data and completing data fusion to obtain fused data; constructing a diffusion model corresponding to a noise scheduling strategy, generating new sensing data and a corresponding label, and forming analysis data; a multi-channel deep learning model is constructed to extract feature parameters from analysis data, regression prediction is carried out, and an identification result is obtained; the system is integrated to a twin platform and is combined with a control decision function. According to the invention, real-time regression prediction of environment characteristic parameters based on sensing data is realized, deep fusion of environment perception and control decision of equipment is promoted, and perception capability and adaptive adjustment capability of a control decision system of the equipment are improved.

The invention provides an emergency resource intelligent scheduling optimization method and system based on large model analysis, and relates to the technical field of emergency resource scheduling. The method comprises the steps of collecting emergency event data and environment data; extracting emergency event features and environment features, constructing a prediction model based on a long short-term memory network, and obtaining a required emergency resource list; constructing an emergency resource evaluation model based on an analytic hierarchy process, and obtaining priority scores of the required emergency resources; constructing a multi-objective optimization model, and solving the multi-objective optimization model by using a particle swarm algorithm to generate a scheduling scheme; and constructing a decision function, and solving by using a genetic algorithm to obtain a scheduling decision. According to the method, through accurate prediction, scientific evaluation, multi-objective optimization and decision in combination with priority, the accuracy and efficiency of emergency resource scheduling and the resource utilization efficiency can be remarkably improved, powerful support is provided for emergency management work, and the method has important practical significance and application value.

The invention discloses a multi-modal large-model multi-agent collaborative scheduling and distribution method, and relates to the technical field of agent deploying.The method comprises the steps that a complex task input by a user is received, the complex task is disassembled into atomic-scale subtasks, and a task decomposition graph is generated; establishing an intelligent agent capability evaluation model, and obtaining a comprehensive capability score of each intelligent agent according to the capability behavior of each intelligent agent in the candidate intelligent agent set; the intelligent agent set generation module is used for dynamically matching and distributing roles through a decision function according to subtask types and intelligent agent comprehensive capability scores, and generating a candidate intelligent agent set; and according to the task decomposition graph and the comprehensive capability score of each agent, constructing a task-agent ant colony allocation algorithm, and solving an allocation scheme. The problems that an existing multi-agent system lacks a dynamic role adjustment mechanism, flexible cooperation cannot be achieved according to task progress and agent states, and the efficient and flexible task processing requirement of a multi-mode large model application development platform is difficult to meet are solved.

The invention discloses a TCN-SVM rolling bearing fault diagnosis method fusing an SE attention mechanism, and belongs to the technical field of mechanical fault intelligent diagnosis. Aiming at the problems of feature redundancy, noise sensitivity, insufficient Softmax classifier generalization and the like existing in a traditional time sequence convolutional network (TCN), the invention provides a solution for collaborative optimization of a deep network and a support vector machine. The method comprises the following steps: acquiring a vibration signal of the rolling bearing; constructing a multi-fault sample set, and processing an original signal; constructing an SE-TCN feature extraction network, capturing multi-scale time sequence features by adopting expansion causal convolution, and embedding an SE module into a residual module to realize channel adaptive weighting; and a support vector machine (SVM) classifier decision function is constructed, and fault classification is completed through the RBF kernel SVM. Experiments show that the method has high fault recognition accuracy and robustness, and the problem of confusion of composite fault features of the rolling bearing is effectively solved.

The invention belongs to the technical field of spectral analysis, and discloses a Raman spectrum characteristic peak segmentation method based on distance vector and probability vector output. Spectral detail features are extracted through multi-scale wavelet decomposition, and a spectral multi-layer structure representation matrix is constructed; identifying a potential peak site and a hierarchical affiliation relationship thereof based on the local curvature change rate; generating an adaptive distance calculation kernel function in combination with the asymmetry index and the peak shape complexity coefficient; and calculating a distance vector of hierarchical perception and a probability vector extracted by deep learning, and constructing a joint segmentation decision function of a multi-layer peak structure. According to the method, the hierarchical relationship among the main peak, the shoulder peak and the sub-peak can be accurately distinguished, the complex conditions of peak overlapping, asymmetric peak shapes, low signal-to-noise ratio and the like are effectively processed, and the accuracy and the reliability of Raman spectrum analysis are improved.

The invention relates to the technical field of active safety of forklifts, and discloses a driving assistance method for stability adjustment of a forklift, which comprises the following steps: acquiring input parameters of the forklift for driving assistance; acquiring a fuzzy set corresponding to the input parameter; establishing a fuzzy rule base for logical reasoning based on the fuzzy set of the input parameters; constructing a decision function through a weighted average method to calculate a driving mode control value, and optimizing a weight through minimizing a decision error based on supervised learning; outputting a corresponding driving mode according to the driving mode control value; the invention further discloses a driving assistance system for forklift stability adjustment. The driving assistance system comprises a road surface recognition module, a forklift state acquisition module, a parameter fuzzification module, a fuzzy rule base storage module, a driving mode decision module and a driving mode execution module. By monitoring a plurality of input parameters, the overall performance and the adaptive capacity of the forklift system are improved, and efficient operation and safe operation of the forklift system in a dynamic complex environment are ensured.

The invention relates to the technical field of intelligent decision making, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a speech synthesis method, device, equipment and medium based on an optimization strategy algorithm, comprising: extracting a time sequence processing network unit and a data sampling scheduling unit in a speech synthesis model; mapping a denoising function in the time sequence processing network unit into a multi-step Markov decision function, and converting an ordinary differential equation in the data sampling scheduling unit into a multi-source stochastic differential equation; sampling multiple groups of independent audio tracks corresponding to the input text based on a multi-source stochastic differential equation; calculating a strategy gradient modulation factor by using an optimization strategy algorithm and a multi-step Markov decision function; optimizing strategy parameters of the speech synthesis model according to the strategy gradient modulation factor to obtain an optimized speech synthesis model; and obtaining a to-be-converted text, and synthesizing voice corresponding to the to-be-converted text by using the optimized voice synthesis model. And the speech synthesis accuracy is improved.

The invention discloses a rope net ladder data production scheduling and traceability system based on big data storage, and particularly relates to the field of data scheduling and traceability, comprising the following steps: the system obtains total factor data of equipment, process, quality and the like through a data perception and digital acquisition module and standardizes the total factor data; the integrated storage and quantitative analysis module constructs functions such as efficiency evaluation and quality risk to quantify production indexes; the adaptive decision optimization and scheduling module generates an optimal scheduling scheme and a dynamic rescheduling instruction based on a multi-target comprehensive decision function; the full-link tracing and self-feedback optimization module realizes full-link bidirectional tracing and drives process parameter and model self-feedback optimization; the system realizes the intelligent control of the whole production process, balances the efficiency, quality, cost and delivery target, improves the resource utilization rate and production stability, and is suitable for the precise production scene of structural members such as rope net ladders.

The invention relates to the technical field of artificial intelligence, and discloses a voice noise reduction method and device based on a vibration sensor, equipment and a medium, and the method comprises the steps: synchronously collecting a mixed signal and a reference signal of the vibration sensor, generating linear echo estimation, and calculating an initial residual error, extracting time-frequency characteristics of the initial residual error and the sensor reference signal to obtain nonlinear echo estimation; adjusting the initial residual error according to a double-talk state decision function and the nonlinear echo estimation to obtain a target residual error; and processing the target residual error through a rear Kalman filtering noise reduction module, and outputting pure near-end voice. The method has the advantages that noise in voice signals is effectively reduced, the voice recognition precision and definition are improved, the advantages of adaptive filtering and deep learning are combined, the method has good adaptability to various environment characteristics, and the response capacity and robustness to dynamic environment changes are improved.

The invention provides a watermark processing method and device, watermark processing equipment, a program product and a medium, and relates to the technical field of privacy computing. The method comprises the following steps: acquiring first data which is requested to be input into a target model by a user through an application programming interface (API); aiming at the first data, judging whether watermarking processing needs to be carried out or not; when it is determined that watermark processing needs to be carried out, based on a backdoor function corresponding to the target model, an API response corresponding to the API request is generated according to the first data, and the backdoor function is constructed according to a decision function of the target model; the API response is output to the user, the first data is added to a trigger set corresponding to the target model, and the trigger set is used for verifying an alternative model of the target model. According to the scheme of the invention, the problem that the existing digital watermarking technology is difficult to effectively defend model extraction attacks initiated through an API (Application Program Interface) is solved.

The invention relates to the technical field of ecological compensation, and discloses an ecological compensation and biodiversity monitoring method based on big data, comprising the following steps: S101, acquiring ecological data of a to-be-monitored area, regularly dividing the area into N grid units, and constructing corresponding ecological data structure units; s102, based on the ecological service characteristic parameters and the biodiversity characteristic parameters, calculating ecological service value characteristics and biodiversity pressure indexes; s103, carrying out coupling processing on the ecological service value characteristics and the biodiversity pressure index, and calculating an ecological coordination coefficient and an elastic regulation coefficient; s104, calculating an ecological compensation amount through a first preset decision function; s105, calculating a cost-benefit ratio according to the ecological service value characteristics and the ecological compensation amount, and performing automatic adjustment when the cost-benefit ratio does not reach a preset performance standard threshold value; according to the invention, accurate identification, dynamic adjustment and performance closed-loop optimization of ecological compensation are realized.

The invention provides a data private storage and access method, a medium and a system for public cloud services, and belongs to the technical field of electric digital data process.The method includes the steps that a pyramid structure neural network model is established, data access and frequency information modification are collected, and resource consumption vectors are calculated; the data classification layer and the feature extraction layer are used for carrying out feature analysis, a high and low frequency division matrix is obtained through the matrix decomposition layer, a data redundancy storage index is calculated in combination with the resource evaluation layer, a comprehensive judgment function is established for storage strategy optimization, and finally multi-level storage distribution and access control of data are achieved. According to the method, the data access characteristics can be identified more accurately, the storage resources can be allocated more reasonably, the data access process can be managed more efficiently, and the technical problem in the prior art that the public cloud service data cannot be dynamically and optimally allocated in a multi-level storage system according to the access characteristics and resource consumption is solved.

The invention relates to the technical field of intelligent driving, and particularly discloses a curve active comfortable braking method which comprises the following steps: acquiring own vehicle state information, curve information, rear vehicle state information and a road adhesion coefficient through a vehicle-mounted sensor; determining a comprehensive expected deceleration based on the above information to construct a comfortable braking decision function, wherein the comprehensive expected deceleration simultaneously meets forward curve safety and backward rear-end collision prevention safety; and according to the comprehensive expected deceleration, a vehicle executing mechanism is controlled to conduct smooth braking. According to the invention, through an innovative collaborative decision-making model, three targets of comfort, forward safety and backward safety, which are often conflicting with each other in curve braking, are successfully integrated, and a smooth, safe, intelligent and self-adaptive complete solution is provided; and the comprehensive performance of the intelligent driving system under the curve working condition is fundamentally improved.

The invention relates to power load prediction, in particular to a dynamic hierarchical granularity model power load prediction method considering time sequence factors. According to the method, the fitting capability of periodic features, trend changes and sudden influences in load fluctuation is remarkably enhanced, and the problem of feature loss caused by neglect of a time sequence dynamic weight of an existing model can be solved. Comprising the following steps: S1, performing time sequence characteristic analysis on historical power load data, and converting an original non-stationary time sequence into a stationary time sequence through difference and logarithm transformation; s2, obtaining a cleaned power load data set; s3, based on the data cleaned in S2, selecting a Gaussian radial basis function (RBF) as a kernel function, and analyzing temperature, holiday identification and linear change trend key influence factors at the same time; s4, performing dynamic multi-level granulation on the data set, and dynamically adjusting the particle level according to the data mixing degree and the particle density; and S5, fusing the time sequence kernel function and the influence factor through a decision function, and predicting the future power load.

The invention discloses a power grid emergency management system and method, and the system comprises an intelligent sensing layer which is used for collecting multi-source original data through a space-air-ground monitoring network when a disaster occurs in an environment where power grid equipment is located, carrying out the time-space calibration, extracting key features, and carrying out the risk initial judgment, generating disaster intensity field data and power grid equipment state data; the dynamic deduction layer is used for matching a target physical model from a physical behavior model library according to the disaster intensity field data and the power grid equipment state data, carrying out power flow prediction, and generating an equipment failure risk time sequence map and a power grid state prediction migration path; and the decision execution layer constructs and solves a target decision function, generates a resource scheduling scheme and outputs the resource scheduling scheme to a corresponding target terminal. A sensing-deduction-decision-evolution closed-loop system is constructed through the layers, so that a response mechanism is changed from lagging disposal to advanced pre-control, and power grid emergency resource scheduling is realized more efficiently and accurately.

The invention belongs to the technical field of automatic driving, and particularly relates to an automatic driving decision-making method and device fusing lane dynamic evaluation and safety indexes and a medium. Real-time collision risks are calculated by collecting dynamic data of a vehicle and surrounding vehicles, multi-lane traffic flow data are collected under triggering of specific requirements, and characteristics such as density, speed and flow are extracted; and a lane basic passage score is calculated by fusing the flow and the large vehicle influence, and correction is carried out by combining the lane changing intention of surrounding vehicles to obtain a dynamic lane evaluation result. And constructing a multi-objective decision function based on the safety index and the lane evaluation result, and finally generating and selecting a trajectory with the minimum comprehensive cost value in a decision period for execution. According to the invention, collaborative evaluation of the vehicle close-range safety risk and the lane passing potential is realized, and the lane evaluation can reflect the traffic flow interaction influence. The driving efficiency and the lane adaptability are optimized, and the decision-making ability of the automatic driving system in the traffic environment is improved.

The invention discloses an anti-unmanned ship unmanned aerial vehicle swarm dynamic clustering algorithm and a saturation attack path planning method, and belongs to the technical field of path planning. The invention discloses an anti-unmanned ship unmanned aerial vehicle swarm dynamic clustering algorithm and saturation attack path planning method. The method comprises the steps of constructing a multi-dimensional situation awareness index system; constructing a clustering decision function; and establishing a cluster structure dynamic adjustment mechanism, and carrying out collaborative scheduling optimization on the cluster structure. According to the invention, the problem of decision error caused by incapability of timely obtaining accurate information when communication is interrupted in the prior art is solved. According to the method, dynamic changes of the bee colony targets can be more flexibly coped with, it is ensured that each bee colony target is covered with the corresponding interception cluster, even if part of communication is interrupted, all clusters can still make decisions autonomously according to local information, certain interception capacity is maintained, basic interception tasks continue to be executed under the condition that communication is limited, and the communication efficiency is improved. It is ensured that interception preparation is completed before the bee colony reaches the defense target, and defense failure caused by response delay is effectively avoided.

The invention discloses a low-orbit satellite beam switching method and a communication terminal, and belongs to the technical field of satellite communication, and the method comprises the steps: synchronously collecting real-time multi-source data; preprocessing the real-time multi-source data to obtain a real-time multi-dimensional feature vector, and based on the real-time multi-dimensional feature vector, performing link quality prediction on links of all visible beams in a period of time in the future by adopting a prediction model to obtain an updated candidate beam set, and providing a time window for decision making; and constructing a comprehensive decision function fused with a multi-dimensional optimization target, calculating a comprehensive score of the updated candidate beam set, identifying a global optimal beam, and performing switching judgment and execution. According to the invention, the switching strategy conversion from passive response to active optimization is realized, the time delay and interruption probability of beam switching are obviously reduced, and the system resource utilization rate and the communication quality are improved.

The invention relates to the technical field of computers, and belongs to a BIOS (Basic Input / Output System) and BMC (Baseboard Management Controller)-based GPU (Graphics Processing Unit) resource intelligent dynamic optimization method and system. A four-layer collaborative architecture of a firmware layer (BIOS), a management controller layer (BMC), a system layer (operating system kernel) and a hardware layer (GPU equipment) is adopted, and the architecture is a cross-layer closed-loop optimization architecture. An optimization decision function is decoupled from an operating system kernel and is deployed in an independent hardware management unit, namely a baseboard management controller (BMC). The system collects GPU operation data in real time through an operation system kernel space and sends the GPU operation data to a BMC; an intelligent optimization engine deployed in the BMC analyzes and calculates the data to generate an optimal GPU resource scheduling strategy; the strategy is returned to an operating system kernel and finally executed by a hardware layer, and intelligent dynamic optimization of GPU resources is achieved through cross-level interaction. Therefore, a continuous intelligent closed-loop optimization link of'deployment-data acquisition-intelligent decision-making-strategy execution 'is formed.

A post-training quantification method based on activation value distribution adaptive hybrid calibration comprises the following steps: 1) acquiring a trained floating point model for target detection, and selecting representative data from original data to form a calibration data set; 2) running the trained floating point model by using data in the calibration data set to obtain activation distribution characteristics of activation values of each operation layer in the trained floating point model; 3) constructing an AH-PTQ decision function, and optimizing the AH-PTQ decision function by using reinforcement learning; 4) based on the optimized AH-PTQ decision function and the activation distribution characteristics of the activation value of each operation layer, determining a quantization parameter; and 5) quantizing the trained floating point model based on the quantization parameter to obtain a quantized integer model. According to the method, the detection precision of the model is kept to the maximum extent while the reasoning efficiency is greatly improved. According to the method, the performance loss caused by a single calibration method is effectively avoided while the model calculation overhead is reduced.

The invention provides a network traffic forwarding method and device, electronic equipment and a storage medium, and is applied to an intelligent network card, the method comprises the following steps: obtaining link quality information measured by the intelligent network card for a cross-cloud link; reporting the link quality information to a forwarding gateway in the cloud; receiving a path selection strategy issued by the forwarding gateway, the path selection strategy being generated by the forwarding gateway based on the link quality information and preset strategy information; and forwarding the network traffic according to the path selection strategy. Therefore, real-time perception of cross-cloud link quality and quick path selection based on real-time quality are realized, the problem of path selection strategy lag caused by the fact that detection and decision-making functions are concentrated on a control level in the background technology is fundamentally solved, and the quality and real-time performance of cross-cloud network transmission are remarkably improved.

The invention discloses an industrial control valve fault diagnosis method based on a cloud variational auto-encoder and an integrated geometric structure network, and the method comprises the following specific steps: collecting fault data of a small sample of a control valve, carrying out the uncertainty representation through a two-dimensional cloud model, constructing a cloud feature space with expectation, entropy and hyper-entropy as features, and carrying out the fault diagnosis of the small sample of the control valve; data enhancement based on generic normal distribution is realized; designing a cloud variational auto-encoder, optimizing a generation process through a multi-objective loss function, and ensuring that enhanced data meet cloud model generic normal distribution characteristics and distribution difference minimization constraints at the same time; the inter-class overlapping degree of the two-dimensional cloud model is mined through the cone geometric volume, and auxiliary information is provided for fault diagnosis; and establishing a lightweight SAMME integrated learning fault diagnosis framework by adopting a geometric construction network, constructing a strong classifier by fusing overlapping degree information, and finally outputting a diagnosis result according to an output decision function. According to the method, the problem of characteristic overlapping between small sample fault data classes is effectively solved, and the performance of the control valve fault diagnosis model is remarkably improved.

The invention discloses an intelligent environment equipment control method, device and equipment based on wearable brain-computer interface equipment, and the method comprises the steps: collecting the physiological index data of a specific region of the body surface of a user through the wearable brain-computer interface equipment, and transmitting the physiological index data to a data processing terminal in a Best Efort mode, the physiological index data comprises electroencephalogram data, photoelectric blood flow mapping data, body temperature data and motion data; performing data processing on the physiological index data through the data processing terminal according to a preset decision function to obtain decision data; data stream matrixes corresponding to different sending frequencies are constructed for the decision data, a data packet obtained after the data stream matrixes are packaged is transmitted to corresponding target equipment through an OSC or an LSL or a user-defined upper-layer application protocol, and the target equipment comprises intelligent environment equipment; and performing a corresponding decision operation through the intelligent environment equipment according to the received data packet. Linkage control of the wearable brain-computer interface device and the smart home system can be realized.

The invention discloses a surveying and mapping system and method for outdoor geographic surveying and mapping, and particularly relates to the field of outdoor geographic surveying and mapping, and the system comprises a preparation module, a constraint module, a model optimization module, a space-time registration module, a verification module and an evaluation module. The preparation module is used for deploying an unmanned aerial vehicle LiDAR scanning unit, a ground mobile surveying and mapping module and a distributed base station in a target area, constructing a space-time synchronous sensor network, and establishing a dynamic three-dimensional reference framework with a timestamp based on a measurement area control point; the constraint module is used for constructing a multi-threshold constraint matrix according to the terrain roughness, the vegetation coverage and the sensor performance parameters; the model optimization module is used for establishing a two-dimensional optimization model integrating spatial precision and data timeliness and forming a dynamic surveying and mapping decision function; according to the method, by introducing the dynamic weight and G-N iterative optimization, the root mean square error of registration is reduced, the convergence times are reduced, and the problems that multi-sensor registration is prone to local optimum and low in efficiency are solved.

The invention relates to the technical field of critical index monitoring methods, in particular to an intelligent critical index monitoring method and system based on clinical data. According to the method, a standardized data packet is constructed by collecting vital sign data of a patient, an inspection index group, drug intervention parameters and individual characteristics of the patient; calculating an individualized drug metabolism correction coefficient based on the liver and kidney function state and a real-time creatinine value, and dynamically generating a drug influence factor in combination with the flow rate of an analgesia pump; scene classification is carried out according to the medicine influence factor value and the blood pressure change trend, and the alarm weight of each monitoring index is dynamically adjusted; and finally, accurate risk assessment and graded early warning are realized through multi-index fusion analysis. The system comprises a data acquisition function module, a dynamic analysis function module, a weight adjustment function module and an early warning decision function module. The clinical problem that a traditional monitoring system is insufficient in sensitivity to progressive deterioration in a drug interference environment is effectively solved, and a more reliable safety monitoring scheme is provided for postoperative high-risk patients.

The invention discloses a charger supply chain data traceability management method based on a block chain, and relates to the technical field of supply chain data management, the method is constructed on a hybrid architecture of on-chain anchoring and under-chain execution, and an encryption trust anchor point is generated according to a supplier trust score and a data importance level; then, in combination with a dynamically evolved supplier trust score and a block chain network load factor, a verification depth and an anchoring frequency are decided in real time through an elastic verification trigger function; further, a total utility function of the system is solved periodically to obtain an optimal parameter combination, and the optimal parameter combination is used for calibrating a decision function to realize combination of strategic optimization and tactical response; and finally, chain storage evidence is carried out on the trust anchor point through the oracle machine, and off-chain asynchronous verification is triggered. According to the invention, the storage and consensus overhead of the block chain is significantly reduced, the expandability of the system is improved, the security, efficiency and cost can be adaptively balanced, and low-cost, high-efficiency, safe and reliable supply chain data traceability management is realized.

The invention relates to a battery replacement decision-making method for an electric unmanned mine car, and belongs to the technical field of battery replacement decision-making, and the method comprises the steps: constructing an electric unmanned mine car simulation system, and setting related static parameters of the electric unmanned mine car; establishing a multi-objective function, determining the actual condition of the current production field, and setting related dynamic parameters of a mine car, an excavator and a battery swap station in the electric unmanned mine car; dividing a parameter space related to the static scene of the electric unmanned mine car into grids, and inputting an initial parameter combination into an electric unmanned mine car simulation system; starting the electric unmanned mine car simulation system to start grid search; outputting a simulation result, and recording the effective operation time of the motorcade and the long-time sequence standard deviation of the battery swap station; and judging whether the grid search is finished or not, if the judgment result is that the grid search is finished, determining an optimal parameter combination based on an entropy weight method, determining a battery replacement decision function according to the optimal parameter combination, and guiding the battery replacement scheduling of the mine car according to the battery replacement decision function.

The invention discloses a road surface recognition method and device based on improved ShuffleNetV2, a medium and a vehicle-mounted intelligent system, and the method comprises the steps: obtaining to-be-recognized road surface image data; road surface image data to be recognized are input into a pre-trained improved ShuffleNetV2 model, a prediction result of a road surface type is obtained, a SENet module is introduced into a main branch of each basic unit of the improved ShuffleNetV2 model, and a ReLU activation function in the SENet module is replaced with an H-Sash activation function; and feeding back the prediction result of the road surface type to the intelligent driving system, so that the intelligent driving system realizes an automatic driving decision function and a vehicle driving mode regulation and control function according to the prediction result of the road surface type. Therefore, the SENet module is introduced into the main branch of the basic unit of the improved ShuffleNetV2 model to improve the pavement feature extraction capability of the model, and the ReLU activation function in the SE module adopts an H-Sash activation function to accelerate the convergence rate and improve the nonlinear expression capability of the model, so that the efficient recognition of the complex pavement type is realized.