417 results about "Shortterm Memory" patented technology

The invention discloses a data center machine room AI energy-saving control method and system, a digital twin model of a machine room operation state is constructed through a holographic perception and heterogeneous data fusion technology, centimeter-level monitoring of an equipment state and environmental parameters is realized, and the system integrates a laser radar array, an acoustic sensor and a gas sensor network. The time-space alignment of multi-modal data is completed by combining edge computing nodes, holographic mapping including thermodynamic characteristics, vibration characteristics and gas leakage risks is formed, historical temperature control strategy characteristics are extracted by adopting a variational auto-encoder based on a dynamic strategy generation mechanism of generative artificial intelligence, and a load trend is predicted by combining a long-short-term memory network. Constructing a self-adaptive strategy pool; the multi-agent reinforcement learning framework enables temperature control, equipment scheduling and power grid response to form game optimization, the strategy robustness in a complex scene is improved, and the system innovatively fuses power grid real-time electricity price and carbon transaction data so as to establish a multi-target decision system.

The invention discloses a fault diagnosis and detection system for production automation equipment. The fault diagnosis and detection system comprises a data sensing layer which is used for carrying out multi-mode signal acquisition and real-time preprocessing; the feature extraction layer is used for constructing a recursive block convolution module, capturing transient impact features in four time steps by using an L1-layer gating convolution unit, associating a 16-time-step cross-block periodic degradation mode with an L2-layer sparse attention mechanism, aggregating multi-sensor spatial-temporal features by using an L3-layer global context node, and performing multi-scale feature extraction; the causal reasoning layer is used for establishing a physical constraint driven causal graph engine and outputting a fault propagation path with probability weight; the state modeling layer is used for constructing a continuous health evolution model by adopting a Shenchang differential equation, embedding a physical constraint loss function, and performing equipment full life cycle health state prediction and residual service life estimation in combination with a three-stage memory fusion mechanism of LSTM short-term memory, differentiable neural dictionary medium-term memory and knowledge graph long-term memory; and the decision support layer is used for generating a personalized maintenance work order.

The invention discloses a network threat detection method, device and equipment and a storage medium, and relates to the technical field of network security, and the method comprises the steps: executing a preset data collection operation to capture initial multi-dimensional data, and carrying out the preset data processing operation on the initial multi-dimensional data to obtain processed multi-dimensional data; executing a preset entity extraction operation on the processed multi-dimensional data to obtain a target entity, storing the target entity in a preset database, and inputting the target entity into a preset long-short-term memory network model to obtain attack time sequence characteristics; inputting the attack time sequence features into a target graph neural network model to construct a target knowledge graph, and determining a cross-device abnormal behavior chain based on the target knowledge graph; and determining an attack chain integrity coefficient according to the cross-device abnormal behavior chain, and determining a network threat event and a target risk level by using the CVSS vulnerability score, the space-time correction factor and the attack chain integrity coefficient to complete network threat detection. The problems of incomplete single-dimensional data coverage, high false alarm rate and the like can be solved.

The invention provides a method, a device and a system for switching master and standby control centers of a smart home. In the scheme, real-time operation state data of each control center in the smart home and the number of times of downtime in a first preset time period are acquired, and based on the real-time operation state data and the number of times of downtime, a long-term short-term memory network model is used to score each control center to obtain a final score of each control center; sorting all the final scores from large to small, and determining the control centers corresponding to the final scores ranked in the front preset number as candidate control centers; an improved PBFT protocol is adopted to carry out consensus election on the candidate control hub, a target control hub is elected, the main control hub is switched to the target control hub for operation, and the target control hub meets at least one of the following preset conditions: the highest network communication efficiency, the shortest network delay and the lowest power consumption. The problem that the switching efficiency of the main and standby control centers in the smart home system is low is solved.

The invention provides a user dialogue generation method and system based on memory fusion, and relates to the technical field of artificial intelligence, and the method comprises the steps: building a user memory knowledge base based on a preset knowledge graph tool; based on the user memory knowledge base, reading current text data input by the current dialogue user and historical text data of the current dialogue user; obtaining short-term memory data, long-term memory data and scene memory data based on the user memory knowledge base, a preset large language model, a preset cue word engineering algorithm, the current text data and the historical text data; and generating a user dialogue based on the preset large language model, the preset cue word engineering algorithm, the short-term memory data, the long-term memory data and the scene memory data. According to the invention, the memory range of the user from recent interaction to long-term important information is fully covered, and the reliability of responding to the user is improved.

The invention discloses a truss structure wind-induced dynamic response prediction method and system based on physical enhancement. The method comprises the following steps: carrying out feature extraction and alignment fusion on input data containing condition parameters and wind speed time sequence data by utilizing a long short-term memory network and a physical enhancement attention mechanism; extracting multi-scale features from the fusion features through expansion convolution, and performing weighted aggregation on the multi-scale features; the physical priori knowledge of structural vibration is fused into position coding and a self-attention mechanism so as to carry out response prediction; and integrating physical model information of the truss structure and a dynamic control equation into a loss function, and calculating physical information residual loss so as to improve the physical interpretability of a prediction result. According to the method, data heterogeneity can be eliminated, complementary information can be fused, the multi-scale characteristic of wind-induced response is coped with, the accuracy and efficiency of wind-induced dynamic response prediction of the truss structure are effectively improved, and the physical interpretability and generalization ability are enhanced.

The embodiment of the invention provides a question and answer management method and device based on a large model, a storage medium and a program product. In the scheme, a'short-term first and long-term 'progressive recall strategy is introduced, that is, in a storage stage, session abstracts are generated in a segmented manner under the condition that whether the collection frequency of a preset round and the topic category are changed or not, the session abstracts are sequentially written into a short-term memory storage area and sink to a long-term memory storage area after the preset storage duration is reached, and a subsequent recall path is pre-buried; in the acquisition stage, the latest abstract closest to the current round is recalled from the short-term region, and if the abstract is missing, the cross-session or cross-round historical session abstract continues to be complemented from the long-term region. According to the mechanism, session context management of'instant light and thin 'and'long-term consistent' is considered under the condition that the computing power and the bandwidth cost are not remarkably increased, accurate contexts are provided for complex session scenes with long-period, multi-topic and multi-file cooperation, and a large question and answer model can make more accurate and more consistent questions and answers based on complete and related context information.

The invention provides a time-space attention-driven soil humidity prediction method in a domestic supercomputing environment, and the method comprises the steps: constructing a time-space feature dynamic fusion soil humidity prediction network model based on attention guidance; the attention-guided spatio-temporal feature dynamic fusion soil humidity prediction network model comprises a convolutional long-short term memory network basic framework and a spatio-temporal attention mechanism module. The introduction of the ConvLSTM network effectively integrates the time sequence and space information of the soil humidity, the potential space-time dependence in the data is fully utilized, the space-time attention mechanism enables the model to adaptively pay attention to important time periods and space regions by dynamically adjusting the weight between time steps, and the accuracy of the model is improved. The limitation of fixed feature selection in a traditional method is avoided, so that the prediction precision is improved. The model can better capture space-time dynamic feature information, further identifies the relationship between the influence factor and the soil humidity, and especially shows unique advantages in complex space-time feature processing and modeling of long-time sequence data.

The invention relates to the technical field of crane equipment health monitoring, in particular to a crane running state health monitoring system and method. A sensing data acquisition unit is used for acquiring a winding drum vibration harmonic component, a steel wire rope leakage magnetic field gradient and a pulley block real-time load; the data analysis unit performs rotating speed synchronous variational mode decomposition on the vibration component to extract resonance characteristics, performs temperature and stress double-compensation correction on a leakage magnetic field gradient, quantifies an energy entropy attenuation rate through wavelet packet decomposition, constructs a phase difference model of a load and vibration to output a slip risk phase offset, calculates a load spectrum damage cumulant, and calculates a load spectrum damage cumulant; and after the four heterogeneous features are fused, a residual life coefficient is output through a dual-channel convolution-long and short-term memory hybrid neural network, and an execution unit triggers crane speed reduction control when the residual life coefficient is lower than a threshold value, so that the problems of insufficient multi-source data fusion and lack of dynamic compensation in the traditional technology are solved, and the fault early warning accuracy is improved.

The invention discloses a complex metering sensor abnormal feature analysis method based on long-term accumulated data, and relates to the technical field of state monitoring and fault prediction. Static statistical characteristics and dynamic frequency characteristics of data and transient changes in non-stationary signals can be comprehensively captured, meanwhile, a model in which a double-layer long-short-term memory network is combined with an attention mechanism is constructed, short-term time sequence dependence in a first-layer LSTM learning data fragment and long-term evolution trend between second-layer LSTM learning fragments are constructed, and the time sequence dependence in a second-layer LSTM learning data fragment is constructed. The attention mechanism focuses on the key period, and the deep fusion from feature extraction to model construction enables the model to accurately identify the difference between normal data and abnormal data, thereby realizing the accurate detection of the sensor abnormality, and in the practical application, the normal fluctuation and real abnormality of the sensor can be effectively distinguished, and the accuracy of the sensor abnormality detection is improved. And reliable guarantee is provided for stable operation of the system.

The invention discloses a water conservancy and hydropower construction resource management scheduling method and system based on artificial intelligence. The method comprises the following steps: collecting construction multi-source data in real time; based on an ST-GNN space-time diagram neural network, predicting the resource demand of each construction area in a future T time period, and combining with an LSTM long short-term memory network to perform joint modeling on the construction progress and environmental disturbance to obtain a demand prediction model; adjusting an inertia weight and a cognitive factor of the demand prediction model by using an IPSO improved particle swarm optimization algorithm, and learning an optimal scheduling strategy in a simulation environment in combination with an RL reinforcement learning training agent to obtain a target demand prediction model; and inputting the construction multi-source data into the target demand prediction model to output a scheduling scheme, and performing digital twin simulation verification and adjustment on the scheduling scheme to obtain a target scheduling scheme. And the prediction accuracy of future resource demands and the management scheduling efficiency are improved.

The invention relates to a man-machine interaction method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: acquiring interaction content input by a user; scene recognition is carried out on the interaction content through a large language model, and a scene label of the interaction is determined; determining a target long-term memory partition corresponding to the scene tag from a plurality of long-term memory partitions preset for the user; inputting target long-term memory content in the target long-term memory subarea and short-term memory content stored in a short-term memory area preset for the user into an intelligent agent; the intelligent agent is used for generating reply content for the interaction content according to the target long-term memory content and the short-term memory content. By adopting the method, effective association and collaborative calling of different scene memories can be realized, and the dynamic requirement of a user on coherent interaction in multi-scene switching is met.

The invention discloses a cross-regional computing power resource collaborative allocation method based on computing power centers, and relates to the technical field of computing power resource scheduling and optimizing.The cross-regional computing power resource collaborative allocation method comprises the steps that real-time load data, historical task execution data and network delay data of all computing power centers are collected, and a regional load feature database is constructed; predicting the load demand of each computing power center in a future time window by using a long short-term memory network model to generate a load prediction value; calculating a resource gap coefficient and a resource margin coefficient of each region according to the load prediction value and the current resource capacity, identifying a resource insufficient region and a resource surplus region, and generating a resource collaborative matching matrix between the regions; and optimizing and solving the cross-regional task allocation scheme by adopting an improved genetic algorithm to generate an optimal resource allocation strategy, and allocating the to-be-processed task to a corresponding computing power center according to the optimal resource allocation strategy. According to the method, the cooperative utilization rate and the distribution efficiency of the computing power resources in the cross-regional scene are effectively improved.

The invention relates to an intelligent water affair remote monitoring and control system based on the Internet of Things, in particular to the field of intelligent water affair remote monitoring and control, and the system comprises the steps: firstly, pre-training a long and short-term memory network model through a cloud, and generating a lightweight edge prediction model to reduce calculation and transmission loads; the data transmission module effectively reduces the occupation of transmission bandwidth based on a dynamic quantization threshold value of a residual error and a differential coding technology, meanwhile, the high precision of the data is kept, the verification feedback module monitors the accuracy of the transmission data in real time through confidence coefficient detection, and triggers model re-calibration when the confidence coefficient is reduced, so that the long-term stability of the system is ensured, and the reliability of the system is improved. The sampling optimization module dynamically adjusts the sampling frequency according to the confidence coefficient and the residual fluctuation characteristics, balance is achieved between bandwidth occupation and reconstruction precision by using the Lyapunov optimization theory, the real-time performance and accuracy of water affair monitoring are improved, and meanwhile bandwidth consumption and energy consumption are effectively reduced.

The invention discloses a heat pump system state anomaly detection method based on a depth auto-encoder, and the method comprises the steps: collecting compressor data, and carrying out the standardization processing to construct a multi-dimensional time sequence; a spatial-temporal feature extraction depth auto-encoder with a thermodynamic coupling attention mechanism is constructed, coupling attention is utilized to calculate physical parameter coupling strength weights to extract spatial features, time features are extracted in combination with a long and short-term memory network, and normal state data are reconstructed and predicted through a decoder after fusion; residual vectors of predicted normal state data and original data are calculated, and a weighted mahalanobis distance is calculated by using a covariance matrix to generate an abnormal score; and constructing a sliding probability distribution model based on historical normal data, calculating a current score occurrence probability, and comparing the current score occurrence probability with a preset threshold to output an anomaly detection result. According to the method, a multi-physical parameter space coupling relationship and a time evolution rule are captured through a thermodynamic coupling attention mechanism, and the anomaly detection accuracy and robustness are improved.

The invention relates to the technical field of artificial intelligence, can be applied to the medical field and the financial science and technology field, and discloses a dialogue method and device based on a memory scheduling framework, equipment and a medium, which are applied to a bank virtual customer service scene or an intelligent triage and pre-inquiry scene. Obtaining a target dialogue page from all dialogue pages of the current dialogue chain in the short-term memory queue; a target topic segment and a target dialogue page are retrieved from the medium-term memory module, and target feature information is retrieved from the long-term personalized memory module; constructing a structured cue word, and generating a target response based on the structured cue word; storing the newly constructed dialogue page in a short-term memory queue; if the short-term memory queue is full, removing the dialogue page from the head of the queue; updating the topic segment in the medium-term memory module based on the removed dialogue page; and updating the long-term personalized memory module according to the popularity of the topic segment in the updated middle-term memory module. The dialogue response accuracy is improved.

The invention relates to the technical field of detection of toner cartridge powder, and discloses a method and a system for improving the uniformity of toner cartridge powder, which are used for continuously sampling powder flow to obtain a real-time weight distribution matrix. And when abnormal flow is detected, noise is eliminated, processed data are input into a fuzzy PID controller, and feeding parameters are dynamically adjusted. Meanwhile, powder is promoted to be uniformly dispersed in combination with a vibration frequency modulation technology, and a weight change trend is predicted by utilizing a long-short-term memory network algorithm. In addition, the method further comprises an anomaly detection and fault diagnosis mechanism, control parameters are continuously adjusted through closed-loop optimization, and finally a batch quality tracing system is established. By means of the method, the precision and consistency of toner cartridge powder conveying can be effectively improved, and intelligent control and quality management in the production process are achieved.

The invention specifically discloses a brain-like reinforcement learning method and system based on hierarchical experience playback, and relates to the technical field of reinforcement learning and brain-like computing. The method comprises the steps that S1, observation data are collected and preprocessed; s2, initializing an experience buffer pool, an actor network, a commentator network and a corresponding target network, and performing parameter initialization; s3, exploring noise is initialized, actions are selected from the actor network according to the current state and executed, and obtained experience samples are stored in an experience buffer pool; s4, obtaining a new sample from the experience buffer pool, and updating the short-term memory pool; s5, determining whether partial experience in the short-term memory experience pool is transferred to the long-term memory experience pool or not by using an attention discrimination module; and S6, updating parameters of the actor network, the reviewer network and the corresponding target network. By adopting the method, the experience utilization rate of the intelligent agent is improved, the reinforcement learning performance is improved, and the method has wide application potential in multiple fields.

The invention discloses an intelligent data center energy scheduling optimization method based on machine learning. The method comprises the following steps: acquiring data to form a multivariable time sequence; the improved PatchTST model calls a multi-level memory interaction structure to establish short-term memory and long-term memory, and an attention constraint energy consumption memory module is introduced to output prediction features; inputting the prediction features into a decoding layer of the improved PatchTST model; constructing an energy scheduling multi-objective optimization problem, and generating an equipment control instruction set by adopting an NSGA-III algorithm; collecting an actual execution result to form feedback data; performing deviation evaluation and strategy updating on feedback data through an energy self-feedback correction process; and judging whether the energy consumption prediction error and the energy scheduling deviation meet a preset termination condition or not. The method is suitable for intelligent energy scheduling and operation efficiency optimization in multi-energy coupling scenes such as an intelligent data center.

The embodiment of the invention provides a context information management method and device based on hierarchical memory, equipment and a medium, and the method comprises the steps: analyzing a task request to generate a sub-task node sequence containing a target description and acceptance function, and arranging a plurality of agents to cooperatively execute a task, and after the audit is passed, a complete execution context is stored in a long-term memory, and a structured abstract is generated and stored in a short-term memory, so that the problem that the context management mechanism of the existing multi-agent system is single is effectively solved, stable maintenance of cross-session cognitive continuity is realized, and the efficiency of the multi-agent system is improved. The method improves the execution reliability of a complex long-process task, optimizes the information storage and retrieval efficiency through hierarchical memory, reduces the risk of semantic deviation accumulation and amplification, clarifies the task target and acceptance standard of each stage, enhances the multi-agent cooperation consistency, and improves the efficiency of task execution. And the execution efficiency and the task completion quality of the intelligent agent system in a complex application scene are comprehensively improved.

The invention relates to the technical field of weather prediction, and discloses a weather prediction method based on an improved quantum long short-term memory network, which comprises the steps of inputting weather data into a CGRU model to perform spatial feature extraction on the weather data, and then inputting an output hidden state sequence into an HAQLSTM model to perform prediction, the HAQLSTM model is an improvement of a quantum long short-term memory network model, and the quantum long short-term memory network model is an improved quantum long short-term memory network model. A parameterized variable component sub-circuit is adopted, an attention mechanism and residual connection are added, a quantum long-short-term memory network serves as a time modeler, the residual connection enhances information transmission, the attention mechanism dynamically balances the importance of different parts of input data, in the processing process, a self-attention mechanism is adopted to calculate the correlation weight of input sequence elements, and the correlation weight of the input sequence elements is calculated. Four parallel parameterized variable component sub-circuits are used for carrying out key calculation so as to improve the model performance; the problems that an existing weather prediction model network is insufficient in expression ability, and the efficiency of capturing the long-term dependency relationship in the sequence is low are solved.

The embodiment of the invention provides a context construction method and device for an agent and a storage medium, and the method comprises the steps: obtaining the current input information of the agent in one interaction round, and carrying out the analysis to generate a current semantic representation; determining a semantic association degree between the current semantic representation and the context of the current dialogue task, and calculating a long-term value score of the current semantic representation; under the condition that the semantic association degree is greater than a first preset threshold value, storing the current semantic representation into a short-term memory library; under the condition that the long-term value score is greater than a second preset threshold value, storing the current semantic representation into a long-term memory library; when the intelligent agent needs to generate a response for the current input information, searching target memory content related to the semantics of the current input information from the short-term memory library and the long-term memory library; and combining the target memory content with the current input information to form prompt information, and inputting the prompt information into a large language model to generate a response for the current input information.

The invention relates to a multi-time scale scene analysis-based micro-grid day-ahead and intra-day optimal scheduling method, which belongs to the field of micro-grid scheduling, and is characterized in that a variational mode decomposition (VMD)-long short-term memory network (LSTM) multi-scale prediction framework is constructed, ultra-short-term precision is improved through variable mode decomposition and frequency division prediction, a Canopy-spectral clustering-K-means hybrid algorithm is designed, and the optimal scheduling of a micro-grid is realized. A typical scene is generated based on Latin hypercube sampling (LHS), the scene coverage capability is enhanced, a day-ahead and intra-day two-stage optimization model is finally constructed, a high-dimensional problem is rapidly solved by adopting a mixed integer programming algorithm, and theoretical support is provided for high-proportion renewable energy consumption and micro-grid refined scheduling.

The invention discloses a PCB (Printed Circuit Board) defect detection method based on machine vision, which relates to the related technical field of computer vision, and comprises the steps of multi-modal data acquisition, data preprocessing and feature extraction, feature fusion, classification, positioning and marking of extracted feature vectors by adopting a support vector machine as a classifier, and establishment of a defect sample library. According to the method, each modal data reflects the state of the PCB from different aspects, the fusion of the multi-modal data can be mutually verified and supplemented, misjudgment and missed judgment are reduced, the related samples in the sample library can enable the model to know the performance of the defects on different materials, so that the defects can be identified more accurately in the detection, and the detection accuracy is improved. By acquiring the image sequences of the same circuit board in different production stages and processing the image sequences by using the long-short-term memory network model, the change trend of the defects in time sequence can be captured, so that the development of the defects in the future production stage can be predicted.

The invention belongs to the technical field of artificial intelligence, and discloses a large model memory management and optimization system and method based on a vector data lake. Comprising a multi-dimensional memory vectorization coding and hierarchical management module, an intelligent retrieval and dynamic updating module, and a memory optimization strategy and interactive evaluation and cyclic adjustment optimization module based on a reflection and backtracking mechanism. According to the large model memory management and optimization system and method based on the vector data lake, a multi-dimensional and hierarchical memory storage and dynamic retrieval framework is constructed, collaborative management of long-term / short-term memory is supported, efficient reasoning, knowledge reuse and continuous learning ability of an intelligent agent in a complex dynamic task are achieved, and the system and the method have the advantages that the system and the method are simple and convenient to operate. Therefore, the robustness, the adaptability and the task migration capability of the intelligent system are remarkably improved.

The invention discloses a method and equipment for eliminating network environment defects and self-healing a closed loop based on RAG and a medium, and the method comprises the steps: constructing a multi-modal knowledge base, and carrying out the regular updating based on a large-scale language model; performing fusion analysis by using a long-short term memory attention model and a graph neural network model, capturing time sequence and topology anomalies, generating a structured early warning report, and associating the structured early warning report with a knowledge base; a three-level retrieval strategy is adopted, and emergency, radical treatment and prevention schemes of multi-objective optimization are extracted from the knowledge base; utilizing an improved time sequence directed acyclic graph algorithm to dynamically select parallel self-healing operation; and automatically adjusting the knowledge base based on the self-healing execution result and the feedback index. According to the method, through deep fusion of the dynamic multi-modal knowledge base and the retrieval RAG technology, normal form transition of equipment defect elimination from passive response to active prediction is achieved, compared with a traditional method, the defect positioning accuracy is greatly improved, and the problem of misjudgment caused by single data source analysis is solved.

This disclosure describes a system and method for generating structured reports from video footage using artificial intelligence. The system extracts frames from video inputs, identifies and tracks objects across frames, and applies importance adjustments based on context. A Long Short-Term Memory (LSTM) network analyzes temporal patterns and integrates spatial data from feature point identification and geomapping techniques. Event detection modules identify key actions, while scene understanding and semantic segmentation provide environmental context and pixel-level detail. Outputs from these analyses are processed by a generative AI engine, specifically a large language model (LLM), to produce a coherent natural language description of the recorded events. A second LLM formats the narrative according to the template required by the organization, such as a police department, ensuring compliance with specific standards. Users can review and edit the final report through an interface before submission.

The invention discloses a part polishing surface roughness prediction method and device, equipment and a storage medium. Comprising the following steps: training a roughness prediction model of the cascaded long-short-term memory network based on a constructed sample data set to obtain a trained roughness prediction model; the polishing process parameters of the part and the surface roughness of the previous moment are collected on line; the polishing process parameters and the surface roughness at the previous moment are input into the roughness prediction model, and a change value sequence of the surface roughness of the part is obtained from the current moment within k moments after the current moment; and on the basis of the change value sequence of the surface roughness of the part and the surface roughness at the previous moment, obtaining the predicted surface roughness at k moments after starting from the current moment. The invention provides a part polishing surface roughness prediction method based on a cascaded long-short-term memory network model. The part surface roughness can be predicted on line under the complex polishing working condition.

The invention discloses a generator set anomaly detection method based on edge calculation. The method comprises the following steps: S1, generating multichannel working condition data of a standardized generator set; s2, deploying a lightweight long short-term memory network prediction model in an industrial edge computing node; s3, constructing a multi-mode residual error map; s4, performing generator set abnormity judgment on the local residual error sequence and outputting generator set abnormity candidate events; and S5, generating a generator set anomaly causal interpretation graph for the generator set anomaly candidate events by using an interpretive analysis algorithm, wherein the generator set anomaly causal interpretation graph reveals the contribution relationship of each working condition feature to the generator set anomaly confidence coefficient. According to the method, the traceability and operability of fault positioning are remarkably improved, and operation and maintenance personnel are assisted in accurately formulating a maintenance strategy.

The invention discloses an enterprise-oriented multi-user electric quantity prediction method, and belongs to the technical field of electric quantity prediction, and the method comprises the steps: obtaining enterprise electric quantity related data, and carrying out the preprocessing of the data, and obtaining a training set, a verification set, and a test set; inputting the training set and the test set into the long short-term memory network for training, and verifying the performance of the long short-term memory network based on the verification set; inputting the training set into the verified long-short-term memory network to obtain multi-dimensional features, and training an extreme gradient lifting algorithm based on the multi-dimensional features; constructing a hybrid model based on a long short-term memory network and an extreme gradient lifting algorithm; obtaining enterprise electric quantity related data in a specified time period, performing preprocessing to obtain a prediction data set, and inputting the prediction data set into the hybrid model to obtain an electricity consumption prediction value of the corresponding enterprise; according to the invention, the problem of low power consumption prediction accuracy of the corresponding enterprise caused by the influence of multi-dimensional unstable factors in the prior art is solved.