10198results about How to "High speed" patented technology

The invention relates to power distribution network fault processing equipment applied to the technical field of power distribution, and aims to improve the fault prediction, diagnosis and processing capabilities of a power system. The equipment comprises a pre-training module, a neural network architecture module, a data acquisition layer, an edge calculation layer, a core processing layer, a context learning module, a reasoning processing module, an output and interaction layer and a continuous learning and improvement layer, and is characterized in that a large-scale pre-trained Transform model is utilized, and professional knowledge of a power system is combined; according to the method, deep understanding and analysis of a complex power grid state are realized, through multi-source data fusion, edge calculation and central cooperative processing, the equipment can monitor the power grid state in real time, accurately predict potential faults and provide intelligent diagnosis and repair suggestions, and model pre-training and optimization are performed by adopting self-supervised learning and federated learning technologies; using reinforcement learning to optimize a fault response strategy; the interpretability of the model is realized, and the decision transparency is improved.

The invention relates to the field of natural language processing, and discloses an SQL statement generation method, system and device based on a large model. Respectively carrying out vectorization processing and document processing on the metadata and the metadata description text information from the database, and storing the metadata and the metadata description text information into a vector database and a full-text retrieval library; in response to the query instruction, respectively performing query matching on the vector database and the full-text retrieval library, screening matching results which are ranked in the front and are preset ranks according to the similarity from high to low, and determining an optimal SQL statement list and optimal metadata; on the basis of the current language of the query instruction, generating a cue word of the current language in combination with the optimal SQL statement list and the optimal metadata; the large model of the preset type is determined according to the language type of the cue word, the preset large model is called to conduct reasoning on the cue word, and the SQL statement is generated. Based on the large model and the generative AI technology, the accuracy of the generated SQL statement is improved, the use threshold of non-technical personnel is lowered, and the query efficiency of the SQL statement is also improved.

The invention relates to the technical field of information security, in particular to a power distribution Internet of Things cloud side end collaborative interaction security protection system, which comprises a network flow monitoring module, an abnormal flow identification module, a security threat response module, a network attack early warning module, a behavior pattern analysis module and an access authority management module. According to the method, the network flow data is collected and analyzed in real time, the abnormal flow recognition speed and accuracy are enhanced, the security threat response speed and efficiency are improved, measures are taken in time at the early stage of a problem, the risks of data leakage and network attacks are reduced, and the timeliness of defense measures is improved by combining security threat response and network attack early warning; by analyzing the relevance between threat events, the complex multi-stage attack activity is effectively predicted and identified, the access data and the communication mode of the equipment are monitored in real time, and the access authority and the trust level are adjusted, so that the security protection is more targeted and flexible, and the management efficiency of the risk equipment is improved.

The invention belongs to the technical field of power system monitoring, and particularly relates to a wireless cable temperature measurement system and method, and the system comprises an operation information collection module, a layout planning analysis module, a data standardization module, a change trend analysis module, an early warning threshold adjustment module, and a fault positioning analysis module. According to the invention, cable operation data and environment information are analyzed, the coverage range, data transmission delay and signal attenuation are considered, the layout of temperature sensors is optimized, the response speed and data accuracy of a temperature sensor network are enhanced, temperature data are formatted and processed, time sequence analysis is carried out, and the temperature change trend is evaluated. Abnormal temperature risk recognition is achieved in the early stage, the accuracy of fault prediction is improved, the cable temperature risk monitoring threshold value is adjusted in combination with cable specifications and meteorological information, the timeliness and effectiveness of risk management are improved, the fault response speed and the system stability are improved, the maintenance cost is reduced, and the reliability and safety of a power grid are improved.

The invention provides a private domain live broadcast room hotspot prediction and adaptive routing method based on swarm intelligence, and relates to the technical field of data processing, and the method comprises the steps: constructing a dynamic interest community through a dynamic graph neural network, extracting group interaction mode features through a multi-layer graph attention network, and carrying out the group interaction mode features; the method comprises the following steps: generating time sequence correlation features in combination with an improved bidirectional gating loop unit, extracting high-order semantic features, performing hotspot prediction through a multi-task learning framework, constructing a multi-level network topology model according to a prediction result, and performing path exploration in combination with an improved heuristic search algorithm to obtain an optimal transmission path. Flow distribution is carried out through a weighted polling algorithm, a deep learning distributed load balancing controller and a congestion control algorithm are combined, the data transmission rate is dynamically adjusted, and self-adaptive routing pushing of live broadcast content is achieved.

The invention relates to the technical field of power grid fault repair, in particular to a power grid fault emergency rescue method. The method comprises the following steps: acquiring topological structure data, key equipment parameters and real-time operation state data of a power grid; constructing a power grid digital twin model according to the power grid topological structure data, the key equipment parameters and the real-time operation state data, and performing real-time state evaluation to obtain fault risk early warning data and real-time fault condition data; when the real-time fault condition data shows that a fault occurs, performing fault point positioning and fault type determination based on deep learning according to the fault risk early warning data and the real-time operation state data to obtain fault diagnosis data; and constructing a fault influence range model according to the fault diagnosis data and a preset FACTS and HVDC characteristic model. According to the method, deep learning, a graph theory and a multi-objective optimization technology are fused, and intelligent fault identification, influence range modeling and accurate emergency disposal scheme optimization are realized.

The invention discloses a safety production supervision system and method based on a multi-modal large model, and aims to solve the problem of large inspection workload of manual checking of potential safety hazards in an existing enterprise production scene. By acquiring image information and position information of a hidden danger scene to be recognized, potential safety hazards possibly occurring in the enterprise production process are detected and marked by utilizing technologies such as a visual large model and a large language model, and rectification suggestions are given according to corresponding safety regulations. The system can monitor the potential safety hazards in the production process of an enterprise in an all-weather manner, remarkably improves the potential safety hazard monitoring efficiency, reduces the manual workload, reduces the labor cost, and provides a basic guarantee for the safety production of the enterprise.

The invention provides a modular power supply system configuration method and system for a micro-module machine room, and relates to the technical field of electric power, and the method comprises the steps: collecting power utilization state data and load distribution data of functional equipment in the micro-module machine room, building a power supply network topology model, dividing a power supply system into a first-stage load, a second-stage load and a third-stage load, an independent power supply loop and a data acquisition unit are respectively configured in the first-stage load, the second-stage load and the third-stage load; a power supply network topology model is updated according to the power utilization data acquired by the data acquisition unit, a reinforcement learning algorithm is adopted to generate an adaptive power distribution strategy, and a modular energy storage unit is arranged to provide a standby power supply for a primary load and a secondary load; and constructing a machine learning fault prediction model based on the power consumption data, and dynamically adjusting a power supply path and a power distribution scheme of a power supply loop.

The invention provides a PCBA surface defect detection method and system based on image recognition, and the method comprises the steps: collecting and constructing a multi-class PCBA overall defect image data set, and carrying out the preprocessing; constructing a pre-training neural network model, and classifying the preprocessed PCBA overall defect image data set; constructing a local target identification method based on a YOLOX network according to an overall defect classification result; and carrying out local defect detection on the PCBA surface based on a local target identification method. According to the method, the overall classification and local detection strategies are comprehensively applied to reduce the burden of the model, and the detection precision and speed are improved. And an attention mechanism is introduced to improve the performance and generalization ability of the model. Data enhancement, consistency processing, classification labeling and the like are carried out on an image data set, and the defect detection effect of the model is improved. And multiple optimization strategies such as structure improvement, loss function improvement and pruning lightweight are adopted for the network model, so that the image target detection performance is effectively improved.

The invention discloses a domain-adaptive retrieval enhancement generation method and system, and the method comprises the steps: carrying out the document analysis and semantic partitioning of a document through a semantic understanding model and a document rule, and storing document fragments; on the basis of the large language model and a preset question library, generating a question and disassembling the question; performing correlation evaluation and sorting on the initial retrieval results in combination with a retrieval technology; candidate content most matched with the cue words is screened out through a large language model, and question-retrieval fragments are scored and marked; performing fusion on the initial retrieval result and the scoring and labeling result to construct positive and negative samples, and constructing a supervised data set; and based on a preset loss function, utilizing the supervised data set to carry out supervised training on the knowledge semantic search model, replacing the RAG mixed search module, and carrying out continuous iteration. By means of the technical scheme, new domain knowledge and operation feedback data can be flexibly applied, and domain self-adaptive retrieval enhancement generation is achieved.

The invention discloses a new energy power generation equipment health management platform based on a large model, and relates to the technical field of power generation equipment health management. The system comprises a multivariate data acquisition and region identification module, a data preprocessing and region adaptation unit, a region perception large model analysis module, an intelligent operation and maintenance decision and scheduling module and a spare part inventory optimization sharing module. The multivariate data acquisition and area identification module deploys multiple types of sensors at key equipment parts of photovoltaic power generation stations in different areas, acquires equipment operation parameters and environment state data, endows the areas with unique codes and feature tags, and ensures that the data are traceable and are associated with area characteristics; according to the invention, the health management efficiency and accuracy of the new energy power generation equipment are significantly improved; the system not only realizes real-time monitoring and fault early warning of the equipment state, but also reduces the maintenance cost and improves the system operation efficiency by optimizing the operation and maintenance resource configuration and intelligent spare part inventory management.

The invention relates to the technical field of mechanical joints, in particular to a humanoid robot linear electric drive joint which comprises a shell, a front end cover and a rear end cover, the front end cover and the rear end cover are fixed to the two ends of the shell respectively, and an execution assembly and a drive control assembly are arranged in the shell; the execution assembly comprises a reverse planetary roller screw and a motor, and the drive control assembly comprises an encoder composed of a coded disc and a magnetic ring, a pull pressure sensor and a driver. Aiming at the technical problem that an existing linear joint has defects, a reverse planetary roller lead screw is adopted as a main transmission component, and the lead screw, a roller and a nut of the reverse planetary roller lead screw are in linear contact, so that high precision, long service life, high integration level and high thrust density can be achieved while high bearing and high speed are achieved; therefore, the method is suitable for use scenes of humanoid robot joints.

The invention discloses a disaster emergency rescue command system and method, and relates to the technical field of rescue command systems. Comprising an information collection module which collects information, including disaster situations, personnel distribution and environmental conditions, of a disaster site through sensors and communication equipment; the collected information is input into the system, so that accurate disaster assessment can be conveniently obtained; the decision support module determines optimal allocation of rescue resources by using a linear programming model according to disaster assessment provided by the information collection module, and plans a rescue path by using a graph theory algorithm; and the command control module is used for converting the rescue decision of the decision support module into a specific rescue instruction. According to the system, the disaster assessment time can be shortened through real-time monitoring and rapid data processing, and the rescue decision-making speed is increased; optimal configuration of resources is realized through an algorithm, resource waste is avoided, and resource availability at a critical moment is ensured.

The invention relates to the technical field of data processing, in particular to a real estate surveying and mapping data processing method and system based on intelligent data. The method comprises the following steps: acquiring multi-source real estate surveying and mapping data; performing space-time synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping space alignment data; real estate space feature extraction is carried out on the multi-source real estate surveying and mapping space alignment data to obtain real estate space feature data; performing cross-domain feature fusion on the multi-source real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data; public surveying and mapping point confirmation is carried out on the multi-source real estate surveying and mapping data through the real estate surveying and mapping fusion spatial feature data, and real estate surveying and mapping public surveying and mapping point data are obtained. Through multi-source data space-time synchronization, feature fusion, distortion correction, high-dimensional space reconstruction, semantic tag association and chain storage, the efficiency and accuracy of real estate surveying and mapping data processing are improved.

The invention provides a network security risk assessment system and method, and relates to the technical field of network security. The network security risk assessment system comprises a data acquisition layer, the data acquisition layer is connected with an analysis processing layer, the analysis processing layer is connected with an assessment decision-making layer, the assessment decision-making layer is connected with a display interaction layer, and the data acquisition layer acquires business scene data, network topology data, user behavior logs and social network conditions. According to the system, through highly integrated module design, 'information isolated island 'between traditional security tools is broken, comprehensive security situation awareness is realized, novel and unknown threats are dealt with by utilizing situational analysis and dynamic adjustment capability, false alarms and missing alarms are remarkably reduced, and the system is based on machine learning and behavior analysis. Intelligent priority ordering and automatic response can be realized, and the speed and accuracy of risk identification and response are improved.

The invention discloses a jet aerator with low energy consumption and high oxygenation efficiency. The jet aerator comprises a Venturi tube and a quick-pass rhombic tube which are of a split structure, multi-rod supports are installed on the inner wall faces of round pipes at the two ends of the venturi pipe and support tail hook bionic stirring blades, a double-end reverse screw is arranged in the venturi pipe, one end of a quick-pass rhombic pipe is connected with the venturi pipe, the other end of the quick-pass rhombic pipe extends into an air suction chamber, and the upper portion of the air suction chamber is connected with an air supply pipe. The end, away from the Venturi tube, of the air suction chamber is connected with a mixing cavity tube, the mixing cavity tube is connected with the front end of a throat tube, a divergent wing-like blade set and a special-shaped taper hole plate are arranged in the mixing cavity tube, and a grid tray scattering nozzle is arranged in the throat tube; compared with a circular pipeline, the quick-passing rhombic pipe can provide higher water conveying capacity; the gradual change spiral body design on the double-end reverse screw can generate vortexes and turbulent flows, the turbulent flow intensity of water flow is improved, the mixing and diffusion capacity of the water flow is improved, and therefore the oxygenation efficiency is improved.

The invention discloses a remote Internet of Things control management system and method based on fire fighting, and belongs to the technical field of Internet of Things. The system comprises an image recognition module which obtains a video stream of a fire scene through a monitoring camera, and carries out the real-time analysis and recognition of an image through image processing and a deep convolutional neural network; the gas recognition module is used for monitoring the gas concentration of a fire scene in real time and recognizing gas components by using a gas recognition algorithm; the data fusion analysis module is used for carrying out feature fusion on the data acquired by the image recognition module and the gas recognition module, and carrying out analysis and modeling on the fused data; the decision support module is used for performing fire risk assessment according to an analysis result of the data fusion analysis module; based on historical data and the scene model, performing simulation and prediction of a fire development trend; and the remote internet-of-things control module is used for providing data for checking fire scene conditions in real time, so that a user can remotely control all equipment and devices of the fire extinguishing system.

The invention discloses a real-time three-dimensional fusion reconstruction method for a ship comprehensive test scene, and the method comprises the steps: carrying out the preprocessing of a target object image data flow, converting an image coordinate system into a camera coordinate system, obtaining a sparse point cloud model, and constructing a voxel three-dimensional grid; the method comprises the following steps: constructing a scale space by using a Gaussian difference pyramid to detect key points of an image under different scales, calculating a gradient direction histogram around the key points and taking the gradient direction histogram as a descriptor, matching the descriptor by using an Euclidean distance, and estimating relative pose transformation between the images to complete a local matching process. Projecting and mapping the local frame block to a reference frame to form a key frame, and entering a global matching process; and extracting a surface grid of the three-dimensional model from the dense body grid by adopting a Marching Cubes algorithm, traversing each cube unit in the surface grid, and obtaining distance information from a vertex to a nearest surface based on the cube units, thereby generating a final three-dimensional model of the test target object.

The invention relates to the technical field of remote monitoring, in particular to a mobile terminal remote control monitoring system and method, and the system comprises a video dynamic coding module, a content importance analysis module, a cognitive load adjustment module and an audio optimization and alarm module. According to the method, the change of the network bandwidth can be responded in real time by dynamically adjusting the video coding parameters, the stability and adaptability in data transmission are remarkably enhanced, the dynamic content and color change are accurately captured by analyzing the video frames, and key events are immediately positioned and extracted, so that the emergency response speed and precision are greatly improved, and the data transmission efficiency is improved. Cognitive resources are dynamically distributed by utilizing video stream complexity evaluation, resource configuration is adjusted according to actual requirements, monitoring quality is guaranteed, resource use efficiency is optimized, audio processing is optimized, real-time alarm strategies are adjusted, clear transmission of sound information and alarm timeliness are guaranteed, and the overall response capability and effect are improved.

The invention belongs to the technical field of model training, and particularly relates to a large model increment training method and system based on dynamic sparsification. The method comprises the following steps: S1, evaluating the parameter importance of a large model by adopting a multi-dimensional evaluation method, and reflecting the contribution of parameters to the performance of the large model; s2, performing dynamic sparsification control on the large model structure by adopting a self-adaptive structure adjustment method; s3, performing incremental training management on the large model by constructing a capacity-adjustable empirical playback buffer pool and proposing a multi-objective loss function; and S4, carrying out model compression optimization on the large model by adopting a mixed precision quantification strategy. The method has the characteristics that the network structure can be dynamically adjusted by evaluating the importance of model parameters in real time, so that the efficient training is realized while the model performance is ensured.

The invention provides an Internet of Things gateway control method fusing local communication and AI computing power, and relates to the technical field of data processing, the method comprises the following steps: receiving an original data packet sent by at least one terminal device; protocol analysis, noise filtering and format conversion are carried out on the received data, an AI analysis model corresponding to the equipment type is loaded, standardized data are input into the AI analysis model, an analysis result is sent to target terminal equipment, and the analysis result and a communication result are stored in a gateway cache module; according to a preset time interval, the analysis result is transmitted to a remote cloud server, and synchronization state information and synchronization error log information are generated; according to the synchronization error log information, synchronization error analysis data is generated, network synchronization optimization and data anomaly positioning are executed, and a synchronization optimization result is generated; according to the data type and the error type, abnormal data are processed, and synchronous updating is executed; according to the invention, the data processing efficiency and accuracy are improved.

The invention relates to a river water ecological space global monitoring method and system, and the method comprises the steps: recognizing and segmenting a water body image from an RGB image photographed by an unmanned plane based on a U-Net deep learning model, and forming a water body recognition image; converting and reconstructing the RGB image aerially photographed by the unmanned aerial vehicle into a water body hyperspectral image based on a hyperspectral information continuation reconstruction model; the U-Net deep learning model extracts a multispectral segment sequence of pixel points of a water body in the water body hyperspectral image and sends the multispectral segment sequence to the classification regression model; and calculating the multispectral segment sequence based on a classification regression model so as to label a concentration classification result of chlorophyll a in a water body hyperspectral image, thereby realizing visualization of chlorophyll concentration. The method gets rid of limitation of technical means and time acquisition of hyperspectral data acquisition, and realizes the effect of acquiring river global images at any time and at any moment.

The invention discloses a long and narrow river cyanobacterial bloom information identification method and system based on remote sensing data, and the method comprises the following steps: selecting a remote sensing image in a research region range through a CEE cloud platform, and carrying out the preprocessing of the remote sensing image; a Sentinel-2 satellite image and a Landsat satellite image are respectively utilized to detect a cloud layer in the preprocessed remote sensing image within a cloud cover threshold value; based on a detection result, removing cloud pixels from the preprocessed remote sensing image to obtain a cloud-removed image; analyzing the cloud-removed image by using the improved normalized difference water body index, and determining the threshold change range of the water body in each image of the cloud-removed image so as to realize the recognition of the water body area; identifying cyanobacterial bloom information in the water body area by using a floating algae index method, and determining a threshold change range of cyanobacterial bloom in each image so as to realize identification of distribution characteristics of cyanobacterial bloom; according to the method, the accuracy and flexibility of narrow and long river cyanobacterial bloom information identification are remarkably improved.

The invention discloses a large language model acceleration system and method based on binary quantization, and the system comprises an extraction and quantization unit, a grouping packaging and splicing unit, an operation realization unit, and an inverse quantization and output unit, and comprises the specific steps: extracting parameters needing matrix / vector multiplication in a model; performing binary quantization processing on parameters of the model matrix / vector multiplication operation; splicing the grouped binary quantized parameters into single integer data bit by bit according to an order when matrix / vector multiplication is calculated by adopting a grouping and packaging algorithm; matrix / vector multiplication which is equivalent to original model reasoning and is friendly to hardware is executed; the result is converted back to the floating point data type through an inverse quantization algorithm, a final calculation result of the large language model in the matrix / vector multiplication operation is obtained, the final calculation result is transmitted into a subsequent network layer, and calculation acceleration for the matrix / vector multiplication operation in the large language model is completed. According to the method, the accuracy is ensured, and meanwhile, the speed is increased during large language model reasoning.

The invention belongs to the technical field of geophysical exploration. The invention provides an inversion method and system based on transient electromagnetic and ground penetrating radar data collaborative correction, and the method comprises the steps: converting the preprocessed ground penetrating radar data into a format of transient electromagnetic detection data, or converting the preprocessed transient electromagnetic detection data into the format of the ground penetrating radar data; performing weighted summation on the ground penetrating radar data and the transient electromagnetic detection data after format conversion to obtain fusion data; performing three-dimensional joint inversion according to the fused data to obtain a final three-dimensional joint inversion result; according to the method, collaborative detection of different depths of the detection area is realized, a brand new underground structure detection interpretation scheme is provided through intelligent data preprocessing, intelligent correction and three-dimensional joint inversion technologies, and comprehensive, efficient and high-precision interpretation of the underground structure is realized.

The invention discloses a new energy automobile lithium battery thermal runaway monitoring system and method. The system comprises a vehicle-mounted lithium battery, a multi-source data acquisition module, a multi-source data fusion module, a hidden Markov model monitoring module, a state identification module, a data analysis processing module, an early warning module, an emergency processing module, a wireless communication module, a cloud platform and a battery management system. The multi-source data acquisition module is responsible for acquiring multi-dimensional data such as voltage, temperature and internal resistance of a lithium battery, and the data fusion module processes the data and then transmits the data to the hidden Markov model monitoring module for state monitoring and prediction. According to the system, a high-order hidden Markov model and a hidden semi-Markov model are adopted, state retention time modeling and a self-adaptive online learning mechanism are combined, and conversion of a battery from a normal state to an abnormal state and a thermal runaway state can be accurately recognized. The system remarkably improves the safety and stability of the lithium battery of the new energy automobile, and is suitable for power battery management of the new energy automobile.

The invention provides a coal mine enterprise and sharing center joint reserve emergency relief goods decision-making method comprising the following steps: aiming at a specific accident type, based on historical accident information, using a random forest algorithm to determine the emergency relief goods of the specific accident type; constructing a material demand model of specific types of emergency rescue materials evolved along with time and accidents in the accident emergency rescue period and the demand quantity of the emergency rescue materials; acquiring basic information of a coal mine, and determining an emergency relief material demand change curve along with time lapse and accident evolution during an accident period according to the basic information and the application demand model; and determining the storage information of the emergency rescue materials according to the demand quantity change curve requirements of the emergency rescue materials under the condition that the time and the material quantity meet the requirements. The problems of high reserve cost and low efficiency in the prior art are solved.

The invention belongs to the field of computer graphics, and discloses a fast parallel multi-scale smooth symbol distance curved surface reconstruction method and system, and the method comprises the steps: carrying out the local fitting of point cloud data through employing a moving least square method, and calculating the Gaussian curvature of a point cloud; constructing a curvature adaptive octree based on Gaussian curvature, wherein the octree is used for dynamically adjusting local resolution and capturing geometric details to improve curved surface reconstruction precision; global fitting is carried out through an implicit function, and a zero contour surface is obtained through an octree contour surface extraction algorithm; and multiple threads are introduced in the process of iteratively solving the linear system to carry out parallel computing. The adaptive octree based on Gaussian curvature can effectively capture complex geometric details, and the algorithm realizes high-precision curved surface reconstruction under different scales. In addition, the local and overall calculation efficiency is remarkably improved through parallel calculation, and the high efficiency of the algorithm in large-scale data processing is ensured. The method provided by the invention provides an efficient and accurate solution for complex curved surface reconstruction.

The invention relates to the technical field of data storage management, in particular to a data storage method based on a large model. The method comprises the following steps: performing input class cluster fragmentation optimization on a target pre-training large model to obtain storage modulus fragmentation data; constructing an intelligent fragmentation storage strategy by using the storage modulus fragmentation data; obtaining target model training data; performing intelligent fragmentation storage on the target model training data by using an intelligent fragmentation storage strategy, and performing redundancy compression optimization to obtain dynamic redundancy storage index data; and training data storage space optimization is carried out according to the dynamic redundancy storage index data, and an optimized data storage strategy is obtained. According to the method, intelligent fragmentation storage and refined data redundancy compression are performed on the data, so that efficient and stable model training data access is realized, the problem of low data storage and access efficiency in a large model training process is solved, and the model training efficiency and reasoning real-time performance are remarkably improved.

The invention discloses a carbon-silicon negative electrode material and a preparation method and application thereof, and the preparation method comprises the following steps: S1, carrying out mixed reaction on a lithium source compound, a lanthanum source compound and a titanium source compound to obtain a mixed reactant; mixing the mixed reactant with a carbon source compound, and dispersing and emulsifying to obtain element-doped microspheres; s2, carbonizing the element-doped microspheres in the step S1 to obtain carbides, and activating the carbides to obtain a porous carbon material; and S3, performing silicon deposition on the porous carbon material in the S2 to obtain silicon deposition porous carbon, and performing carbon deposition on the silicon deposition porous carbon to obtain the carbon-silicon negative electrode material. The carbon-silicon negative electrode material disclosed by the invention is high in lithium ion transmission rate, the problem of poor electronic conductivity of silicon is solved, and the electrical property of a battery can be effectively improved.