244 results about "Encoding algorithm" patented technology

The invention discloses a financial document automatic auditing method and device and a medium, and relates to the technical field of financial reimbursement auditing. The method comprises the following steps: receiving a financial document to be audited and an associated attachment document, respectively extracting a first entity set, and extracting a second entity set from unstructured content; constructing a dynamic knowledge graph state space based on the entity set, wherein the dynamic knowledge graph state space comprises an entity vector generated by an entity embedding algorithm and a relation vector generated by a relation coding algorithm; defining a reinforcement learning action space, wherein the reinforcement learning action space comprises three types of atomic operations of newly adding and deleting a triple and adjusting confidence; in combination with the real-time document flow, the historical case library and the audit result data, dynamically evolving the knowledge graph through atomic operation, and calculating a value return value of each operation; pre-judging accumulated return values of different operation sequences by utilizing a Monte Carlo tree search algorithm, and pruning a low return sequence; executing the optimized operation sequence to update the knowledge graph; and finally, based on the updated atlas, triggering a logic verification rule to generate an auditing result.

The invention relates to the technical field of electrical load management, and discloses an electrical load spatial-temporal distribution modeling and adaptive optimization regulation and control system. The system comprises a load monitoring module, an optimization decision-making module, an exception handling module, a communication coordination module and a data tracing module. The load monitoring module collects load data by using a space-time correlation analysis technology; the optimization decision-making module adopts a dynamic clustering algorithm to generate a regulation and control strategy; the exception handling module corrects load exception in a graded manner based on a multi-scale coordination mechanism; the communication coordination module realizes instruction interaction through a hierarchical routing protocol; and the data tracing module generates a topology storage index by using a multi-dimensional feature coding algorithm. The system can accurately collect load data, reasonably distribute power, effectively process load abnormity, guarantee communication stability, facilitate data tracing, improve the operation efficiency and reliability of an electric power system, and meet the requirement of a modern electric power system for electrical load management.

The invention discloses a power grid subsynchronous oscillation suppression method based on a neural network prediction model, and particularly relates to the technical field of power grid control. The method comprises the following steps: extracting a high-dimensional feature vector of power grid measurement data and performing frequency domain decomposition to obtain feature distribution information of different frequency components; utilizing a sparse coding algorithm to realize mode separation, and identifying a running state abnormal region set; constructing a dynamic coupling model to evaluate the interaction relationship between the oscillation mode and the operation state in the abnormal region and the time evolution characteristic; analyzing modal distribution characteristics through adaptive filtering, and calculating a local modal separation degree; based on oscillation evolution information and a modal structure evaluation result, power grid operation parameters and suppression device configuration are dynamically adjusted, and the recognition and response capability of a neural network to a potential dangerous subsynchronous oscillation mode is effectively improved.

The invention relates to the technical field of product test data management, and discloses a product test data storage and management system based on an MES system. The system comprises a dynamic configuration module which can use a self-adaptive parameter adjustment algorithm to configure data acquisition parameters according to experiment types; the closed-loop feedback module is used for binding experimental data with production batches and process parameters based on a real-time association algorithm; the two-stage verification module is used for detecting data exception through a double-layer cascade verification algorithm; and the intelligent storage module is used for generating hierarchical storage labels by using a multi-dimensional structured coding algorithm. In addition, the system integration module realizes data interaction with ERP and SCADA systems based on an interface adaptation algorithm. The system solves the problems that in a traditional data management mode, collection parameters are fixed, data relevance is poor, a verification mechanism is imperfect, storage and retrieval are inconvenient and the like, data can be efficiently collected, accurately associated, strictly verified and intelligently stored, and the enterprise data management level and production competitiveness are improved.

The invention discloses a sprint learning path optimization method based on an improved whale optimization algorithm. The problem that existing sprint path planning is unreliable is solved. The method comprises the following steps: constructing a total learning cost objective function; using a random key coding algorithm based on chaotic mapping to represent the learning paths in a sequence mode, and using serial scheduling to obtain a plurality of candidate sprint learning paths; introducing an adaptive weight mechanism, an examination driving offset item and a Gaussian disturbance item, and adopting an improved white whale optimization algorithm to carry out iterative optimization on the candidate sprint learning paths to obtain a plurality of iteratively optimized sprint learning paths; in any iterative optimization, if the current candidate sprint learning path violates a first repair relation or / and a time window or / and a daily learning duration budget in the learning path, performing feasibility repair on the current candidate sprint learning path; performing neighborhood local search on the iteratively optimized sprint learning path based on a forgetting risk index; and outputting an optimal sprint learning path.

The invention discloses a printed circuit board withstand voltage detection and evaluation method, which comprises the following steps: in the whole withstand voltage detection process, aiming at different process batches and environments, acquiring electrical signals, process parameters, environment variables and multi-modal visual data, and carrying out time sequence synchronization marking and standardized preprocessing; extracting multi-source features by using a feature coding algorithm, and establishing a multi-mode distribution model covering signal mutation, visual defects and working condition anomalies; through cross-modal feature fusion and a time sequence causal inference model, an abnormal event causal relationship graph is automatically constructed, and a voltage withstanding failure root cause chain is identified and positioned; according to the method, the efficient structured management of the detection data, the accurate traceability of the abnormal reasons and the cross-batch analysis are realized, and the capability of diagnosing and preventing the withstand voltage abnormality of the printed circuit board is remarkably improved.

The invention relates to the technical field of photovoltaic power generation modeling and simulation, in particular to a photovoltaic model parameter identification method and system based on an improved symbiont search algorithm. A complex number coding mechanism is introduced on the basis of a traditional SOS algorithm and is expanded from original one-dimensional real number coding to a two-dimensional complex number coding space, so that the search range of a group is expanded, and the optimization capacity and speed of the algorithm are enhanced; establishing a photovoltaic model, and determining a to-be-identified parameter solution vector; adopting a root-mean-square error as a parameter identification objective function of the photovoltaic model; and an improved complex number coding SOS algorithm is operated to identify unknown parameters of the photovoltaic model so as to minimize the difference between actually measured current data and a simulation result, thereby pursuing an optimal fitting effect between the actually measured current data and the simulation result. The improved algorithm provided by the invention has good applicability in the parameter identification process of a single-diode model, a double-diode model and a photovoltaic module model and can quickly optimize, prediction errors are effectively reduced in the aspect of balancing global and local optimal solutions, and the parameter identification precision is improved.

The invention discloses a data processing method and a related device, and the method comprises the steps: firstly obtaining a target instruction of a virtual machine, and enabling the target instruction to be used for controlling the virtual machine; and then according to the target virtual memory address corresponding to the target instruction, an encryption key corresponding to the target instruction is determined, and different virtual memory addresses correspond to different encryption keys. And according to the encryption key, performing instruction coding on the target instruction through a coding algorithm to obtain a coding result, and storing the coding result as the target instruction in the target virtual memory address. Finally, in the running process of the virtual machine, when a calling request for the target instruction is obtained, the coding result is read from the target virtual memory address, instruction decoding is conducted on the coding result through a decoding algorithm corresponding to the coding algorithm according to the encryption key, and the target instruction is obtained. The encryption key is generated based on the storage address of the instruction, and the encryption key is used for instruction coding to realize the specificity of a coding result, so that the security of the virtual machine is improved.

The invention relates to the technical field of data information retrieval, and discloses an efficient batch privacy information retrieval method and system based on OCD and GPU optimizing.The efficient batch privacy information retrieval method comprises the steps that firstly, a server is initialized, a database is subjected to bucket division through a PBC encoding algorithm based on the client query number, the database subjected to bucket division is obtained, and when a user conducts information retrieval, the user can retrieve privacy information in a batch mode; the method comprises the following steps of: finding a sub-bucket position of a retrieval request in a server at a client by using a PBC scheduling algorithm, carrying out homomorphic encryption on the retrieval request in each sub-bucket, compressing all the retrieval requests by using an OCD to obtain a retrieval ciphertext, sending the retrieval ciphertext to the server, and sending the retrieval ciphertext to the server according to the retrieval ciphertext provided by the client. The retrieval result in the ciphertext form is obtained and returned to the client side, the client side decrypts the retrieval result in the ciphertext form, and the required retrieval result in the plaintext form is obtained. According to the method, the GPU is used for parallel processing, computing resources in a real scene can be fully utilized, and the computing efficiency of privacy information retrieval is remarkably improved.

The invention relates to the technical field of Internet of Things data management. The electrical equipment management system based on the Internet of Things comprises a hierarchical edge compression module used for performing hierarchical edge compression processing on unstructured data to generate a lightweight data packet; the hierarchical transmission scheduling module is used for performing priority marking and network slice mapping processing on the lightweight data packets to obtain hierarchical transmission data streams; the edge cloud collaboration module is used for carrying out edge-cloud collaboration processing based on the hierarchical transmission data stream to generate structured metadata and a depth analysis result; and the state linkage control module is used for carrying out state linkage management on the electrical equipment according to the structured metadata and the deep analysis result and generating an equipment control instruction so as to solve the problems that the compression efficiency and fidelity of a fixed coding algorithm are unbalanced, network channel priority distribution is rigid and equipment control and data flow dynamic linkage is missing.

The invention relates to an encrypted network traffic classification method based on a pre-trained large language model, and belongs to the technical field of encrypted network traffic classification. The method mainly comprises three stages: a pre-training stage: converting original encrypted network traffic data into a double-byte hexadecimal format through preprocessing, generating and optimizing a basic vocabulary by using a byte pair coding algorithm, then constructing a large language model, and obtaining a pre-training model through distributed training; in the retraining stage, the data is subjected to head byte shuffling processing, and the pre-training model is quickly retrained to improve the generalization ability. In the fine tuning stage, to-be-classified data is preprocessed to generate hexadecimal double-byte data with labels, and classification task training is performed by using the retrained model to obtain an encrypted network traffic classification fine tuning model and classification accuracy. Through the combination of pre-training and retraining and the fine tuning of the pre-training model by means of data classification, the efficient processing and accurate classification of the complex encrypted network traffic are realized.

The invention provides a low-power-consumption embedded data recording system and algorithm for on-line monitoring of SF density. The system is provided with an MCU main control unit, an external independent watchdog circuit, a LoRa wireless communication module, an RS485 interface, an SF density and temperature measurement sensor, a battery power supply and voltage acquisition module and a Flash data storage and real-time clock module. Algorithms of the system comprise an intelligent data recording strategy, a dynamic sensor activation and sleep mechanism, a power failure data protection and breakpoint continuation mechanism, a multi-parameter compression coding algorithm, a dynamic sampling frequency adjustment strategy, a real-time clock synchronization and timestamp calibration mechanism, a multi-sensor fusion sensing mechanism and an ultra-low power consumption system architecture mechanism. The low-power-consumption embedded data recording system and algorithm for on-line monitoring of the SF density have the functions of multi-data change trend intelligent judgment, multi-data fusion perception judgment, ultra-low power consumption and flexible communication, and are suitable for long-term field deployment.

The invention discloses a three-dimensional light field content construction and editing method, which relates to the field of naked eye three-dimensional display, and comprises the following steps of: collecting multi-view images of a real scene through a camera, and constructing a unified three-dimensional space coordinate system; generating an initial three-dimensional scene model; performing adjustable content editing on each frame of multi-view image; updating the initial three-dimensional scene model through the edited image; the updated three-dimensional scene model is rendered through a shear type rendering method, and an image sequence with multi-view consistency is generated; and coding the generated image sequence into three-dimensional light field content by using a light field coding algorithm. According to the method, the real static scene can be efficiently converted into the three-dimensional light field content with a complete structure and a continuous visual angle through multi-visual-angle image acquisition, three-dimensional reconstruction and rendering processing, so that the method has stronger sense of space depth and reality, and the visual experience and the display effect of the three-dimensional light field content are remarkably improved.

A processor-implemented method including instructing a receiver to generate an OKVS (oblivious key-value store) matrix by applying an OKVS encoding algorithm to first data and hash data of the first data, generating a vector or scalar parameters satisfying a preset linear equation using vector oblivious linear evaluation (VOLE) for a subspace based on Minicrypt, and distributing a preset first group and a preset second group among the parameters to a sender and a receiver, respectively, instructing receiver to generate a masking matrix by masking the OKVS matrix to a first vector included in the first group and transmit the masking matrix to the sender, instructing the sender to update one of the vectors included in the second group using the masking matrix, and instructing the receiver to generate first comparison data by applying an OKVS decoding algorithm to a second vector included in the first group and the first data.

The invention discloses a multi-sensory interaction display system based on the Internet, and the system comprises a multi-sensory data collection layer which carries out the synchronous collection of visual, auditory, touch and temperature data, carries out the preprocessing of the collected multi-modal data, and generates a multi-modal data package with a unified timestamp; the multi-modal data coding and transmission layer is used for compressing a multi-modal data packet based on a space-time joint coding algorithm and transmitting the multi-modal data packet through a low-delay transmission protocol; the terminal rendering and interaction layer is used for generating user interaction feedback in real time by adopting a dynamic multi-sensory fusion algorithm; and the edge-cloud cooperative computing layer is used for realizing low-delay feedback control and privacy protection based on a federated learning distributed computing framework. According to the invention, through layered decoupling and cross-layer optimization, strong space-time consistency of multi-modal interaction is realized, and through three innovative technologies of space-time joint coding, dynamic multi-sensory fusion and low-delay tactile control, high-fidelity and low-delay multi-sensory interaction is realized.

The invention discloses a self-adaptive multi-vehicle cooperative sensing method and device based on intelligent distributed decision, and the method comprises the steps: carrying out the voxelization of unified point cloud data for each vehicle, carrying out the high-dimensional voxel feature extraction of the voxelized point cloud data through a voxel feature coding algorithm, and carrying out the high-dimensional feature extraction of the voxelized point cloud data; based on the extracted high-dimensional voxel features, vehicle local high-dimensional perception features are generated; each vehicle adaptively determines a compression ratio according to the signal-to-noise ratio of the current channel, and dynamic compression coding is performed on the local high-dimensional perception features of the vehicle by using the compression ratio to obtain local compression features of the vehicle; each vehicle iteratively solves a pre-constructed multi-vehicle cooperative sensing optimization problem by adopting a multi-agent reinforcement learning method based on a global state to obtain a communication sub-channel for transmitting the local compression characteristics of the vehicle and a target vehicle for receiving the local compression characteristics of the vehicle; wherein the optimization objective of the multi-vehicle cooperative sensing optimization problem is to maximize the sensing precision and minimize the communication time delay; each vehicle sends the vehicle local compression characteristics to the target vehicle through the communication sub-channel. According to the method, the sensing accuracy can be ensured, the communication delay is reduced to the maximum extent, and bandwidth resources are saved.

Data compression with quantum-resistant intrusion detection, that measures in real-time the probability distribution of an encoded data stream and analyzes entropy characteristics across multiple bit-scale windows to detect both classical and quantum-generated intrusions. The system compares the probability distribution to a reference probability distribution and uses statistical algorithms to determine divergence between distributions while simultaneously analyzing entropy cascade patterns characteristic of quantum computing sources. When divergence exceeds configured thresholds or quantum-generated characteristics are detected, the system generates intrusion alerts identifying the threat type. The system comprises encoding and decoding machines, an intrusion detection engine that performs multi-scale entropy analysis, a codebook training engine that creates quantum-resistant codebooks using entropy-stratified training algorithms, and databases including a quantum signature database storing compression patterns of known quantum algorithms. The codebook training engine adaptively retrains encoding algorithms upon detecting new quantum patterns, maintaining system effectiveness against evolving quantum threats.

The present invention relates to communication system and method for error-proportional energy-saving in encoding and decoding in Body Area Networks (BAN) using Human Body Communication (HBC). The method includes receiving message signal from data sources. Further, the method includes encoding data symbols using encoding algorithms. Furthermore, the method includes calculating syndrome values for the encoded data symbols. Furthermore, the method includes generating an error signal when the calculated syndrome values corresponds to a non-zero value. Furthermore, the method includes receiving the error signal from the syndrome module. Furthermore, the method includes activating an Error Location Polynomial (ELP) module when the syndrome values corresponds to a non-zero value. Subsequently, the method includes generating an error indication signal. Consequently, the method includes activating an Error Magnitude Polynomial (EMP) solver module and a chien search module. Finally, the method includes decoding the encoded data symbols.

The invention provides a multi-precision floating point fusion multiply-add structure and a microprocessor architecture, and the structure is characterized in that in a first-stage assembly line, an input preprocessing module decomposes an input operand to obtain a sign bit, an index bit and a mantissa bit; the Booth encoder generates partial products through a radix-4 Booth encoding algorithm, and the tree array multiplier compresses the partial products into three groups; in the second-stage assembly line, the CSA4-2 compression adder compresses the mantissa bits after the three groups of partial products and shift alignment into two groups; the summator module sums the two groups of partial products to obtain a mantissa summation result; in the third-stage assembly line package, a leading zero detection module performs leading zero detection on the mantissa summation result, and performs index adjustment and mantissa adjustment to obtain a normalized result; and in the fourth-stage assembly line, rounding of floating point data is carried out. According to the application, the operation performance, the energy efficiency ratio and the adaptability of the floating point fusion multiply-add structure are improved, so that the high performance and the high energy efficiency of the microprocessor are balanced.

The invention discloses a high-speed fixed-point multiplication circuit. The multiplication circuit is mainly composed of a multiplier coding module, a partial product generation module, a partial product compression module and a traveling wave carry adder module. The multiplier coding module is composed of a radix-4-Booth coding algorithm and an opposite number generation module, and is used for carrying out three-bit block coding on input multiplication data and generating an opposite number of a multiplicand in advance. The partial product generation module generates a plurality of groups of partial products with symbol extension according to the multiplicand coded signal. And the partial product compression module adopts an improved Wallace compression structure to perform layered compression on the partial product. And the traveling wave carry adder module sums the two groups of results output by compression and outputs a multiplication result. According to the invention, multiplication accumulation series can be reduced, the switching times of invalid signals in the circuit can be reduced, and the longest delay path in an operation link can be shortened, so that fixed-point multiplication which is high in speed, low in power consumption and more favorable for a comprehensive tool in structure is realized.

A system and method for file type identification involving extraction of a file-print of a file, the file-print being a unique or practically-unique representation of statistical characteristics associated with the distribution of bits in the binary contents of the file, similar to a fingerprint. The file-print is then passed to a machine learning algorithm that has been trained to recognize file types from their file-prints. The machine learning algorithm returns a predicted file type and, in some cases, a probability of correctness of the prediction. The file may then be encoded using an encoding algorithm chosen based on the predicted file type.

The present invention provides a flexible LED vehicle-mounted display screen and a production process thereof. The production process includes the following steps: adopting an FPC as a basic material of the display screen main body, fixing the flexible screen on a mold, mixing a PU glue, degassing treatment, glue dripping, automatic degassing, curing, and collecting. The flexible screen is fixed on a mold tray by magnetic suction or vacuum, and an air pressure sensor, a camera, a solenoid valve and the like are used to intelligently process the glue dripping and degassing processes. A plurality of Bluetooth BLE is installed on an FPC for communication, an MCU with a DMA function is adopted, and data are compressed to 50% of original data by an LZSS coding algorithm, which greatly reduces the time for the flexible screen to send data and improves the user experience.

A text search method is disclosed. The text search method includes, based on a query including a text being input, computing a vector value having a preset size by using a preset encoding algorithm, the vector value corresponding to the text, generating a query ciphertext by homomorphic encryption for the computed vector value, transmitting the generated query ciphertext to a server, receiving a calculation result ciphertext having similarity information with the query for each of a plurality of indexes, determining an index having a preset similarity by restoring the calculation result ciphertext, and receiving information corresponding to the index by transmitting the determined index to the server.

The invention provides a forward error correction capability diffusion method and a related device. The method comprises the steps that the forward error correction capacity of a first node is determined, the forward error correction capacity comprises a coding algorithm set, the maximum grouping duration and the maximum protection level, and the forward error correction capacity of the first node comprises a first coding algorithm set, the first maximum grouping duration and the first maximum protection level; packaging the first coding algorithm set, the first maximum grouping duration and the first maximum protection level into a first capability message; and if the first node has the directly connected downlink node, sending a first capability message to the downlink node, so that the downlink node determines the forward error correction capability of the first node based on the first capability message. The forward error correction capability of the node in the transmission network is diffused downstream through the message, so that the receiving end node can determine the forward error correction coding mode of the sending end node based on the message to execute corresponding decoding, and the bandwidth utilization rate and the computing resource utilization rate are improved.

The invention provides an AT command parameter dynamic encoding and decoding method and system based on prefix identifications, and relates to the technical field of communication, the method comprises an encoding process and a decoding process, the encoding process comprises the steps of predefining a special character set and encoding algorithms, and configuring a unique corresponding prefix identification for each encoding algorithm; performing character traversal analysis on each parameter of the AT command to be sent, and judging whether any character in the predefined special character set is included or not; if not, directly outputting the parameter as a plaintext parameter; if so, encoding the parameter according to an encoding algorithm corresponding to the parameter, and splicing a corresponding prefix identifier in front of the encoded data to form an encoding parameter; and assembling all the plaintext parameters and the coding parameters according to the AT command grammar, generating a target command character string, and sending the target command character string. According to the invention, unnecessary processing overhead can be reduced, the command transmission length is shortened, and both transmission efficiency and reliability are considered.

The invention particularly relates to an image deblurring method and device based on a convolutional sparse coding feature insertion network, and the method comprises the steps: obtaining a to-be-processed blurred image; and inputting the to-be-processed blurred image to a pre-trained image deblurring model, extracting depth features from the to-be-processed blurred image through the pre-trained image deblurring model, and outputting a clear image of the to-be-processed blurred image according to the depth features of the to-be-processed blurred image, the pre-trained image deblurring model is obtained by training a preset recovery network by using the blurred image training set and a reference image training set corresponding to the blurred image training set based on a preset sparse coding algorithm. Therefore, through the convolution sparse coding feature insertion network, the clear reference database and the blurred image training set are combined, depth feature extraction and reference feature connection are utilized, the clear image is output, the problem that in the prior art, deblurring cannot be carried out on the blurred image of spatial transformation is solved, and the deblurring effect is improved.

The invention discloses a Tranformer network-oriented hybrid precision multiplier, which is applied to an FPGA (Field Programmable Gate Array), and is used for allocating a target high-resolution image according to the weight precision of the weight data of the current layer of the target Tranformer network, the feature map precision of the feature map data of the target high-resolution image and a preset data allocation rule. Determining a first quantity of weight data and a second quantity of feature map data of a single calculation cycle; according to the first quantity of weight data and the second quantity of feature map data, recoding the weight data and the feature map data after determining a target recoding algorithm to obtain weight coded data and feature map coded data; performing multiplication calculation on the weight coding data and the feature map coding data in a single calculation period to obtain an initial product result of the single calculation period; and decoding the initial product result, and merging the multiple sub-feature map data of all the calculation periods corresponding to the current layer of the target Transform network to obtain target feature map data. According to the method, the resource utilization rate is improved on the basis of ensuring the model precision.

The invention discloses an electric energy meter operation state inspection and evaluation method and system, and relates to the technical field of electric power metering safety, and the method comprises the steps: collecting and preprocessing the electrical working data of an electric energy meter, obtaining the reference current and working current of the electric energy meter, extracting error features, and generating a current error signal; carrying out voiceprint collection on the electric energy meter, and capturing a voiceprint signal of the ammeter; converting the voiceprint signal into a discrete pulse sequence through a coding algorithm, and obtaining a standardized pulse sequence through dimension conversion and optimization compression; performing feature extraction on the standardized pulse sequence by applying a pulse neural network, and obtaining fault probability distribution through synaptic weight calculation and neuron state updating after obtaining pulse sequence features; the feedback control signal and the electric energy meter evaluation report are generated based on the fault probability distribution, and the problem of poor real-time performance of fault mode recognition is solved.

The invention discloses a digital signal self-adjustment and switching path optimization system. The system comprises a signal feature sensing unit, a modulation coding decision unit, a path state monitoring unit, a path optimization decision unit, a signal transmission execution unit and a feedback closed loop correction unit. The signal feature sensing unit collects a digital signal multi-dimensional basic parameter and converts the parameter into a feature vector; the modulation and coding decision-making unit selects a modulation and coding mode according to the characteristic vector based on an adaptive modulation and coding algorithm; the path state monitoring unit monitors multi-dimensional parameters of a transmission path to construct an incidence matrix, and the path optimization decision-making unit evaluates the path by using a multi-path optimization model and outputs a selection instruction; the signal transmission execution unit processes and transmits the signal according to the instruction; and the feedback closed-loop correction unit compares the parameters before and after transmission, and feeds back deviation data to optimize subsequent processing. The system realizes adaptive modulation and coding of digital signals and dynamic optimization of a transmission path, and improves transmission efficiency and stability.

The invention discloses a rapid star map lossless compression algorithm, and aims to solve the problems of large memory space and low compression efficiency of the existing lossless compression algorithm. According to the algorithm, the efficient compression of star map data is realized through the combination of a context modeling module, a predictive coding module and a run length coding module. The method specifically comprises the steps that a flat area and a non-flat area are divided according to local gradient values, run length coding is adopted in the flat area, and predictive coding is adopted in the non-flat area; the predictive coding is realized through gradient quantization merging, predictive error calculation and Rice coding; and run length coding is realized by counting the length of continuous same pixel points and performing table look-up coding. The algorithm optimizes the number of context types, reduces the storage demand, and improves the compression efficiency by dynamically correcting the predicted value. The method is suitable for application scenes with high requirements on data integrity, such as star sensors.