257 results about "Consistency test" patented technology

The invention relates to the technical field of intelligent monitoring, in particular to an intelligent diagnosis system and method for a comprehensive energy station, and the system comprises a dynamic trajectory capture module, a lag response analysis module, a mismatch behavior diagnosis module and a fault chain positioning module. According to the method, a dynamic time warping algorithm is adopted to process sliding window time sequence data and calculate track slope difference, capture precision of instantaneous disturbance characteristics is enhanced, a grey correlation model is utilized to analyze track matching degree and set a dynamic lag threshold value, and a continuous non-convergence condition trigger mechanism is combined to improve hidden fault identification sensitivity. Multi-parameter range calculation and direction consistency check integrate start-stop frequency and load rate change trend, reduce misjudgment risk caused by single parameter fluctuation, construct a time sequence alignment axis and calculate delay response joint probability distribution, realize time-space association of historical data and real-time monitoring, accurately locate a coupling relationship of a multi-source fault chain, and improve the reliability of the multi-source fault chain. The abnormal state early warning capability is enhanced, and the fault positioning efficiency is optimized.

The invention provides a consistency test method and device for single-to-wire communication, and the method comprises the steps: receiving a communication signal transmitted by a tested device, extracting a time domain feature, a frequency domain feature and a modulation feature of the communication signal, generating a protocol feature value, carrying out the dimension reduction processing, and generating a protocol feature vector; performing matching degree analysis on the protocol feature vector and a predefined mapping dictionary, and determining a target communication protocol type with the highest matching degree; based on the determined communication protocol, dynamically generating a consistency test flow through a pre-trained neural network model; configuring a signal generator to inject an excitation signal according to the test flow, and synchronously acquiring various parameters of the tested equipment; based on the real-time feedback data, dynamically adjusting the signal amplitude, frequency and judgment threshold through a pre-trained neural network model; and summarizing feedback data of multiple rounds of tests, and generating a test report of the consistency index. According to the method, the protocol of the tested equipment can be automatically identified, the test flow is generated for the protocol, and the test efficiency is effectively improved.

The invention belongs to the technical field of tunnel inspection and auxiliary rescue, and particularly discloses an unmanned aerial vehicle multi-source fusion inspection and auxiliary rescue method based on an urban tunnel, multiple sensors are integrated on an unmanned aerial vehicle platform, and multi-source data are processed through a dynamic weighting factor graph optimization method based on a sliding window. By introducing a Mahalanobis distance consistency test mechanism, dynamically evaluating the consistency between sensor observation data and IMU prediction data, screening out data with high credibility, and endowing each factor with different optimization weights, the better the quality of the sensor observation data is, the higher the factor weight is, so that the robustness of final target estimation is improved, and the target estimation accuracy is improved. And then uniformly converting sensor data at each moment into a global coordinate system by using an SLAM framework, gradually constructing a three-dimensional map of the tunnel, and finally realizing high-precision real-time positioning of the unmanned aerial vehicle and construction of the three-dimensional map of the tunnel for subsequent inspection and auxiliary rescue tasks.

The invention discloses a memory read-write consistency testing method and system, and relates to the technical field of memory testing. Comprising the steps of S1, performing crosstalk coupling modeling: constructing an interlayer crosstalk coupling transfer function according to a quantum tunneling current curve and a three-dimensional parasitic parameter matrix; s2, constructing a three-dimensional failure probability model: obtaining a plane coupling error distribution diagram, and generating an interlayer crosstalk coefficient matrix according to the interlayer crosstalk coupling transfer function; and S3, identifying electromagnetic coupling hot spot regions: determining a risk level of each region according to the three-dimensional failure probability, setting test parameters according to the risk levels, and performing read-write test on the to-be-tested memory through the test parameters. According to the method, three-dimensional quantitative modeling of cross-layer interference is realized, so that the detection range is expanded from a plane to a three-dimensional structure, and a blind area of interlayer electromagnetic coupling in a traditional method is solved.

The invention provides a communication protocol consistency test method and system. Key function points are extracted by analyzing a target protocol document; based on the key function points, a predefined first prompt template is applied to generate a test case prompt, a large language model is guided to generate a standardized test case corresponding to each key function point, and the first prompt template comprises k few-sample examples; dynamically retrieving a related code context from a pre-constructed long-term memory library through a retrieval enhancement generation mechanism, generating a code generation prompt by applying a predefined second prompt template based on the standardized test case and the related code context, and generating an executable test code based on the code generation prompt; and performing iterative optimization on the executable test code through the large language model, and generating a new code generation prompt based on a code execution result of the previous iteration and the retrieved related code context in each iteration. The test case can be automatically generated and dynamically adapted, and the test coverage rate, efficiency and flexibility are improved.

Disclosed are a method and apparatus for drawing a distributed map of ice covering-prone regions of a power grid. The method comprises: obtaining regional basic data corresponding to a region to be drawn, and creating a corresponding grid region map; on the basis of the regional basic data, determining, in the grid region map, influencing factor data under a plurality of influence types; in response to significance scores inputted for the influencing factor data, constructing an ice covering susceptibility degree matrix, and executing a consistency test; if the consistency test succeeds, performing normalization on a feature vector corresponding to a maximum feature root of the ice covering susceptibility degree matrix, and extracting influence weights corresponding to the influence types; and, on the basis of the influence weights and the influencing factor data, separately calculating an ice covering susceptibility index of each cell in the grid region map, and drawing a distributed map of ice covering-prone regions. Therefore, a more accurate distributed map of ice covering-prone regions is provided for transmission line operation and maintenance units, so that the operation and maintenance units can more accurately foresee and locate key regions for winter icing disaster prevention and control.

The invention relates to the technical field of electronic recording carriers, in particular to an RFID electronic tag and a manufacturing method thereof. The method comprises the following steps that a small antenna packaged with a chip is attached to the attaching surface of bearing base cloth and fixed through dispensing, wherein non-imitation cloth of the bearing base cloth is composed of fabric; pressing the pressing cloth strip and the bearing base cloth through a roll-to-roll pressing process, so that the pressing cloth strip covers the electronic tag body and forms a clamping and fixing structure; arranging a plurality of electronic tag bodies on a base band in an array form, and conveying the electronic tag bodies to a roll-to-roll detection device to carry out functionality and consistency testing; after the test is completed, carrying out surface printing, laser code engraving and UV code printing on the electronic tag body; and obtaining target product information and writing the target product information into the RFID chip. According to the invention, efficient production of the RFID electronic tag is realized through a roll-to-roll pressing and fixing technology, so that the production efficiency is improved, and the tag identification performance and traceability are improved.

The invention provides a time-space consistency testing method and device for cross-time-zone medical cooperation and a readable storage medium, and belongs to the technical field of medical information. The system aims at solving data conflicts, decision delay and clinical risks caused by space-time dislocation in cross-time zone medical cooperation. The system comprises a space-time scene configurator, a space-time label generator, a conflict resolution algorithm library and a clinical influence evaluator. Wherein the space-time label generator adds a four-dimensional coordinate label for medical operation and solves the problem of time zone conversion boundary; the conflict resolution algorithm library dynamically processes concurrent operation conflicts based on priorities, and combines automatic coverage with an artificial arbitration mechanism; a clinical impact evaluator quantifies the time lag risk. Through the system and the method, the conflict rate of the electronic medical records is reduced by 91%, the emergency operation response delay is shortened by 96%, the clinical decision error rate is reduced by 92%, the robustness of the cross-time-zone medical cooperation system is effectively verified, and the clinical safety is improved.

The invention relates to the technical field of dual-polarization radars, and discloses a dual-polarization radar transmitting dual-channel consistency checking method and system, and the method comprises the steps: constructing a dual-polarization radar transmitting dual-channel structure equation model and radar operation state data; determining a dual-polarization radar transmitting dual-channel consistency analysis path diagram; using a daily quantile pairing method and radar operation state data to check the significant difference of the same attribute observation variables of the two channels of the antenna; under the condition that significant difference exists, calculating a dual-channel optimal path coefficient of the same attribute observation variable by adopting a daily quantile-to-daily quantile regression method and radar operation state data; and configuring the optimal path coefficient of the two channels based on the analysis path diagram, and comparing and analyzing the consistency of the two channels on different daily quantiles. According to the method, the dynamic consistency characteristic of dual-channel influence during radar operation can be tested.

The invention discloses a memory performance detection method, device and equipment and a memory medium, and relates to the technical field of memory performance detection. Memory with the same capacity of a data path port of a memory box is mapped to an endpoint port, the mapped memory is converted into an extended memory which can be identified by a host node, and then the memory performance of the extended memory is subjected to a consistency test, so that a memory mapping relationship can be quickly and effectively established; according to the embodiment of the invention, the host nodes can schedule the memory capacity required by the host nodes in the memory box, and the inconsistency caused by different mapped memory spaces is eliminated by configuring extended memories with the same capacity for the host nodes, so that the memory performance of the plurality of host nodes tends to be consistent on the premise, and the effectiveness of the consistency test is improved.

The invention belongs to the technical field of geographic information systems and PS-InSAR, and discloses a stress-strain-considered InSAR building deformation risk assessment method, which comprises the following steps: carrying out PS-InSAR processing on time sequence SAR image data to obtain a time sequence deformation result and carrying out precision verification; adopting a PS point correction method based on a self-adaptive building contour to screen out PS points of the building; selecting five indexes of building strain, building cumulative inclination amount, building cumulative settlement amount, building age and building structure material type; building risk assessment modeling is carried out by applying an analytic hierarchy process, consistency check and weight calculation are carried out, and the maximum characteristic value of a judgment matrix established by the five risk assessment indexes is calculated; grading the indexes of the model, performing risk assessment on each index, and drawing; and verifying a building risk assessment result in combination with actual dangerous house data. According to the invention, accurate evaluation of the deformation risk level of the building is realized.

The invention relates to the technical field of data processing, and particularly discloses a data fusion method for an industrial data quality consistency test based on artificial intelligence, and the method comprises the steps: enabling an industrial data platform to be in communication connection with target equipment, so as to collect target industrial data of the target equipment, according to the method, the data transmission process of the target equipment can be dynamically adjusted according to the time sequence quality consistency evaluation result of the target industrial data, and time sequence synchronous calibration is performed on the target industrial data, so that an intelligent closed-loop system is formed; according to the invention, a comprehensive intelligent data transmission fusion method is provided for data fusion of industrial data, the reliability of a data fusion basis is ensured, and the precision and value of a fusion result are remarkably improved.

The invention discloses a joint object attitude generation method based on physical perception and graph diffusion, and relates to the field of computer vision. The method comprises the following steps: firstly, reconstructing componentized geometric and physical attributes of an object from an image through a double-branch neural implicit network, and initializing a component connection relationship; then, a component relation graph is refined through kinematics fitting and time sequence consistency test, and attitude prior distribution of the component on the SE (3) manifold is inferred by utilizing a physically enhanced graph diffusion process; and finally, constructing a conditional diffusion model on the SE (3) manifold under the condition of prior and reconstruction information, and performing reverse sampling through a physically guided two-step reverse sampling framework to generate a group of diversified and physically reasonable joint object attitude hypothesis sets. According to the method, efficient generation of diversified and high-physical-rationality postures of a joint object is realized through tight coupling of physical rules and data driving generation.

The invention discloses an aviation fastener quality control method and system, belongs to the technical field of production control systems, and aims to solve the problems that multiple tests are needed before the existing aviation fastener is produced, the test steps are tedious, and the test period is long. Based on comprehensive collection, preprocessing, hierarchical analysis and decision support of data and effective storage and management of the data, key data in the production process are collected in real time, and after cleaning and arrangement, the system adopts an analytic hierarchy process to decompose a quality control target into a plurality of hierarchies, including a target layer, a criterion layer and a sub-criterion layer, so that the quality of the product is controlled. A clear quality control framework is formed, through expert consultation and statistical analysis, a pairwise comparison judgment matrix is constructed, the relative importance between elements of all levels is quantified, a weight vector is calculated, consistency check is conducted on the judgment matrix, and a reasonable threshold range is set through a statistical method. Scientific basis is provided for optimization of technological parameters and adjustment of threshold values, and test efficiency and product quality are improved.

The invention relates to the technical field of power distribution terminals, and discloses a power distribution terminal automatic joint debugging function integrity and reliability test system, which comprises a co-simulation module for performing closed-loop coupling on a virtual power grid and a tested terminal through deterministic time control and generating a reproducible working condition; the scene arrangement module is used for realizing automatic switching and rollback of cross-domain scenes based on transactional snapshots; and the communication module is used for executing a consistency test on multiple protocols and injecting delay jitter, packet loss and clock drift. The functional integrity and reliability test system for the automatic joint debugging of the power distribution terminal aims to solve the problems of lack of deterministic time control of cross-domain cooperation and insufficient guarantee of state consistency in a digital twin test method. The problems that a test result cannot be reproduced, crosstalk misjudgment is caused by state non-atomicity consistency during multi-scene switching, and faults are difficult to reproduce due to lack of time determinacy replay capability are solved.

The invention relates to the technical field of weight assignment, in particular to a fixed-point industry development effect evaluation system-based weight assignment calculation method, which comprises hierarchical model establishment, index importance evaluation, hierarchical analysis, entropy analysis and index weight assignment. According to the weight assignment calculation method based on the fixed-point industrial development effect evaluation system, an original judgment matrix is constructed according to relative importance data of indexes of all layers through an analytic hierarchy process, and a maximum feature root and a maximum feature vector are calculated to serve as bases to perform consistency check on the judgment matrix; then, the relative importance data of the indexes are subjected to forward processing through an entropy evaluation method, so that the index proportion and the entropy and information entropy redundancy of each index are calculated, the index weights obtained through the analytic hierarchy process and the entropy evaluation method are subjected to weight combination, weight assignment of each index is obtained through weighted arithmetic average processing, and the weight assignment of each index is obtained; the subjective influence and the influence on weight fluctuation during data change can be effectively reduced.

The invention relates to the technical field of high arch dam deformation field feature analysis, in particular to an interpolation algorithm for high arch dam deformation field feature analysis. According to the technical scheme, the method comprises the steps of data collection and classification, variation function initial parameter setting, variation function fitting through a local weighted least square method, variation function parameter global optimization, Kriging interpolation calculation and consistency checking and parameter adjustment, in the data collection and classification process, monitoring data of the high arch dam under different load working conditions are collected, and the monitoring data of the high arch dam under different load working conditions are obtained. The load working conditions comprise a high water level in a flood period and a low temperature period in winter, and the deformation data of different parts and different time from the total station, the level gauge, the inclinometer and the strain gauge are associated with the corresponding load working conditions and monitoring point coordinate information. Through comprehensive data association, reasonable parameter setting and optimization, accurate interpolation calculation and a reliable result adjustment mechanism, more accurate deformation field analysis of the high arch dam under different load conditions is realized, and safe operation of the dam is guaranteed.

The invention discloses a multi-protocol compatible intelligent test method and system for a power distribution automation terminal, and relates to the technical field of power distribution terminal test. The method comprises the following steps: acquiring basic information and historical test data of a tested terminal; automatically identifying and matching a communication protocol through a multi-protocol adaptive identification model, and generating a protocol conformance test template; according to the template, executing signal injection and collecting real-time response data, and calculating a terminal response matching degree and a protocol analysis accuracy parameter; and inputting the parameters into the test result evaluation model, and outputting a test result. Comprising an information acquisition module, a protocol identification and template construction module, a test execution and data acquisition module and a test evaluation module. According to the invention, automatic identification, standardized testing and intelligent evaluation of the multi-protocol terminal are realized, the testing efficiency, consistency and accuracy are improved, and the method is suitable for testing and diagnosis of distribution automation terminals of different models.

The invention discloses a project performance evaluation method, system and device based on a weight optimization method, and a medium. The method comprises the following steps: S1, inputting an initial project performance evaluation index system; s2, constructing a comparison judgment matrix, and calculating a consistency ratio CR, if CRlt; 0.1, if so, passing the consistency test, and performing the step S4; if CR is greater than or equal to 0.1, adjusting the comparison judgment matrix, and performing the step S3; s3, automatically optimizing the comparison judgment matrix, and recalculating CR until CRlt; 0.1, optimization is stopped, and the step S4 is carried out after consistency check; and S4, outputting the effective weight value of each index if the consistency test is passed, and obtaining a final performance evaluation index system. The method has the advantages that the defects that when a classical analytic hierarchy process is used for performance evaluation, the workload is large, dynamic optimization adjustment is difficult and the like are overcome, efficient data processing and analysis are achieved, especially when the number of orders of a comparison judgment matrix is large, the adjustment efficiency can be improved, the number of iterations can be reduced, and the weight accuracy can be improved. And the scientificity and practicability of the analytic hierarchy process are improved.

The invention belongs to the technical field of air conditioning system evaluation, and relates to a comprehensive performance evaluation method for a medium-temperature cold water central air conditioning system, which comprises the following steps of: 1, constructing an evaluation index system; based on the characteristics of the medium-temperature cold water system, selecting core indexes to construct an evaluation index system; 2, determining the weight through a subjective and objective weighting method; wherein the subjective weighting adopts a 1-9 scale method to construct a judgment matrix, an effective matrix is screened through consistency check, and an initial weight is calculated; the initial weight of objective weighting is corrected according to the dispersion degree of expert scoring data; 3, performing grey relational degree calculation on the to-be-evaluated system, and quantifying the comprehensive performance; according to the method, subjective and objective weighting is combined, and subjective deviation of weight distribution is reduced, so that the influence of subjective preference or data distribution on the weight in comprehensive performance evaluation of the air conditioning system can be avoided, and scientificity and universality of an evaluation result are enhanced.

The utility model relates to the technical field of millimeter wave radio frequency communication, and discloses a broadband millimeter wave dual-channel receiver, which comprises two receiving links and a power divider, each receiving link is connected with the power divider, each receiving link comprises an isolator, a frequency mixer and an intermediate frequency amplifier which are sequentially connected from input to output, one input end of the frequency mixer is connected with a frequency multiplier, and the input end of the frequency multiplier is connected with one output end of the power divider; according to the utility model, mutual interference of multiple paths of signals in a test can be effectively prevented, two paths of millimeter wave radio frequency signals can be tested and analyzed at the same time, and the device can be used for various test scenes such as down-conversion test, two paths of radio frequency signal amplitude-phase consistency test, noise coefficient test and the like.

The invention relates to an autonomous navigation obstacle avoidance performance evaluation method based on multi-dimensional comprehensive analysis, and belongs to the technical field of autonomous navigation system evaluation. Comprising the following steps: in a set scene, obtaining an expected target value through a global path planning algorithm; acquiring an actual value of autonomous navigation; processing the original data to generate intermediate data; calculating an index value by using the path planning data and the autonomous navigation data; weighting the basic indexes by using an analytic hierarchy process and carrying out consistency check to obtain reasonable weights of the indexes; and carrying out index fusion by using the weights to obtain a final evaluation result. According to the method, the autonomous navigation obstacle avoidance performance evaluation index system is established, the influence factors of the autonomous navigation obstacle avoidance performance are determined, so that the autonomous navigation obstacle avoidance performance evaluation model based on the analytic hierarchy process is constructed, index fusion is realized, the autonomous navigation obstacle avoidance performance evaluation result is obtained, and the obstacle avoidance performance of the autonomous navigation system is comprehensively, quantitatively and accurately evaluated.

The invention discloses a financial industry distributed system data consistency automatic test platform and method, and the method comprises the steps: a test data distribution module is mainly used for generating a test data set with financial transaction characteristics, and distributing the data to a plurality of service nodes of a distributed system; the automatic test module is mainly used for testing the data consistency of the distributed system in four aspects of read-write, transaction, abnormity and final consistency; the node agent module is mainly used for collecting data states, operation logs and abnormal events of each service node in real time, and is synchronized with the central control end; and the result analysis module is mainly used for performing comprehensive evaluation analysis based on the test result of each service node to obtain a consistency analysis result. The method has the advantages that through intelligent data distribution, comprehensive consistency testing and real-time monitoring analysis, the stability and reliability of the financial transaction system in a high-concurrency environment are ensured.

The invention relates to the technical field of deep learning, and discloses a deep learning prediction method and system for multi-source space-time lattice point data, and the method comprises the steps: obtaining live lattice point data, forecast lattice point data and static lattice point data, and carrying out the preprocessing, thereby obtaining uniform lattice point feature data; and generating missing mask lattice point data, generating confidence coefficient lattice point data according to observation coverage information, interpolation distance information, a time-space consistency test result and a forecast aging attenuation rule, and forming model input lattice point data. And constructing a training sample and generating forecast aging coding data. And constructing and training a deep learning prediction model, wherein the model comprises a space coding network, a time coding network and a forecast aging segmentation prediction network. In the training stage, confidence coefficient is used for weighting regression loss. In the reasoning stage, a release prediction result is obtained. According to the method, the learning stability of the multi-source grid point data under the missing measurement and filling conditions is improved, and the reliability of continuous value prediction and grading alarm probability under different prediction time periods is improved.

The invention discloses a data quality evaluation method based on AHM and GTN. The method comprises the following steps: step 1, identifying a data set and dividing the data set into four classes; step 2, constructing a multi-level evaluation index system; step 3, performing normalization processing on index parameters of the multi-level evaluation index system, and then determining a weight distribution result of each factor in efficiency evaluation by adopting an AHM attribute analytic hierarchy process; step 4, obtaining a historical evaluation label by using the weight distribution result; and 5, giving a data quality score of the evaluated data set. According to the method, the evaluation workload is greatly reduced, and the complexity and subjectivity of consistency check are effectively avoided.

The invention discloses a protocol logic vulnerability mining method based on program multi-dimensional variation. The method comprises the following steps: firstly, based on an RFC protocol standard, automatically positioning a buffer write function responsible for writing a message and a state variable used for identifying a protocol state in a program; then, multi-dimensional variation is carried out, including content level variation (field replacement, field multiplexing and field deletion) and sequence level variation (message repetition and message skipping), and a variation message with legal grammar and abnormal semantics is generated; and finally, monitoring state variables of a protocol state machine and an instrumentation program defined based on the RFC standard, detecting the difference of behaviors of a plurality of protocol implementation state machines under the same variation input by using a consistency test method, automatically discovering violation of protocol implementation on the RFC standard, and classifying the violation into logic vulnerabilities. According to the method, typical vulnerabilities such as degradation attacks, repeated extension and missing extension in cryptographic protocol implementation can be automatically mined, and 49 logic problems are found in multiple protocol implementation.

The invention relates to the technical field of human body kinematics parameter measurement, in particular to an adult joint motion range evaluation method and system based on a multi-view video, and the method comprises the steps: obtaining a multi-view video sequence of a testee, and generating an observation data set containing two-dimensional key point observation, a human body segmentation mask and camera parameter information; constructing an individualized joint geometric model containing a bone segment length, a joint center, a joint principal axis and a joint angle coordinate system based on the observation data set, and generating a three-dimensional symbol distance field; constructing a factor graph and performing incremental optimization solution, and outputting a joint angle sequence and an abnormal frame set; and determining an activity range interval and carrying out anti-fact consistency check, and if the validity is not satisfied, calculating an information matrix by a Jacobian matrix to generate a supplementary collection instruction to update a result, thereby improving robustness and verifiability.

Methods and systems for managing inference models are disclosed. To do so, a first inference model that is deemed both internally consistent and correct may be used to evaluate an internal consistency and a correctness of a second inference model hosted by a remote resource. An inference model consistency test may be performed using a set of prompts deemed consistent by the first inference model to determine whether the second inference model is internally consistent. An inter-inference model consistency test may be performed using the set of prompts to determine whether the second inference model is consistent with the first inference model and, therefore, is consistent. If a first information content of a first set of responses generated by the second inference model is consistent with a second information content of a second set of responses generated by the first inference model, the second inference model may be correct.

The invention provides a cache consistency test method and device, electronic equipment and a computer readable storage medium. The method comprises the steps of obtaining a test sequence of a multi-core cache system; the multi-core cache system comprises at least two processor cores and a multi-level cache. The test sequence comprises an operation instruction for each processor core; inputting the test sequence into the simulation model, processing the test sequence in sequence through multi-stage caches of the simulation model according to a cache coherence protocol, and outputting a state check point of the multi-core cache system; the state check point is used for representing the current cache state of each processor core in the multi-core cache system; and testing the cache consistency of the multi-core cache system according to the state check point to obtain a test result. According to the embodiment of the invention, the reliability and comprehensiveness of the cache consistency test can be improved.

The invention relates to the technical field of oil reservoir gas injection development, and discloses an oil reservoir gas injection mode optimization method and experiment device for CO2 yield increase and storage, and the optimization method comprises the following steps: S1, building an optimization experiment device; s2, constructing a geologic model after fracturing of the target oil reservoir and configuring a fluid sample; s3, carrying out multi-scheme physical simulation experiments under different gas injection modes of the oil reservoir; s4, the crude oil recovery rate, the CO2 oil change rate, the CO2 storage amount and the CO2 storage rate under different gas injection modes are calculated; s5, establishing a hierarchical structure model by using an analytic hierarchy process and constructing a judgment matrix of evaluation indexes; and S6, calculating the weight vector of each evaluation index, performing consistency check, calculating the comprehensive score of CO2 yield increase and storage performance under different gas injection modes, and screening out the optimal gas injection mode of the oil reservoir. Physical simulation of different types of oil reservoirs under multiple gas injection modes of continuous gas injection, pulse gas injection, advanced gas injection, gas injection huff and puff and gas-water alternation is achieved, and the problem that gas injection mode optimization cannot be conducted in existing oil reservoir CO2 injection scheme optimization is solved.