Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

58results about How to "Comprehensive consideration" patented technology

Method and system for identifying and evaluating foreign matter invasion risk of rail transit

The invention provides a rail transit foreign matter invasion risk identification and evaluation method and system, and belongs to the technical field of target identification of image processing. Image data of a running environment in front of a train are collected in real time; performing foreign matter detection on the acquired image data frame by frame through a foreign matter detection algorithm, and obtaining the category and position information of the detected foreign matter if the foreign matter is detected to exist in a certain frame of image; segmenting a track region in the frame of image through a track segmentation algorithm to obtain position information of the track region; based on the relative position relation between the foreign matter and the rail area, the distance between the foreign matter and the train and the category of the foreign matter, comprehensively evaluating and outputting the rail transit foreign matter invasion risk level. According to the method, the foreign matter invasion risk in the rail transit scene can be accurately identified in real time, meanwhile, a rail transit foreign matter invasion risk grade evaluation system is established, and efficient detection, identification and evaluation of the rail transit foreign matter invasion risk are achieved.
Owner:BEIJING JIAOTONG UNIV

Security assessment method, system and device of energy storage system and storage medium

PendingCN119001457ASecurity is accurate and more intuitiveRisk assessment results take into account comprehensive factorsElectrical testingElectrical batteryElectric current flow
The invention provides a safety assessment method, system and device for an energy storage system and a storage medium. The method comprises the steps that S1, the operation temperature, current and voltage of a battery are detected and extracted in real time; s2, predicting the RUL of the battery, estimating the SOC of the battery, and detecting and calculating the temperature rise rate of the battery; s3, calculating subjective weights and objective weights of the RUL, the SOC and the temperature rise rate of the battery; s4, calculating a risk degree score corresponding to the battery in combination with a preset energy storage system safety evaluation model; and S5, evaluating the risk degree of the battery according to the risk degree score, and adjusting an operation strategy according to the risk degree. According to the method, the RUL, the SOC and the temperature rise rate of the battery are obtained as evaluation indexes by detecting measurable data in the operation process of the energy storage system, the evaluation indexes are subjected to combined analysis and verification of subjective weights and objective weights, the risk degree score of the battery is obtained, and the risk degree of the battery is evaluated. And the safety of the energy storage system can be judged more accurately and intuitively according to the score of the risk degree.
Owner:LBATTERYCLOUD CO LTD +1

Roadbed compaction quality monitoring, management and maintenance method and system based on virtual and real index collaboration

The invention relates to a roadbed compaction quality monitoring, management and maintenance method and system based on virtual and real index collaboration. The method comprises the following steps: step 1, establishing an indoor compaction test for reproducing on-site roadbed compaction conditions, and establishing a data set of the indoor test; 2, implementing a field test on roadbed pressure, and establishing a data set of the field test; 3, building a roadbed compaction quality prediction model based on virtual and real data collaborative training; and 4, carrying out construction management and control application on the roadbed compaction quality prediction model based on virtual and real index collaborative prediction. According to the method, the influence of roadbed filler parameters, road roller working parameters and external environment parameters of roadbed compaction on the compaction quality is fully considered, multiple virtual-real indexes cooperate with one another to establish an artificial neural network compaction quality prediction model of the roadbed compaction quality, and the model is optimized and improved while being migrated to engineering practical application. And real-time accurate monitoring, management and maintenance of the compaction quality are realized in the on-site roadbed compaction process.
Owner:HEBEI UNIV OF TECH +1

Urban flood disaster risk assessment method based on crowd sensing, medium and equipment

The invention provides an urban flood disaster risk assessment method based on crowd sensing, a medium and equipment, and the method comprises the steps: collecting flood disaster text data on a social platform, carrying out the preprocessing, and constructing a flood disaster text data set; extracting flood disaster common words from the flood disaster text data set, classifying the flood disaster common words according to subject terms, and constructing a disaster descriptive lexicon based on a co-occurrence network; designing a crowdsourcing questionnaire based on the disaster descriptive word bank, issuing the crowdsourcing questionnaire to a target user group, and collecting flood disaster feedback data and geographic information fed back by the target user group; performing spatial distribution on the collected flood disaster feedback data according to geographic information; and carrying out risk assessment by combining two types of indexes which respectively represent the flood disaster situation and the flood disaster influence area. According to the invention, real-time monitoring and accurate assessment of urban flood disasters are realized, and the accuracy and real-time performance of flood disaster risk assessment are improved.
Owner:JIANGSU HONGXIN SYST INTEGRATION +1

Vehicle tire load determination method and device, terminal equipment and storage medium

PendingCN118991800Aload accuratelyfit the current stateTerminal equipmentControl theory
The invention is suitable for the technical field of intelligent automobiles, and provides a vehicle tire load determination method and device, terminal equipment and a storage medium, and the method comprises the steps: obtaining a mass parameter and an acceleration parameter of a vehicle and a road slope of a road where the vehicle is located; obtaining a transverse dynamic load and a longitudinal dynamic load of the vehicle based on the mass parameter of the vehicle and the acceleration parameter of the vehicle; obtaining a static load of the vehicle based on the quality parameter of the vehicle and the road gradient; and obtaining the tire load of the vehicle based on the transverse dynamic load, the longitudinal dynamic load and the static load. When the tire load is determined, not only are the transverse dynamic load and the longitudinal dynamic load considered, but also the static load is considered, the considered factors are more comprehensive, and the obtained tire load is more accurate and better conforms to the current state of the vehicle.
Owner:GREAT WALL MOTOR CO LTD

Underground chamber stability assessment method based on deep learning and fusion uncertainty

ActiveCN119442763Aaccurate analysisOvercome the problem of difficult constant determinationBiological modelsDesign optimisation/simulationEvaluation resultStability coefficient
The invention provides an underground chamber stability assessment method based on deep learning and fusion uncertainty, and relates to the technical field of underground chamber stability assessment, and the method specifically comprises the steps: constructing an instability assessment model, and employing crustal stress parameters and rock mechanics parameters collected historically as a training set, the stability coefficient of the underground chamber is used as a label, and the stability of the underground chamber can be analyzed more accurately through training of a deep learning model; besides, a function relationship of the influence of the rock parameters on the stability of the underground chamber is constructed, and multiple groups of current second influence coefficients are obtained by inputting multiple groups of current rock parameters into the function, so that the comprehensiveness and the accuracy of evaluation are improved; and finally, through data processing and correction, uncertainty factors are comprehensively considered, and the stability and reliability of an evaluation result are improved. The method can overcome the technical defects that constants are difficult to determine, parameter processing is incomplete, and evaluation results are unstable in a traditional method.
Owner:HUNAN UNIV OF SCI & TECH

Volcanic rock buried hill fractured oil and gas reservoir modeling method

The invention relates to a volcanic rock buried hill fractured oil and gas reservoir modeling method, which comprises the steps of S1, identifying fractures in imaging logging data according to the imaging logging data, analyzing occurrence characteristics of the identified fractures, grouping the fractures according to the occurrence characteristics, and explaining main control factors of fracture development in a target area; s2, based on the main control factors of the crack development of the target area, respectively constructing a crack development probability body for each main control factor, and fusing the crack development probability bodies controlled by other main control factors to form a crack development comprehensive probability body; s3, building a fracture density data body of each group of fractures by taking the bile meridian fracture linear density data of the grouped fractures as integration and taking the fracture development comprehensive probability body as a constraint condition; and S4, according to the statistical structure of the occurrence characteristics of each group of fractures, in combination with the corresponding fracture density data volume, establishing a fracture space distribution model.
Owner:CHINA NATIONAL OFFSHORE OIL (CHINA) CO LTD +1

Quantitative prediction method for reservoir geomechanical parameters of complex structure superposition area

The invention provides a quantitative prediction method for geomechanical parameters of a reservoir in a complex structure superposition area, and is suitable for the fields of petroleum and natural gas geology and rock mechanics. The method comprises the following steps: firstly, collecting drilling rock cores, conventional logging, imaging logging and three-dimensional seismic data in a complex structure superposition area, calculating rock mechanical parameters by utilizing experiments and logging, and constructing a single well rock mechanical parameter profile S0; then, fracture parameters are picked up, the relation f1 and f2 between fracture density of upper and lower walls of a fault and the distance from the fault and a fracture weakening rock mechanical property model F are established, S0 is converted into a rock mechanical parameter profile S1 under the actual stratum fracture-containing condition, and the relation between the rock mechanical parameter profile S1 and seismic attributes is established; and finally, constructing a natural fracture field and a rock mechanical field of the complex structure superposition area, and realizing quantitative prediction of reservoir geomechanical parameters. The method is comprehensive and rigorous in considered factors, high in operability and high in prediction result credibility.
Owner:CHINA UNIV OF MINING & TECH

Cultivated land heavy metal pollution control zoning method, system, equipment and medium

The invention discloses a farmland heavy metal pollution control zoning method, system, equipment and medium, and relates to the technical field of soil treatment and environmental protection. Comprising the following steps: determining soil heavy metal content standard exceeding conditions of cultivated land to be detected, crop heavy metal content standard exceeding conditions, potential ecological risk conditions, human health risk conditions and cultivated land grading results; comprehensively evaluating the soil heavy metal content standard exceeding condition, the crop heavy metal content standard exceeding condition, the potential ecological risk condition, the human health risk condition and the cultivated land grading result, and determining the heavy metal pollution control partition type of the cultivated land to be detected according to the evaluation result. The cultivated land is partitioned through multi-aspect evaluation and constraint of the cultivated land, factors are comprehensively considered, and the accuracy of heavy metal pollution management and control partitioning is improved.
Owner:ZHEJIANG UNIV

Multi-factor intelligent site selection method and system

The invention relates to the technical field of ocean space planning, in particular to a multi-factor intelligent site selection method and system. Data such as administrative region data, a shoreline-to-sea-side sea area, a shoreline-to-land-side sea area, an ocean function division, a mainland coastline, an isobath, an ocean ecological red line, ocean ownership data and ocean grading data are considered, factors are comprehensively considered, and the accuracy of intelligent site selection is improved; according to the method, when an analytic hierarchy process is adopted to carry out adaptability evaluation on the site selection scheme, the analytic hierarchy process is improved, the weights are determined by adopting a matrix judgment mode and a subjective scoring mode respectively, then the weights with large errors are screened out, the weights with the large errors are updated by adopting an entropy evaluation method, and the adaptability of the site selection scheme is evaluated. Therefore, the accuracy of weight determination is improved, and the accuracy of site selection scheme evaluation is further improved.
Owner:ZHEJIANG ACAD OF OCEAN SCI (ZHEJIANG OCEAN TECH SERVICE CENT)

Distributed electric drive vehicle integrated stability prediction control method and device

The invention relates to a distributed electric drive vehicle integrated stability prediction control method and device. The method comprises the following steps: constructing an initial tire model of a vehicle according to tire attribute data and a magic algorithm, and performing segmented affine processing on the initial tire model according to a segmentation algorithm and a segmented affine algorithm to obtain a linear tire model; based on the stress model of the vehicle, the road adhesion coefficient and the linear tire model, constructing a target stress model of the vehicle, and determining a tire slip angle model according to the target stress model; aiming at each piece of speed data in the speed data set, determining a phase plane graph corresponding to each piece of front wheel turning angle data of the vehicle under the speed data according to a tire slip angle model, the front wheel turning angle data set, the vehicle attribute data set and a fixed point algorithm; and determining a stable range corresponding to the speed data according to each phase plane graph under each piece of speed data. By adopting the method, the accuracy of the stable range can be improved.
Owner:TSINGHUA UNIVERSITY

A method for predicting surface vibration waveforms during tunnel blasting

ActiveCN116432815BComprehensive considerationAccurately reflect the actual situation of blasting vibrationWave shapeClassical mechanics
This invention provides a method for predicting surface vibration waveforms during tunnel blasting, comprising: first, deriving the vibration waveform function of a short-charge explosive charge based on Heelan theory; then, constructing a vibration calculation form suitable for tunnel cut-out blasting based on this short-charge explosive charge vibration waveform function, and calculating the surface vibration waveform function of the cut-out holes using the superposition principle; next, simplifying and correcting the formula for the waveform function of multiple-hole blasting to obtain the surface vibration waveform function of multiple-hole blasting in the tunnel; finally, determining the specific parameters in the formula by comparing with field measured data, and obtaining a surface vibration waveform function curve suitable for field use. This method can comprehensively and accurately predict the waveform time history curve of the entire process of surface vibration during tunnel blasting, rather than just predicting a single blasting peak value. It can effectively promote the field application of surface vibration waveform prediction for tunnel blasting and is of great significance for optimizing blasting parameters and ensuring the safety of various facilities and personnel around the blasting area.
Owner:CHINA RAILWAY DEV INVESTMENT CO LTD +4

Calculation and optimization method for trunk lid elbow hinge axis arrangement

The present invention relates to the technical field of automobile structural design optimization methods, and specifically refers to a trunk lid bent tube hinge axis arrangement calculation optimization method. According to the rear modeling CAS surface, as well as known design parameters and set constraints, the trunk lid initial opening θ0 and the hinge axis initial coordinate f0 are set; a hinge optimization area is constructed, and within the hinge optimization area, the trunk lid initial opening θ0 and the hinge axis initial coordinate f0 are calculated based on the hinge span design requirements, human-machine goals, the safety gap of the hinge relative to the sealing strip movement, the safety gap requirements of the trunk lid and the rear windshield during the opening process, the assembly space distance between the hinge axis and the rear windshield, and the trunk lid closing force requirements to obtain the optimal solution for the hinge axis. The optimization method of the present invention is reasonably designed, with rich considerations, avoiding the risk of repeated modifications in the later stage, improving the efficiency of the hinge axis design and development, and has great promotion value.
Owner:DONGFENG MOTOR GRP

A method for predicting the vibration response of building structures caused by train operation

The present invention provides a method for predicting the vibration response of a building structure caused by train operation, which relates to the technical field of vibration prediction of rail transit environment, and includes the following steps: obtaining train dynamics design parameters and establishing a train model; obtaining track structure design parameters and establishing a track structure model; using the train track contact relationship to establish a train-track structure model; obtaining the building structure design parameters of the train running position and establishing a building structure model; using the track structure and the building structure contact conditions to construct a train-track structure-building structure coupling model; considering the influence of track unevenness to calculate the wheel-rail contact force generated by train operation; calculating the track structure and the building structure vibration acceleration time history curve. The present invention can quickly and accurately predict the vibration response of the building structure caused by the train operation in the time domain, considering more comprehensive factors, and the established coupling model is more in line with the working conditions, which greatly improves the solution efficiency and obtains more accurate prediction results.
Owner:GUANGDONG UNIV OF TECH

Intelligent matching method, device, equipment and storage medium for multi-scenario emergency measures

The present invention provides an intelligent matching method, device, equipment and storage medium for multi-scenario emergency measures, and belongs to the field of emergency data processing technology. The method includes: obtaining the scene information of the current scene; wherein the scene information includes the scene purpose, scene scale, risk category, risk level and risk stage; matching the current scene with the historical scene in the emergency measures database based on the scene information of the current scene, and obtaining a matching scene similar to the current scene; wherein the emergency measures database stores scene information and emergency measures of multiple historical scenes; based on the difference in scene information between the current scene and the matching scene, adjusting the emergency measures corresponding to the matching scene, and obtaining the emergency measures corresponding to the current scene. The present invention can improve the implementation effect of the generated emergency measures, and has higher efficiency and more comprehensive and objective considerations than manually formulated emergency measures.
Owner:HEBEI ELECTRONIC & INFORMATION TECH ACAD +1

Quantitative evaluation method of shear risk of shale fractures considering fluid-solid coupling and stress shadow

The present invention discloses a quantitative evaluation method for shear risk of shale fractures considering fluid-solid coupling and stress shadow, which comprises four steps: a dynamic expansion simulation method for complex fractures considering fluid-solid coupling, a criterion for judging the expansion direction of natural fractures, calculation of fracture shear displacement considering stress shadows, and quantitative evaluation of the risk of shear deformation of shale casing. The method can effectively evaluate the shear displacement of hydraulic fractures on the casing wall of the shale fracturing layer, realize the risk prediction of shear deformation of the casing during the fracturing process, and provide effective means and technical support for guiding and optimizing construction parameters and ensuring the integrity of the wellbore.
Owner:CHINA NAT PETROLEUM CORP +1

A method, system and storage medium for negotiation and scheduling of emergency resources in a distributed environment

The present invention discloses a method, system and storage medium for negotiating and dispatching emergency resources in a distributed environment, including the following steps: gridding and numbering the layout area of ​​emergency materials; obtaining the state matrix of emergency materials; obtaining the value of emergency materials in each grid area; dispatching the emergency materials corresponding to the designated support area to the corresponding area to be replenished. The present invention defines and represents the state of the layout area and the state of emergency materials, so that the state of emergency materials can be expressed more vividly and is conducive to subsequent calculations; obtains the value of resources in each grid area, thereby providing a basis for subsequent resource dispatch; supplies resources to high-value areas through low-value areas to maximize the value and maximize the overall benefits.
Owner:NAT UNIV OF DEFENSE TECH

An abnormality positioning method based on a cloud management platform and a cloud management platform

PendingCN122309110AComprehensive considerationImprove the efficiency of abnormal locationNode clusteringExtreme scale computing
This application discloses an anomaly localization method and a cloud management platform based on a cloud management platform, which can improve the efficiency of anomaly localization to a certain extent. The method includes: the cloud management platform can create a large-scale computing node cluster for tenants, which can contain multiple computing nodes. If these multiple computing nodes fail to execute a job task, the cloud management platform can first obtain the logs generated by these multiple computing nodes during the execution of the job task, and generate log space characteristics and log time characteristics of these multiple computing nodes based on the logs. Then, the cloud management platform can evaluate these multiple computing nodes based on these log space characteristics and these log time characteristics to obtain evaluation values ​​for these multiple computing nodes. Subsequently, the cloud management platform can identify computing nodes whose evaluation values ​​are greater than or equal to a preset threshold as computing nodes that have experienced an anomaly.
Owner:HUAWEI TECH CO LTD

Method and system for measuring and calculating highest gathered number of people in station based on card swiping data in station

The invention discloses a method and a system for measuring and calculating the highest gathered number of passengers in a station based on pull-in card swiping data, and the method comprises the steps: carrying out the fitting based on the pull-in card swiping data of passengers of different trains, obtaining a logarithmic normal distribution function of the arrival time of the passengers of the different trains, and obtaining key parameters mu and sigma; training a decision tree model; outputting key parameters mu and sigma of each train of the station to be measured and calculated through the decision tree model, obtaining a logarithmic normal distribution function of arrival time of passengers of each train, and calculating an arrival distribution curve of the passengers of each train; and superposing the passenger arrival distribution curves of the trains to obtain a passenger arrival distribution curve of the whole station, wherein the highest point of the ordinate is the highest number of gathered passengers of the station. According to the method, various factors such as station environment attributes, train attributes and different train passenger arrival laws are comprehensively considered, the problems that an existing maximum gathered passenger number calculation method is simple in consideration factor and large in calculation result deviation are solved, the building scale of a passenger station building can be reasonably determined, and railway construction investment is saved.
Owner:CHINA RAILWAY FIRST SURVEY & DESIGN INST GRP

Method for evaluating toughness of power distribution network under hail disasters

The invention discloses a power distribution network toughness evaluation method under hail disasters, and belongs to the technical field of alternating current power distribution network toughness evaluation. When the component failure rate of the power distribution network under the hail disaster is calculated, importance screening is carried out on d physical characteristics of the power distribution network affected by the hail disaster, the important physical characteristics with the large influence degree are screened out, and the component failure rate of the power distribution network under the hail disaster is calculated through the screened-out important physical characteristics. The problems of instability and inaccurate calculation results caused by judging physical characteristics by experience in the prior art are solved. According to the invention, when the power distribution toughness is evaluated, the indexes of two latitudes, namely the loss load rate of the key load of the power distribution network and the mobile energy storage response rate, are adopted for evaluation, so that the real condition can be reflected more accurately; meanwhile, the occurrence probability of hail disasters and the component failure rate of the power distribution network under the hail disasters are introduced to correct the evaluation result when the power distribution toughness is evaluated, so that the evaluation method is more accurate.
Owner:STATE GRID JIANGSU ELECTRIC POWER CO LTD NANJING POWER SUPPLY COMPANY +1

Method for determining battery pack aging value, electronic device, and readable storage medium

This application belongs to the field of battery pack technology, and particularly relates to a method for determining the aging value of a battery pack, an electronic device, and a readable storage medium. The method calculates the cycle aging value and the static aging value based on the battery pack's cycle aging parameters, a preset first parameter table, and static aging parameters, and then determines the battery pack's aging value based on these two values. This application considers both the aging effects of cyclic charging and discharging and the aging effects of static storage when determining the aging value, providing a comprehensive assessment of the factors affecting battery pack aging. This results in higher accuracy and reliability of the battery pack's aging value, thereby reducing the risk of battery pack use.
Owner:ECOFLOW INC

A compressor service life prediction method and an electronic starting controller

The application discloses a compressor service life prediction method and an electronic starting controller. The method comprises the following steps: obtaining working condition parameters of a compressor, performing time sequence unification and preprocessing on the working condition parameters, and generating quantitative indexes, wherein the quantitative indexes comprise long-time sequence sensitive indexes and short-time sequence fluctuation indexes; extracting physical characteristics and model automatic characteristics of the long-time sequence sensitive indexes and the short-time sequence fluctuation indexes, and obtaining a time sequence sample set; training and testing a pre-constructed fusion model by using the time sequence sample set, obtaining an evaluation result of the fusion model, and deploying based on the evaluation result. The long-period aging characteristics and high-frequency fluctuation characteristics in the compressor are processed in parallel by using the fusion model. Compared with the existing service life prediction mode, the overall precision is higher, the comprehensive consideration factors are more comprehensive, and the double paths can also adjust the hierarchical parameters to adjust the overall precision to retain stable characteristics and adapt to the dynamic working conditions of the compressor.
Owner:CHANGHONG HUAYI COMPRESSOR CO LTD

Product recommendation method and device, storage medium and computer equipment

The invention relates to the field of Internet technology and finance, and particularly discloses a product recommendation method and device, a storage medium and computer equipment, and the method comprises the steps: obtaining sample data; based on the sample data, training the initial recommendation model to obtain a target recommendation model; when any client accesses the dialogue system, obtaining second demand information and second user information of a target user corresponding to any client, and real-time product information and real-time risk information of each current product; and inputting the second demand information, the second user information, the real-time product information and the real-time risk information into a target recommendation model, obtaining a second product recommendation list corresponding to the target user based on model output of the target recommendation model, and returning the second product recommendation list to any client. According to the method, the user demand and the time-varying characteristics of financial products and the like are integrated in the product recommendation process, so that the accuracy and success rate of product recommendation can be greatly improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Calibration method and system for pantograph-catenary contact pressure sensor

The invention discloses a calibration method and system for a pantograph-catenary contact pressure sensor, and the method comprises the steps: sequentially applying a force with a specified strength at each intersection point of a sliding plate and a support of a pantograph to be measured, respectively measuring the voltage of each intersection point when the force is applied each time, and obtaining a sensitivity coefficient matrix of all intersection point pressure sensors based on the voltages; during application, the actual contact pressure of the pressure sensor is obtained by utilizing the sensitivity coefficient matrix according to the real-time voltage of the to-be-measured pantograph at each intersection point.
Owner:CHINA ACADEMY OF RAILWAY SCI CORP LTD +2

Route recommendation method and device, electronic equipment and storage medium

The invention discloses a route recommendation method and device, electronic equipment and a storage medium, and belongs to the technical field of Internet. In the method, after a departure place and a destination of a user side are obtained, N routes from the departure place to the destination are planned, and feature values of various characterization features representing user side route preferences are used as feature values of various characterization features representing user side route preferences; the method comprises the following steps: inputting a plurality of characterization features including at least one user feature of a user side and / or at least one travel feature of the user side in the N routes and feature values of the plurality of route features of the N routes into a pre-trained LightGBM to obtain a target route meeting the route preference of the user side in the N routes, and sending the target route to the user side, so that the user side can receive the plurality of characterization features including at least one user feature of the user side and / or at least one travel feature of the travel of the user side. According to the route recommendation method and the route recommendation device, the feature values of the various representation features representing the user side route preference and the feature values of the various route features of the N routes are comprehensively considered when the user appears every time, the routes are recommended to the user, the considered factors are comprehensive, and therefore the matching degree of the recommended routes and the user is high.
Owner:NANJING LINGXING TECH CO LTD

Emotion recognition method and device

The invention provides an emotion recognition method and device, and relates to the technical field of data processing. The method comprises the following steps: performing feature extraction according to acquired multi-modal data for emotion recognition to obtain various feature vectors; performing feature fusion on the multiple feature vectors to obtain fused features, and performing sentiment classification on the fused features by adopting a first preset classifier to obtain a sentiment recognition result; or adopting a second preset classifier to carry out sentiment classification on the multiple feature vectors to obtain a classification result corresponding to each feature vector, and fusing the classification results corresponding to all the feature vectors to obtain a sentiment recognition result. According to the method, emotion recognition is performed based on the multi-modal data, comprehensive utilization of various types of data is realized by performing feature extraction, fusion and classification on the multi-modal data, the emotion of the corresponding individual can be considered more comprehensively, the limitation of single-modal data is made up, and the accuracy and comprehensiveness of emotion recognition of the corresponding individual are improved.
Owner:HARBIN INSTITUTE OF TECHNOLOGY (SHENZHEN) (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)

Method and apparatus for determining coverage sector of directional antenna, and computer program product

The invention discloses a method and a device for determining a coverage sector of a directional antenna and a computer program product. Relates to the field of directional antenna signal transmission. The method comprises the following steps: acquiring node positions respectively corresponding to a plurality of sensors; determining a plurality of initial coverage sectors corresponding to the plurality of candidate transmission signals of the directional antenna; based on the node positions corresponding to the plurality of sensors and the plurality of initial coverage sectors, the coverage sector of the directional antenna is optimized with the lowest energy consumption of signal emission of the directional antenna and the maximum sensor coverage rate as the optimization target, and the target coverage sector of the directional antenna is obtained, the sensor coverage rate is used for indicating the proportion of the maximum number of the sensors covered by the candidate transmission signals in the initial coverage sector corresponding to the transmission state to the total number of the plurality of sensors. According to the method and the device, the technical problem of excessive energy consumption caused by incomplete consideration factors when the coverage sector of the directional antenna is determined in the prior art is solved.
Owner:STATE GRID BEIJING ELECTRIC POWER CO +1

An autonomous route planning method for unmanned aerial vehicles

The present invention proposes an autonomous route planning method suitable for UAVs, which can continuously adjust the priority of feasible paths for UAVs according to the mission requirements of the UAVs, the sensor information obtained by navigation and positioning sensors and environmental perception sensors, and dynamically judge the degree of obstacles and interference strike threats around the UAVs, determine the optimal path in the current environment, and realize autonomous navigation. This method improves the autonomous decision-making flight capability and working reliability of UAVs in complex environments, and has the characteristics of simple implementation, small calculation amount and high autonomous control level.
Owner:THE 54TH RESEARCH INSTITUTE OF CHINA ELECTRONICS TECHNOLOGY GROUP CORPORATION