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

193results about How to "Guaranteed pertinence" patented technology

Banking business marketing data processing method and system based on multiple channels

The invention relates to the technical field of banking business marketing data processing, in particular to a multi-channel-based banking business marketing data processing method and system, and aims to guarantee the accuracy and reliability of a marketing strategy by integrating multi-channel data and acquiring and verifying a banking business marketing data source in real time. Then, a machine learning algorithm is used for generating a customer portrait, analyzing a behavior pattern and potential requirements of the customer portrait, generating a personalized marketing strategy, a natural language processing technology is combined, real-time performance and pertinence of marketing content are ensured, pushing is carried out according to customer preferences during pushing, the pushing opportunity is optimized, and the system monitors feedback behaviors in real time after pushing, so that the marketing quality is improved. A strategy effect is evaluated, marketing activities are optimized by using an A / B test, closed-loop feedback is formed, a strategy is continuously improved, and high efficiency and accuracy of a marketing scheme are ensured. According to the method, automatic strategy generation and optimization are realized through the AI technology, the marketing efficiency and customer experience of banking business are greatly improved, and the method is suitable for a multi-channel data processing scene.
Owner:HUNAN QIAOJIE NETWORK TECHNOLOGY CO LTD

Athlete real-time posture analysis and correction method and system based on computer vision

The invention relates to the technical field of computer vision, in particular to an athlete real-time posture analysis and correction method and system based on computer vision, and the method comprises the following steps: obtaining multi-view action video data and multi-modal sensor data of an athlete, and pre-establishing a standard action model library; based on the multi-view action video data, a posture estimation result is obtained through a self-adaptive multi-scale posture estimation algorithm; according to a posture estimation result, utilizing a dynamic time sequence diagram convolutional network to realize action recognition; fusing the attitude estimation result with the multi-modal sensor data to obtain a fusion feature; on the basis of the fusion features and a standard action model library, generating a personalized standard action model to determine the difference between the actual action of the athlete and the personalized standard action model; generating a correction suggestion according to the difference; an optimal feedback mode is determined, and correction suggestions are provided for the athletes; the action details of the player can be captured with millimeter-level precision, and the technical actions of the player can be comprehensively evaluated.
Owner:TIANHE COLLEGE GUANGDONG POLYTECHNIC NORMAL UNIV

Production management method and device for flat curved surface product

The invention relates to the technical field of image processing, and discloses a production management method and device for a flat curved surface product. The method comprises the following steps: carrying out feature extraction processing on the surface morphology of a flat curved surface product material to obtain a curved surface feature topological graph; performing non-uniform curvature partition processing on the curved surface feature topological graph to obtain a flat curved surface product processing area division scheme, and performing variable curvature compensation path planning processing to obtain a self-adaptive processing track sequence; performing real-time curved surface error detection processing on the self-adaptive processing track sequence to obtain local morphology deviation data; performing curved surface incremental forming compensation processing on the local morphology deviation data to obtain dynamic correction parameters; and performing curved surface quality feature correlation tracing processing on the dynamic correction parameters to obtain a full-cycle quality evaluation report of the flat curved surface product. Real-time error detection, dynamic compensation and quality tracing in the machining process of the flat-curved-surface product are achieved, and therefore the machining precision and quality stability of the flat-curved-surface product are improved.
Owner:XIAN HONGYING TECH CO LTD

Visual inspection multitask learning method based on multimodal prompt cooperation

The invention discloses a visual inspection multi-task learning method based on multi-mode prompt collaboration, which takes a multi-mode prompt collaboration multi-task learning network as a vision-language model to realize visual inspection multi-task learning and comprises a language prompt encoder and a visual encoder. The language prompt encoder comprises a frozen language encoder and a language encoder which are parallel to each other; the frozen language encoder is used for ensuring that the adjustment of the language encoder is not greater than a threshold limit; the language encoder and the visual encoder calculate the cosine similarity of the features of the language encoder and the visual encoder through a coupling function to measure the similarity degree of the two tasks, so that the consistency of visual and language representation of task groups with high total similarity is improved to the greatest extent, and efficient joint training of visual inspection multi-task learning is realized. According to the invention, the adjustment effect of the visual inspection multi-task model is improved, and the pertinence and generalization of the visual inspection multi-task learning method are ensured.
Owner:STATE GRID ANHUI ELECTRIC POWER CO LTD ELECTRIC POWER SCI RES INST

Open flood and inland inundation chain generation disaster intelligent early warning directional release method and system

The invention provides an external flood and inland inundation chain disaster intelligent early warning directional publishing method and system, and relates to the technical field of flood disaster early warning, and the method comprises the steps: obtaining a city monitoring data set of a target city through connecting a city monitoring Internet of Things; waterlogging association identification is carried out based on the city monitoring data set, and a monitoring association identification result is obtained; constructing an external flood and internal waterlogging chain disaster prediction model; based on the monitoring association identification result, according to the external flood and internal waterlogging chain disaster prediction model, obtaining an urban internal waterlogging risk assessment report; generating first early warning information based on the urban inland inundation risk assessment report; determining an early warning target population based on the target city; and directionally issuing the first early warning information to the early warning target crowd. The technical problem that the information transmission efficiency is low due to the fact that a traditional early warning publishing mode is not accurate enough is solved, and the technical effects of intelligently and directionally publishing the early warning information and improving the information transmission efficiency and accuracy are achieved.
Owner:应急管理部大数据中心

Intelligent maintenance system for coal mine conveyor belt

The invention belongs to the technical field of coal mine conveyor belt maintenance, and particularly discloses an intelligent maintenance system for a coal mine conveyor belt. The system comprises a belt information import module, a belt operation monitoring module, a belt operation analysis module, a belt maintenance judgment module, a belt maintenance confirmation module, a database and a belt maintenance execution terminal. According to the method, when the current belt position deviates, the belt position overhaul maintenance degree is counted by combining historical belt overhaul data, overhaul confirmation of the belt position is carried out, the effectiveness of belt overhaul is guaranteed, the time regularity analysis is carried out on the temperature, the sound loudness and the vibration frequency, and the accuracy of belt overhaul is improved. The pertinence of coal mine conveyor belt environment analysis is guaranteed, predictive maintenance is facilitated, meanwhile, the coal mine adhesion degree of the target belt is analyzed by setting the position weight and combining the adhesion growth rate and the coal mine adhesion ratio, and the influence of the coal mine adhesion position on the belt is accurately evaluated.
Owner:CHINA SHENHUA ENERGY CO LTD SHENDONG COAL BRANCH

Database monitoring processing method and system for reservoir, medium and electronic equipment

The invention discloses a database monitoring processing method and system for a reservoir, a medium and electronic equipment, and relates to the field of data processing. The method comprises the following steps: acquiring the positions and the number of a plurality of sensors of different types arranged in a reservoir; determining a first sampling frequency of each sensor according to the position, the number and the reservoir information of each type of sensor; acquiring first reservoir data acquired by each sensor at the first sampling frequency at the first time; predicting a first water level of the reservoir after a preset duration according to the first reservoir data and historical reservoir data in a database; and if the first water level is greater than or equal to a threshold value, generating an early warning prompt. By implementing the technical scheme provided by the invention, the sensor layout and sampling strategy can be adjusted according to the dynamic change of the reservoir geographic characteristics, and the representativeness and prediction precision of the water level monitoring data are improved.
Owner:武汉盛科达科技有限公司

Vocal music pronunciation training system

The invention discloses a vocal music pronunciation training system, and relates to the technical field of vocal music training, and the vocal music pronunciation training system comprises a sound collection module, a sound preprocessing module, a feature extraction module, a model construction module, and a standard pronunciation database module. The system has the advantages that the standard vocal music pronunciation data is pronunciated through the exclusive sound model of the trainee, so that the difference between the current vocal music pronunciation of the trainee and the standard vocal music pronunciation can be visually displayed, and the difference coefficient between the sound of the trainee and the standard pronunciation is analyzed through the comparative analysis module; according to the vocal music pronunciation training method, different types of vocal music pronunciation training schemes are formulated in a personalized manner according to the difference, and the personalized training scheme considers the individual difference between different trainers instead of using the same training scheme by all trainers traditionally, so that the training efficiency is improved. And the pertinence and effectiveness of training are further ensured.
Owner:HUAINAN NORMAL UNIV

Online and offline combined digital interactive teaching method and system

The invention relates to the technical field of mixed learning, in particular to an online and offline combined digital interactive teaching method and system, and the method comprises the following steps: collecting online and offline learning data of students, carrying out the statistics of the number and frequency of various interaction types, including the number of discussion times, the number of question answering times and the group cooperation frequency, and generating an initialized interactive data set. According to the method, redundancy and deficiency of various interactions are calculated through the information entropy technology, information vacancy in learning is helped to be recognized, teaching content is optimized, student requirements are matched, the optimized design defines a learning target, an expected interaction frequency is set, the interaction adjustment effect is verified through a simulation test, it is ensured that teaching activities are more targeted, and the teaching efficiency is improved. The interaction frequency is dynamically adjusted in real-time teaching, the sense of participation of students is improved, the learning effect can be monitored in real time, the learning motivation and achievement of the students are improved, and implementation of personalized learning is promoted.
Owner:YUANJIAN UNIVERSE (CHONGQING) TECHNOLOGY CO LTD +1

Household unmanned control management system based on washing robot

The invention belongs to the technical field of machine control and management, and particularly discloses a household unmanned control and management system based on a washing robot, which comprises a washing robot main body and a washing control system, the washing control system comprises a clothes identification and analysis module, an environment information acquisition module, a clothes cleaning confirmation module, a user interaction verification terminal, a database and a clothes processing execution module. According to the invention, when the clothes information of the dirty clothes placement area is collected, whether the dirty clothes placement area needs layered detection is judged according to the collected overall scanning visual image, overall spectral data and overall scanning depth image, so that the problem of insufficient attention to clothes identification accuracy at present is effectively solved; according to the method, the mode, the water amount and the adding amount of the detergent of subsequent automatic clothes washing can be accurately controlled, misjudgment is reduced, and meanwhile, the flexibility and pertinence of washing setting are guaranteed by confirming the washing operation instruction.
Owner:ZHEJIANG HOOEASY SMART TECH

Micro course generation method based on OCR (Optical Character Recognition) and server

The invention discloses a micro course generation method based on OCR recognition and a server, and relates to the field of image data processing, and the method comprises the steps: collecting maintenance record document image data, and carrying out the optical character recognition processing of the maintenance record document image data, and obtaining digital text data; performing natural language processing on the digital text data according to a preset bidirectional encoder representation model, and integrating the terminology information, the fault code information and the operation step information into structured knowledge data; obtaining a knowledge level parameter and a post information parameter of the target user, and performing difficulty grading on the structured knowledge data according to the knowledge level parameter to obtain difficulty grading knowledge data; performing knowledge range screening in the difficulty grading knowledge data according to the post information parameters to obtain target knowledge data; and selecting teaching materials matched with the target knowledge data from the knowledge resource library, and generating a micro course resource bundle according to the teaching materials. By implementing the method, the updating efficiency of the training data can be improved.
Owner:BEIJING COLAYA TECH & SERVICE

Complex database question answering system based on large language model

The invention discloses a complex database question-answering system based on a large language model, which relates to the technical field of large language models and comprises an instruction receiving module, a question-answering matching module, a statement generating module and a question-answering processing module. The instruction receiving module is used for receiving a natural language instruction input by a user; the question and answer matching module is used for converting and matching the natural language instruction to obtain a related database table; the statement generation module is used for forming the natural language instruction and the related database table description into prompt, and sending the prompt to a large language model to generate a corresponding SQL query instruction; the question and answer processing module is used for executing the SQL query instruction and feeding back a query result to the user; the method and the device are used for solving the problem that the flexibility and the efficiency are not high when a non-professional user queries or operates a database due to the fact that the requirement for a user instruction is too high in the query process of an existing database question-answering system.
Owner:BEIJING ZHONGKE STRON CLOUD INTELLIGENT TECH CO LTD

Multi-scene intelligent camera shooting, patrolling, analyzing and managing system for regional security and fire protection

The invention belongs to the technical field of multi-scene patrol analysis management, and particularly discloses a multi-scene intelligent shooting patrol analysis management system for regional security and fire protection. Comprising a regional information recording module, a regional security monitoring module, a regional security analysis module, a regional hidden danger monitoring module, a regional hidden danger analysis module, a regional fire-fighting monitoring module, a regional fire-fighting analysis module, a regional early warning confirmation module and a regional early warning management terminal. According to the invention, the pertinence of regional monitoring analysis is guaranteed by analyzing the security and protection qualified index, the fire hazard qualified index and the fire hazard qualified index of each monitoring region, so that the discovery timeliness of potential problems is improved, and meanwhile, according to the security and protection qualified index, the fire hazard qualified index and the fire hazard qualified index of each monitoring region, the monitoring accuracy is improved. And the early warning item of each monitoring area is confirmed, so that the accuracy and effectiveness of early warning are guaranteed, and the management efficiency of area management is improved.
Owner:WUHAN BOHAI RADIO CO LTD

Oil sunflower field precise fertilization control system based on unmanned aerial vehicle hyperspectral technology

The invention discloses an oil sunflower field precise fertilization control system based on an unmanned aerial vehicle hyperspectral technology, and relates to the technical field of fertilization control. The system carries out precise region division on an oil sunflower field by utilizing a GIS technology through fusion of multi-source data such as hyperspectral data, soil humidity and temperature; and accurate fertilization can be carried out in different management areas according to soil characteristics and crop requirements. The differentiated fertilization strategy can reduce excessive fertilization and fertilizer waste and optimize the utilization efficiency of the fertilizer. The crop growth model is established through the deep learning technology, and the system can accurately calculate the required fertilization amount according to the specific growth conditions and historical data of each region, so that the growth conditions of the oil sunflowers are optimized, and the overall yield of crops is improved. The problem that a traditional fertilization system is difficult to effectively deal with soil and environment differences in different areas is solved. Through a hyperspectral technology and multi-source data acquired by a sensor, the system can realize accurate fertilization according to environmental differences in a field.
Owner:ILI KAZAKH AUTONOMOUS PREFECTURE AGRI SCI RES INST

Construction method and system for neural rehabilitation evaluation model

The invention relates to the technical field of data processing, in particular to a construction method and system for a neural rehabilitation evaluation model. The method comprises the following steps: acquiring multi-modal data of a neurological rehabilitation patient; performing feature extraction according to the multi-modal data of the neurological rehabilitation patient to obtain multi-modal feature data of the neurological rehabilitation patient; performing data classification on the multi-modal feature data of the neurological rehabilitation patient to obtain multi-modal feature classification data; and marking the multi-modal feature data of the neurological rehabilitation patient by using the multi-modal feature classification data to obtain multi-modal feature marking data of the neurological rehabilitation patient so as to carry out neurological rehabilitation evaluation model construction auxiliary work. According to the method, the model capable of comprehensively and objectively evaluating the rehabilitation progress of the neurological rehabilitation patient is constructed in an auxiliary manner, so that a scientific basis is provided for rehabilitation treatment.
Owner:FUDAN UNIVERSITY

Infrared imaging detection method and system for power equipment

The invention relates to the technical field of imaging detection, in particular to an infrared imaging detection method and system for power equipment. The method comprises the following steps: firstly, acquiring a normal working temperature range of equipment and an actual temperature value of each region in an infrared image; then analyzing the equipment state according to the standard range and the actual value, and performing image segmentation and analysis on the abnormal heat area to obtain temperature rise reason parameters; performing cooling compensation analysis on the local heat area to obtain a compensation parameter; finally, the cooling amount of the area is adjusted according to the compensation parameters, and cooling procedure parameters are issued to a control system to be executed. The acquired infrared image is analyzed and processed, so that temperature rise reason parameters causing local hot spots are accurately positioned; carrying out cooling compensation analysis on the local hot area according to the local hot area, and generating targeted cooling process parameters; and finally, the parameters are issued to an equipment control system, the cooling amount and the cooling mode of the corresponding area are automatically adjusted, and therefore accurate and efficient active cooling is achieved.
Owner:GUANGDONG WEIYANG TECH CO LTD

Cyclone separator optimization system and method based on machine learning

The invention relates to the technical field of separation devices, and discloses a cyclone separator optimization system and method based on machine learning, and the system comprises a user operation module, a numerical simulation module and a deep learning module. The method comprises the steps that when a user terminal inputs cyclone separator parameters in a cloud platform, a system calls a cyclone separator parameter database; if no corresponding cyclone separator parameter exists in the cyclone separator parameter database, performing analogue simulation calculation according to the cyclone separator parameter input by a user, and establishing a flow prediction model according to a simulation result; the flow prediction model performs prediction according to the simulation result; after the prediction is finished, performing comparison according to a prediction result; and finally obtaining optimized parameters required by the parameters of the cyclone separator, and transmitting the optimized parameters to a user terminal through the cloud platform. According to the method, the separation efficiency of cyclone separators with different designs is predicted, and manpower, material resources, time, cost and the like are saved in actual production.
Owner:KUNMING UNIV OF SCI & TECH

Media enterprise information system intelligent operation and maintenance method based on big data analysis

InactiveCN118964134AGuaranteed accuracyEffective monitoring layoutEnsemble learningHardware monitoringMedium enterprisesBusiness enterprise
The invention provides a media enterprise information system intelligent operation and maintenance method based on big data analysis, and the method comprises the steps: carrying out the monitoring layout of a sensor based on a media enterprise information system architecture, and collecting the multi-dimensional business data of a media enterprise information system based on a monitoring layout result; constructing a data analysis model, analyzing the multi-dimensional business data based on the data analysis model, and determining system hidden dangers and system performance trends; early warning is carried out based on the system hidden danger and the system performance trend, and an operation and maintenance decision is determined based on early warning and analysis results; and performing system repair on the media enterprise information system based on the operation and maintenance decision. According to the method, targeted system repair is carried out on the media enterprise information system according to the operation and maintenance decision, the operation and maintenance accuracy and the operation and maintenance effect of the media enterprise information system are guaranteed, and efficient and accurate operation and maintenance requirements are met.
Owner:JIANGSU ZHENYUN TECH CO LTD

Contraband detection model training method and contraband detection method

The invention discloses a contraband detection model training method and a contraband detection method. Acquiring backbone network features of the sample image; the sample image comprises a contraband label; according to the backbone network features, splicing the sample images to obtain a spliced image; performing a first round of training on the contraband detection model based on the spliced image to obtain a model prediction result of the sample image; determining a detection result of the sample image according to the contraband label of the sample image and the model prediction result; and if the detection results of the sample images are not consistent, updating the sample data and the loss function of the next round of training according to the detection results of the sample images, and repeating the training process according to the updated sample data and the loss function until the detection results of all the sample images are consistent. According to the embodiment of the invention, the training efficiency and pertinence of the prohibited article detection model are improved, the accuracy of the trained model is improved, and the prohibited article detection accuracy is improved.
Owner:ZHEJIANG PECKERAI TECH CO LTD

Method for modeling photovoltaic power station for relay protection by using fault recording data

The invention relates to a method for modeling a photovoltaic power station for relay protection by using fault recording data. The method comprises the following steps: step 1, acquiring a fault recording file by a fault recording analysis system; 2, processing voltage and current data based on the fault recording file obtained in the step 1, and then calculating the short-circuit current of the photovoltaic power station; 3, obtaining a latest short circuit calculation model based on the voltage and current data processed in the step 2, and obtaining a final short circuit calculation model through multiple times of model correction; and 4, performing short-circuit calculation by using the short-circuit calculation model corrected in the step 3. According to the invention, simulation and actual short-circuit tests can be avoided.
Owner:ELECTRIC POWER SCI & RES INST OF STATE GRID TIANJIN ELECTRIC POWER CO +2

Motion sickness detection device and system and storage medium

The invention relates to the technical field of physiological signal processing, and discloses a motion sickness detection device and system and a storage medium. Based on a signal preprocessing module, a feature extraction module, a feature weighting module, a global feature capture module and a classification detection module which are sequentially connected, the device executes the following steps: performing preprocessing and data enhancement on an electroencephalogram signal to obtain a preprocessed electroencephalogram signal; a convolution module is used for sampling up and down in a time frequency dimension to obtain local time frequency characteristics of the preprocessed electroencephalogram signals; performing feature weighting on the local time-frequency features to obtain a feature weighted graph; inputting the feature weighted graph into a Transform module to capture global features to obtain the global features; according to the method, global features are used as data to be classified to be input into a full connection layer and finally pass through a Softmax layer to calculate prediction probabilities of multiple categories, so that efficient feature extraction and accurate classification of the electroencephalogram signals are realized, and motion sickness symptoms of a subject are effectively monitored and evaluated.
Owner:HANGZHOU INTERNATIONAL INNOVATION INSTITUTE OF BEIHANG UNIVERSITY

Urban building solid resource supervision method and system

ActiveCN119027056AAccurately grasp the processing situationEnsure reasonable handlingClimate change adaptationOffice automationDistributed servicesService efficiency
The embodiment of the invention discloses an urban building solid resource supervision method and system, and the method comprises the steps: generating solid resource supervision early warning time and supervision nodes through obtaining a project process node and a project progress table, generating project information collection time, monitoring the project progress at preset time intervals to confirm whether to start a supervision process or not, and carrying out the supervision of the solid resources. According to the method, effective supervision can be performed on specific supervision items in different stages, item information of corresponding item process nodes is collected when item information collection time is met, legality of the item information is confirmed, accurate mastering of processing conditions of solid resources is facilitated, reasonable processing of the solid resources is guaranteed, effective utilization of service resources is guaranteed, and the service efficiency is improved. The monitoring path corresponding to the process node of the project is generated to provide clear guidance for subsequent monitoring work, timeliness and pertinence of monitoring are ensured, and effective utilization of resources and pertinence of monitoring are ensured by distributing service resources and generating the monitoring path according to the actual condition of the project.
Owner:GUANGDONG CTV INFORMATION TECH CO LTD

Off-road running training plan generation method and device, electronic equipment and storage medium

The invention discloses an off-road training plan generation method and device, electronic equipment and a computer storage medium. The method comprises the steps of obtaining feature information of a target off-road race and an initial long-term training load value of a user; according to the feature information and the initial long-term training load value, judging whether the user can successfully complete the target off-road race or not; and when it is judged that the user can successfully complete the target off-road running event, determining course arrangement of an off-road running training plan based on the training course library. In the whole off-road running training plan generation process, the off-road running training plan with pertinence, reasonability and scientificity can be generated, and therefore the off-road running ability of the runner can be improved in a targeted mode by combining the characteristics of the target off-road running event and the actual ability of the runner.
Owner:SUUNTO SPORTS TECHNOLOGY (DONGGUAN) CO LTD

Short-circuit reverse-sequence protection method for three-phase alternating current and related equipment

The invention provides a short-circuit reverse-sequence protection method for three-phase alternating current and related equipment, and relates to the technical field of new fields. Complex three-phase current information is converted into positive, negative and zero-sequence components which are easier to analyze through symmetric component decomposition. By calculating the anti-sequence component ratio and the zero-sequence component ratio, the ratios are kept relatively stable during normal load change, so that the influence of load change on fault judgment can be effectively eliminated. By introducing a first-order derivative and a second-order derivative, not only can the instantaneous characteristic change when the fault occurs be reflected, but also the dynamic process of fault development can be reflected, which is essentially different from a method which purely depends on a fixed threshold. According to the multi-dimensional feature analysis method, load fluctuation, harmonic interference and real faults can be effectively distinguished, the accuracy of fault recognition is improved, and misoperation of a protection device is avoided.
Owner:SHENZHEN SKONDA ELECTRONICS

Structural design optimization method, device and equipment for cylindrical heat absorption tower

The invention provides a structural design optimization method, device and equipment for a cylindrical heat absorption tower, and relates to the technical field of data processing. The method comprises the following steps: determining optimization variables and constraint conditions of structural characteristics of the heat absorption tower according to structural design requirements of the cylindrical heat absorption tower; according to a genetic algorithm, initial population individuals are randomly generated within the limitation range of the optimization variables, constraint condition verification is carried out on the optimization variables corresponding to the initial population individuals, and qualified individuals are screened out; based on a crossover and variation rule, optimization variables corresponding to the qualified individuals are adjusted, and new individuals are generated through parameter recombination and random variation; and calculating a fitness value of a new individual according to an optimization objective function of the heat absorption tower, dynamically adjusting control parameters of a crossover and variation rule, and repeatedly iteratively optimizing a population until optimization variables are converged to an optimal solution meeting design requirements. According to the technical scheme, the efficiency and comprehensiveness of structural design optimization of the cylindrical heat absorption tower can be improved.
Owner:NORTHWEST ENGINEERING CORPORATION LIMITED

Platform operation and maintenance method, electronic equipment, medium and product

The invention discloses a platform operation and maintenance method, electronic equipment, a medium and a product, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining the current state information of a service platform; a current state feature vector is extracted from the current state information through a preset bert pre-training model, and the preset bert pre-training model is obtained through fine adjustment of a preset fine adjustment operation and maintenance task; and inputting the current state feature vector into a preset neural network decision model to obtain a target operation and maintenance strategy of the service platform. According to the method, automation and intelligentization of operation decision making are realized, and the decision making network model can automatically learn and optimize from a large amount of network data, so that the accuracy and effect of the operation and maintenance strategy are continuously improved, the manual intervention demand and dependence are reduced, the operation efficiency is improved, and the labor cost is reduced.
Owner:CHINA MOBILE INFORMATION TECHNOLOGY CO LTD +1

Business data processing method and system based on multiple channels

The invention discloses a business data processing method and system based on multiple channels, and the method comprises the steps: obtaining the basic information of a to-be-sold commodity and a preset advertisement putting amount, calculating the average re-purchase period of the commodity through analyzing the historical business data of each channel, comparing the remaining re-purchase time of a user with the average re-purchase period, and determining a first intention user. If the number of the first intention users meets the advertisement putting demand, allocating the advertisement putting amount and screening the advertisement putting users based on the remaining re-purchase time and a preset advertisement putting preference prediction algorithm; otherwise, the second intention users who have purchased the commodities recently are found out by analyzing the commodity set with high relevance, and the final advertisement putting object is determined by combining the conditions of the two types of intention users. According to the invention, by analyzing the multi-channel business data and the user re-purchase cycle, the intentional user is accurately positioned, the advertisement putting is optimized, and the advertisement conversion rate and the resource utilization rate are effectively improved.
Owner:SHENZHEN HUAYUE SHUZHI TECHNOLOGY CO LTD

Obstacle association method and device, computer equipment and storage medium

The invention provides an obstacle association method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining measurement data from at least one sensor, and enabling the measurement data to comprise a plurality of obstacle measurements and detection information thereof; for each obstacle measurement to be associated, selecting a target reference point type from a plurality of predefined candidate reference point types according to detection information of the obstacle measurement to be associated; determining a measurement reference point from the detection information of the obstacle measurement based on a target reference point type selected for each obstacle measurement; determining a matching measure between a measurement reference point and a track reference point based on the measurement reference point measured by the obstacle and the track reference point determined for the fused track; according to the calculation result of the matching measurement between all the obstacle measurements and all the fused tracks, the association relationship between the obstacle measurements and the fused tracks is determined, and the accuracy and the reliability of obstacle association can be remarkably improved by adopting the method.
Owner:CHINA FAW CO LTD

Urban green infrastructure comprehensive benefit applicability evaluation method based on subjective and objective weights

PendingCN121961268ARespond to low-carbon development goalsAchieve full-dimensional coverageClimate change adaptationInstrumentsEntropy weight methodOperations research
The invention provides an urban green infrastructure comprehensive benefit applicability evaluation method based on subjective and objective weights. The urban green infrastructure comprehensive benefit applicability evaluation method comprises the steps of establishing a basic evaluation system, screening indexes, calculating index weights, calculating quantitative indexes, calculating qualitative indexes, performing grading evaluation, performing standardized score assignment and performing comprehensive evaluation. The basic evaluation system is of a three-layer structure and covers four criteria of runoff regulation and storage benefits, environmental benefits, economic benefits and social benefits and 19 indexes; a subjective weight is determined through an analytic hierarchy process, an objective weight is determined through an entropy weight method, and a comprehensive weight is obtained in combination with a D-S evidence theory fusion method; quantitative indexes are calculated through methods such as hydrological simulation, and qualitative indexes are rated by public; the indexes are unified into dimensionless scores through standardized score assignment, and finally an evaluation result is obtained through weighted summation. According to the method, the applicability quantitative evaluation of matching of the typical green infrastructure and the site condition construction target is realized, and a scientific and quantitative decision support tool is provided for sponge city planning.
Owner:YANGTZE ECOLOGY & ENVIRONMENT CO LTD +1

A method and system for fit welding of an automobile bumper

ActiveCN121650265BEnsure welding fit accuracyImprove welding qualityEnergy absorptionVibration detection
The application relates to a matching welding method and system of an automobile bumper, and relates to the technical field of welding, which comprises the following steps: collecting first vibration detection information of a bumper beam clamp, second vibration detection information of an energy absorption box clamp and welding parameters of a welding device; determining first vibration offset parameters according to the first vibration detection information; determining second vibration offset parameters according to the second vibration detection information; analyzing the first vibration offset parameters and the second vibration offset parameters to determine the relative offset amount of the energy absorption box; based on the welding parameters, calling a welding current position point and a current welding power; combining the welding current position point and the relative offset amount to determine welding offset influence parameters; when and only when the welding offset influence parameters meet a preset moving reference reference value, combining the welding offset influence parameters and the current welding power to determine welding adjustment information, and outputting the welding adjustment information. The application has the effect of improving the welding quality of the energy absorption box and the bumper beam.
Owner:YUYAO TELSONIC AUTOMATION TECH CO LTD