55results about How to "Realize automatic prediction" patented technology

The invention discloses an epidemic disease morbidity index prediction method, device and equipment and a readable storage medium, and the method comprises the steps: obtaining public opinion data andepidemic disease data related to epidemic diseases, and calculating the epidemic disease morbidity index through the epidemic disease data; Inputting the epidemic disease morbidity index and target feature data extracted from the public opinion data and the epidemic disease data into a preset machine learning model and a deep learning model to obtain a predicted morbidity index corresponding to the epidemic disease; And sending alarm information to the disease control center system when the predicted attack index is greater than a preset threshold value, so that the disease control center system prompts workers to take epidemic prevention measures according to the alarm information. Through intelligent decision making, the epidemic index of the epidemic disease is automatically predicted,when the epidemic index is high, alarm information is sent out in time, and workers can take epidemic disease prevention measures in time conveniently.

The invention relates to a method for rapidly and safely predicting a tunnel face of an underground cavity on the basis of an image. The method comprises the following steps of 1, shooting by an infrared camera to acquire a tunnel face image in a current mileage; 2, carrying out image preprocessing on the tunnel face image; 3, carrying out clustering analysis; 4, carrying out lithologic identification to obtain lithologic classified information; 5, carrying out edge detection on the image preprocessed in the step 2; 6, carrying out boundary extraction to obtain bedding and jointing information of the tunnel face; 7, drawing a geologic sketch map of the current tunnel face by combining the lithologic classified information and the bedding and jointing information, and obtaining structural surface information of the current tunnel face; 8, moving to a next mileage and repeatedly carrying out the steps 1 to 7; 9, according to the extracted structural surface information, carrying out three-dimensional geologic modeling; 10, according to a model formed by the three-dimensional geologic modeling, carrying out rock mass analysis, predicting stability of rock masses and finally obtaining a cavity safety predicting result. Compared with the prior art, the method has the advantages of low noise, visual modeling and the like.

The embodiment of the invention provides an image processing method, device and system, electronic equipment and a computer readable storage medium, and belongs to the technical field of computers. The method comprises the steps of obtaining a current mammary gland ultrasonic image; processing the current mammary gland ultrasonic image through a first neural network model to obtain predicted pathological features of the current mammary gland ultrasonic image; processing the current mammary gland ultrasonic image through a second neural network model to obtain at least one prediction acoustic image feature of the current mammary gland ultrasonic image; obtaining a fusion feature of the current mammary gland ultrasonic image according to the predicted pathological feature and at least one predicted acoustic feature of the current mammary gland ultrasonic image; and processing the fusion features of the current mammary gland ultrasonic image through a third neural network model to obtaina benign and malignant prediction result of a lump in the current mammary gland ultrasonic image. According to the image processing scheme provided by the embodiment of the invention, the accuracy ofbreast ultrasonic intelligent diagnosis can be improved.

The present invention discloses a target data identification method and apparatus. The method comprises the steps of calling a preset information training model including association relationships between sample data identification and sample information templates; marking target data identification on target data in target information according to the information training model, and obtaining target information templates; and identifying the to-be-identified target data in the target information according to the target information templates. The target information templates can be automatically generated, so efficiency of marking the data identification is improved.

The invention relates to the technical field of computer vision and deep learning, and provides a microscopic image-based gramineous plant leaf stomatal index measurement method, which comprises the following steps: 1, acquiring a microscopic image of a gramineous plant leaf to be measured; 2, constructing and training an air hole recognition model based on a deep learning target detection algorithm; 3, constructing and training a cell network prediction model based on a deep learning semantic segmentation algorithm; 4, obtaining the total number of air holes by utilizing the air hole recognition model, utilizing the cell network prediction model to obtain a cell network prediction image, sequentially carrying out self-adaptive threshold binarization processing, skeleton extraction, morphological operation of firstly corroding and then expanding, connected domain counting and connected domain filtering on the cell network prediction image to obtain the number of cells, and calculatingstomatal indices. According to the invention, the precision and efficiency of stomatal index measurement can be improved, and the technical problem of misjudgment of stomata and cells due to the timeand labor waste and subjectivity in the prior art is effectively solved.

The embodiment of the invention discloses a method and device for predicting stopping accuracy in the precise stopping stage during ATO control. The method comprises the steps that according to recorddata, corresponding to a first running process of a target train, in various sub-systems of a train control system, target record data of the precise stopping stage during ATO control is extracted; characteristic values of all characteristics in a characteristic element set corresponding to a running path are calculated through the target record data, and a first characteristic value combinationis obtained; the first characteristic value combination serves as an input parameter of a pre-trained prediction model, the stopping accuracy of the target train in the first running process is predicted through the prediction model. The prediction model is obtained through machine learning and training, automatic prediction of the stopping accuracy is achieved, and dependence on work experience is got rid of. The prediction model is obtained through training of a lot of training samples, and the prediction model has a reliable data foundation, so that the prediction result is high in interpretability and reliability.

The invention discloses a method for estimating the remaining emergency maintenance time of equipment, an early warning method, a corresponding estimation system and a corresponding early warning system. The method for estimating the remaining emergency maintenance time of the equipment comprises the steps of configuring and storing the parameters, an alarm threshold value and a larger hazard threshold value of the equipment; obtaining monitoring parameter values and occurrence time of the monitoring parameter values of the equipment in real time, and collecting abnormal data according to thereal-time monitoring parameter values and the alarm threshold value; and generating remaining emergency maintenance time according to the collected abnormal data information records and the larger hazard threshold value. According to the method, an alarm threshold value can be configured according to the actual experience and the equipment conditions, and the greater hazard threshold value is configured according to the technical manual of the factory, so that the method achieves the estimation of the remaining time from now to the time when the monitoring parameters of the equipment reach thegreater hazard threshold value, provides the accurate remaining emergency maintenance time for a user, facilitates the user to carry out the corresponding processing in time according to the calculation result, saves the time of the user, and avoids the heavy loss.

The invention discloses a method for predicting the performance of an engine by a big data analysis model. The method mainly comprises the following steps: 1) determining input data; And 2) establishing an engine performance index prediction model and an engine performance classification detection model; ; 3) training self-learning parameters of all regression algorithms; 4) inputting the test sample matrix C into the engine performance index prediction model and the engine performance classification detection model after the self-learning parameters are adjusted to obtain the prediction errorrate of each regression algorithm; And 5) inputting the input data of the engine to be detected into an engine performance index prediction model so as to output a rotation speed prediction result ofthe engine to be detected under different working conditions. According to the method, engine performance prediction is carried out on the process detection data and the quality detection data generated in the engine production process, automatic prediction of the engine performance condition is achieved, and the reliability of the engine offline quality performance is guaranteed while the laborcost and the engine loss cost are saved.

The invention relates to a weather prediction model generation method and device, a computer device and a storage medium, and a weather prediction method and device, a computer device and a storage medium. The weather prediction model generation method comprises the steps of obtaining historical meteorological data of a plurality of position points corresponding to historical time points, the plurality of position points comprising observation position points; performing spatial gridding processing on the historical meteorological data of the plurality of position points to generate meteorological sample data corresponding to historical time points; obtaining weather phenomenon label data of observation position points corresponding to the historical time points; and training an initial weather prediction model through the meteorological sample data and the weather phenomenon label data corresponding to the historical time points to obtain a weather prediction model for predicting whether a weather phenomenon occurs or not. According to the method, the weather prediction model is trained by adopting the historical meteorological data, and the relationship between the meteorologicaldata and the weather phenomenon can be effectively obtained, so that the weather phenomenon can be automatically predicted according to the meteorological data.

The embodiment of the invention relates to a determination method for a silting area, a vehicle scheduling method, a device, electronic equipment and a storage medium. The determination method for thesilting area comprises the following steps: acquiring user travel characteristics corresponding to a grid area, wherein the user travel characteristics comprise travel behavior characteristics and travel willingness characteristics, the travel behavior characteristics are used for representing behavior characteristics generated when the user uses the vehicle, and the travel willingness characteristics are used for representing willingness characteristics of the user to use the vehicle; inputting the user travel features corresponding to the grid area into a traffic tool flow determination machine learning model to obtain flow information of the traffic tool; wherein the vehicle flow determination machine learning model is a machine learning model pre-trained according to a travel sample,and the travel sample comprises a user travel feature sample; and if the flow information of the vehicle meets the preset silting condition, determining that the grid area is a silting area. By adopting the method, the accuracy of vehicle siltation judgment can be improved.

The invention provides a natural gas pipeline corrosion failure time prediction method and device. The method comprises the following steps: determining pipeline parameters influencing the pipeline corrosion failure time by establishing a pipeline corrosion failure equation; selecting environmental parameters influencing the corrosion failure time of the pipeline; screening the pipeline parameters and the environment parameters based on correlation; and by taking the screened parameters as input variables and the corrosion failure time as output variables, constructing a prediction model, and predicting the corrosion failure time of the pipeline by using the trained model. According to the method, the pipeline parameters influencing the corrosion failure time are determined by establishing the pipeline corrosion failure equation, the environmental parameters of the pipeline are increased, and the parameters screened based on correlation serve as the input variables of the prediction model, so that the prediction precision of the prediction model can be obviously improved.

The embodiment of the invention discloses a household WiFi prediction method and a device, electronic equipment and a storage medium. The method comprises the steps of collecting WiFi data at a plurality of set moments, generating a plurality of mac lists, the mac lists comprise a plurality of WiFi signal sources, and the set moments are selected according to the fixed time period of the equipmentposition state; analyzing each mac list to obtain signal intensity information corresponding to each WiFi signal source at each set moment; and based on the signal intensity information, calculatinga prediction score of each WiFi signal source as the home WiFi to which the current mobile terminal device belongs, and determining the home WiFi to which the current mobile terminal device belongs according to the prediction score. Compared with the prior art, the method has the advantages that the matching relationship between the mobile terminal equipment and the home WiFi does not need to be manually input, automatic prediction of the home WiFi is realized, accurate matching between the mobile terminal equipment and the home WiFi is realized, and the use experience of a user is further optimized.

The invention relates to a liquid content analysis method and device, a medium, an upper computer and a drying line system. The liquid content analysis method comprises the following steps: collecting current various production process parameters of process equipment of a to-be-detected object; on the basis of the production process parameters, a liquid content prediction model corresponding to the process equipment is adopted for prediction, and a liquid content prediction result of the to-be-detected object is obtained; and carrying out qualification analysis according to the liquid content prediction result to obtain a liquid content qualification analysis result of the to-be-detected object. By adopting the method, the liquid content analysis efficiency can be improved, so that the production efficiency of a production line is improved.

The invention relates to the technical field of channel transmission, in particular to a channel allocation method based on channel idle duration prediction. The method comprises the following steps:classifying a to-be-transmitted service; selecting all idle channels in a spectrum pool, inputting the channel information of each idle channel into a prediction model for analysis, and determining the idle duration of each channel; and selecting an idle channel to transmit the to-be-transmitted service according to the classification result of the to-be-transmitted service, the type priority andthe service requirement of the to-be-transmitted service. According to the invention, the automatic prediction of the idle duration of the idle channel is realized, and a basis is provided for reasonably arranging service transmission; the to-be-transmitted service is classified, and when the emergency service is completely transmitted or is not transmitted, a reasonable idle channel is matched for the to-be-transmitted service in all other service types according to the service requirements of each to-be-transmitted service in all other service types through the combination with the idle duration and other contents of each idle channel, so the high efficiency and reliability of service transmission are ensured, and the transmission interruption probability is reduced.

The invention relates to the field of artificial intelligence, and provides a behavior prediction method and device based on zoom dot product attention, equipment and a medium. Firstly, a long time sequence is split based on a time interval, a user layer and a behavior sequence layer are separated by a time interval layer and are not directly connected, the sequence length in the interval is greatly reduced, and parallel computing is facilitated; the cross calculation amount is reduced, the operation efficiency is improved, encoding is carried out based on a scaling dot product attention mechanism, data features are optimized, to-be-predicted data is subjected to standardization processing to conform to the input data format of the model, the model is conveniently utilized for prediction, and then automatic prediction of behaviors such as purchasing is achieved based on an artificial intelligence means; and the accuracy and the prediction efficiency are higher. The invention also relates to a blockchain technology, and the behavior prediction model can be stored in the blockchain.

The invention provides a fan life prediction method, system and device and a readable storage medium, and the method comprises the steps: setting a temperature detection point at an air outlet position of a server, so as to monitor the environment temperature of a fan; the service life of the fan at different temperatures and rotating speeds is obtained, and the service life reference value of the fan is obtained accordingly; when the server runs, environment temperature information and rotating speed information of the fan are obtained through the BMC; determining a first service life weight of the fan according to the environment temperature information of the fan, and determining a second service life weight of the fan according to the rotating speed information; obtaining the current running duration of the fan through the BMC; according to the first service life weight, the second service life weight and the operation duration, the service life consumption value of the fan in this operation is calculated; updating the life reference value according to the life consumption value; if the service life reference value is lower than the service life threshold value, warning information is sent out through the BMC. According to the method, the service life of the fan can be predicted by utilizing the chip temperature and the holding time output by the BMC, and system warning is carried out.

The invention discloses a scoliosis progress prediction method and device based on an X-ray film. The method comprises the following steps: acquiring and preprocessing spine X-ray film data and a hand X-ray film of a patient within a preset time period; and according to the preprocessed spine X-ray film data and the hand X-ray film, constructing a deep learning model to evaluate the scoliosis degree and predict the scoliosis progress. By the adoption of the technical scheme, automatic intelligent scoliosis progress estimation can be achieved, manual rapid and accurate processing and analysis of medical images can be replaced, the problems that doctors in multidisciplinary cross times are weak in competitiveness and lack of doctors can be solved, and meanwhile the influence of X-ray film radiation on body functions of sick children can be reduced.

The invention provides an early warning method based on time series data of an industrial control system. The early warning method comprises the steps of: 1, receiving time series data input by a user or data of acquisition equipment; 2, establishing an optimal prediction model through a neural network; and 3, receiving current data of the equipment, calling the optimal prediction model to predict data of the equipment at the next moment, and judging whether to give an alarm or not. The early warning method and the system can achieve the prediction of the future data according to the current time sequence data, and achieve the early warning of a safety accident.

The invention discloses an intelligent prediction method and device for residual evaluation terms, computer equipment and a storage medium, and relates to the technical field of intelligent prediction. The method comprises the following steps: acquiring wounded person data, and verifying the wounded person data; inputting the checked wounded person data into a pre-training model, and predicting whether the wounded person is evaluated or not by utilizing the pre-training model; if the prediction result output by the pre-training model is to evaluate the disabled person, calling a preset disabled person evaluation model to perform disabled person evaluation term prediction on the disabled person to obtain disabled person evaluation terms of the disabled person, and classifying the injuries corresponding to the same disabled person evaluation term into the same injury combination; and verifying the disabled evaluation terms of the wounded person, and correcting the disabled evaluation terms according to a verification result so as to avoid injury crossing among different injury combinations. According to the method, the automatic prediction of the disability evaluation terms of the injury is realized, the prediction efficiency is improved, and the cost is reduced.