31results about How to "Improve the effectiveness of analytical processing" patented technology

The invention discloses a method and a device for identifying isomerism graph and property corresponding to a molecular space structure, and machine equipment. The method comprises the following steps: carrying out feature description containing a topological structure on a heterogeneous graph to generate feature information; through sampling the isomerism graph and the feature information, generating a feature vector, corresponding to a key node, on a topological structure contained in the isomerism graph; performing aggregation processing on the feature vectors to generate graph representation vectors corresponding to the isomerism graphs; and according to the graph representation vector, performing classification processing on the isomerism graph to obtain a classification prediction result. Therefore, the identification of the graphical representation corresponding to the heterogeneous graph, such as the molecular spatial structure, can be realized through the neural network, the analysis and processing performance related to the isomerism graph is effectively improved, the neural network is not limited to the classification and identification of network data any more, and the application scene is greatly expanded.

The invention discloses a distributed smart grid data analysis platform based on cloud computing. The distributed smart grid data analysis platform comprises a data collection layer, a cloud computinglayer, an intermediate layer and a presentation layer. Each lower layer provides information and data services to the corresponding upper layer. The data collection layer collects distributed electric energy data and preprocesses the data, and provides original electric energy data to the cloud computing layer; the cloud computing layer introduces a Hadoop platform to perform data analysis taskssuch as user power utilization analysis, power distribution counting and the like on the electric energy data; the intermediate layer includes a Web background program, a communication service moduleWebHadoopServer communicated with a Web application and Hadoop, and a result data saving and loading module; the presentation layer achieves the presentation of the analysis result of the electric energy data. The platform utilizes the advantages of cloud computing platforms in processing of massive data to improve the efficiency of electric energy data analysis tasks.

The invention provides a dynamic car-pooling method and system based on automatic number plate recognition data. The system is capable of efficiently processing the automatic number plate recognition data based on a Hadoop and Spark parallel and processing frame under the cloud computation environment so as to immediately and accurately providing the car-pooling recommendation service for a user. Different from the traditional car-pooling system which needs a place of departure and a destination as query conditions, the method and system provided by the invention can analyze and excavate cars commonly appeared a certain number of monitoring points in parallel through the adoption of a frequent item set discovery algorithm after a period of time range is given, so that the dynamic recommendation function of the car-pooling group is realized.

The invention discloses a motion recognition system based on machine learning and radar combination. The motion recognition system comprises an acquisition module which is used for transmitting and receiving a radar signal and processing the received signal and transmitting the processed information signal to a cloud computing module; the cloud computing module which is used for computing the signal received from the acquisition module according to the data processing algorithm so as to obtain the motion recognition result, the hardware parameter and the algorithm related parameter and transmitting the motion recognition result and the hardware parameter to a rear-end processing module and locally storing the algorithm related parameter; and the rear-end processing module which is used fortransmitting the adjusting command to the acquisition module according to the motion recognition result and the hardware parameter so as to realize adaptive adjustment of the signal processing unit and transmitting the control command to the external equipment to realize control according to the motion recognition result.

The invention discloses a rail traffic data processing method and device. The rail traffic data processing method comprises the following steps: collecting generated message data and sending the collected message data to a preset message middleware; then distributing the message data in the message middleware to each preset server according to a preset data distribution mode; then parsing sub-message data in each server; and sending the parsed sub-message data to preset displayers separately for displaying. Compared with the prior art, the invention distributes the collected message data to aplurality of servers for parsing processing through the message middleware, and then sends the parsed message data to the preset displayers for displaying, so as to improve the data message analysis and processing capability, and achieve the purpose of real-time analysis and processing.

The embodiment of the invention discloses a power distribution network fault analysis method and device, equipment and a storage medium. The method comprises the following steps: obtaining data information which comprises the environment temperature, the environment humidity, the equipment performance, the equipment operation time, the port output/input flow, the processor utilization rate and thememory utilization rate; performing normalization modeling processing on the data information to generate a two-dimensional matrix; establishing a multi-layer training model; substituting the two-dimensional matrix into the multi-layer training model to obtain a first output value; if the first output value meets a preset threshold, storing the first output value into an experience library; and if the first output value does not meet the preset threshold, substituting the first output value into the multi-layer training model, and carrying out iterative optimization until the output value ofthe multi-layer training model meets the preset threshold. The method can improve the analysis and processing effect of the abnormal problems related to power distribution network communication, and reduces the time and manpower cost.

The invention provides a streaming data processing method and system adaptive to a cloud edge collaborative multi-data center scene. According to an allocated sub-task request, computing resources, memory resources, network resources and storage resources required for processing the sub-task request are allocated to a virtual machine, adn the virtual machine processes streaming data to be processed to obtain a current processing result; the current processing result is sent to a resource position where the next sub-task request is located according to the serial-parallel cooperative processing flow of each sub-task request and the processing priority of each sub-task request; and the demand of multi-data center resource cooperative processing is met.

The embodiment of the invention discloses a data analysis method and device. The method comprises the following steps: processing collected information according to a preset rule to obtain a relationship among elements in each piece of information; a corresponding specific knowledge graph is constructed according to the relation between the elements in each piece of information, and the specific knowledge graph is used for displaying an information combination with the incidence relation of each piece of information in a specific field by analyzing the relation between the elements in each piece of information; and generating an information analysis result according to the specific knowledge graph and the corresponding information pushing mode. According to the scheme provided by the invention, the analysis processing capability of specific information can be improved.

The invention relates to an infectious disease prediction method and system based on a hidden Markov model, and a medium. The method comprises the following steps: S1, generating a meteorological and hydrological observation sequence and an infectious disease outbreak state sequence; S2, preprocessing the meteorological and hydrological observation sequence to generate a training sample set, and dividing samples in the training sample set into a plurality of sample feature intervals according to sample features; S3, calculating an observation probability matrix and an outbreak state transition probability matrix according to the sample features, the sample feature intervals and the infectious disease outbreak state sequence; S4, generating a hidden Markov model according to the meteorological and hydrological observation sequence, the infectious disease outbreak state sequence, the observation probability matrix, the outbreak state transition probability matrix and the initial state probability distribution; and S5, predicting a meteorological and hydrological sequence at a certain moment in the future according to the historical meteorological and hydrological observation sequence, and substituting the predicted meteorological and hydrological sequence into the hidden Markov model to predict the infectious disease outbreak state. The method has the characteristics of high calculation speed, high accuracy and easy acquisition of sample data.

The invention relates to an electric power big data online analysis processing method and device, computer equipment, a storage medium and a computer program product. According to the invention, the observation data of each node in the power network can be collected in real time, data mining can be carried out on a large amount of observation data, useful power characteristic data can be obtained, and the comprehensive analysis processing capability of a large amount of different types of data is improved. The method comprises the following steps: acquiring original data of each node in a power grid; performing data preprocessing on the original data; carrying out attribute reduction on the preprocessed data to obtain power feature data; and classifying the power feature data according to a preset storage structure, and associatively storing the classified data in a preset database for data calling.

The invention relates to a confidential storage medium smashing system and method. According to the confidential storage medium crushing system, related information of a cutter and a confidential storage medium can be efficiently collected in real time through the information collection module and sent to the crushing system modeling module and the real-time crushing module in time; a crushing system regression model is established by adopting a crushing system modeling module based on a least square support vector machine algorithm, so that the data analysis and processing capability is improved; the information acquisition module and the crushing system modeling module are adopted to carry out regression prediction on the cutter crushing speed and the liquid cooling water flow speed based on the least square support vector machine algorithm, so that the cutter can be cooled, the confidential storage medium can be fully crushed, and the power consumption can be reduced.