81 results about "Time perception" patented technology

The invention puts forward a power distribution equipment state visualization platform based on big data. The platform comprises a data processing module, a data analysis module and an evaluation module, wherein the data processing module is used for obtaining multi-platform data, processing the multi-platform data and displaying the processed data; the data analysis module is used for carrying out big data integration, storage and retrieval and data mining analysis; and the evaluation module is used for generating a power distribution equipment evaluation model based on the big data, evaluating the power distribution equipment according to the power distribution equipment evaluation module, and generating a corresponding processing strategy according to an evaluation result. By use of theplatform, the business requirements of intensive development and lean management can be met, the multisource information interaction fusion ability of the equipment is improved, the full view real-time perception, and the multidimensional intelligent monitoring and control of the power distribution equipment can be realized, equipment operation risks can be prevented in advance, reaction speed for emergency events can be improved, and the full life cycle of the equipment can be subjected to management transparency and high efficiency.

The invention relates to a multi-data set and collaborative tensor decomposition-based scenic spot recommendation method. According to the method, user behavior information of different data sources is utilized to provide fine-grit travel recommendation services for the users. The method comprises the following steps of: firstly obtaining information of a plurality of data sets from a social network site; constructing a user-scenic spot-time tensor on the basis of user travel history information, combining a collaborative tensor decomposition model to decompose and complement the tensor so as to obtain travel preferences of the users; and finally recommending proper scenic spots according to the complemented user-scenic spot-time tensor and travel cities and time scene information input by users. According to the method, time perception-based scenic spot recommendation services can be provided for the users.

The invention discloses an intelligent vehicle GPU parallel acceleration trajectory planning method, and the method comprises the steps of obtaining a real-time perception obstacle grid graph, a global reference path, intelligent vehicle real-time GPS information and an upper layer decision instruction at a CPU end, carrying out the sampling along the reference path, and obtaining a series of target sampling terminals; at the GPU end, obtaining a sampling terminal sequence, the real-time state information of an intelligent vehicle, the perception environment grids and the historical frame planning track parameters, designing a track generation kernel function, generating an intelligent vehicle stable tracking track connected with an initial state and a terminal state for each target sampling terminal, designing a track evaluation kernel function, and evaluating the cost of each track; and returning the track data to the CPU end, selecting an optimal track and matching the optimal trackwith the speed value, obtaining a track planning result and transmitting the track planning result to the control execution mechanism. The method is used for improving the real-time planning efficiency of the track of the intelligent vehicle, achieving the purposes of efficiently generating a large number of tracks in real time and further improving the track planning result.

A real-time attendance method using a GSM/3G mobile phone perception technology is realized in the invention. The technology includes the following steps: building a 3G/GSM perception base station platform by using combining four modules comprising a protocol parsing module, a user identity simulation control module, an information interaction control module and a real time management module with a GSM perception base station module, a 3G perception base station module and a user identity stimulation hardware module, perceiving the mobile terminal (mobile phone) IMSI number of an employee, obtaining the telephone number MSISDN of the user through the IMSI number, storing the information in a company employee information database, obtaining the online/offline information of the employee through the real-time perception of the mobile phone state of the employee, and displaying the online/offline information of the employees in an operation interface. The method can realize the real-time perception of the presence information of the mobile terminal independent of a service provider in order to perceive the online/offline information of the employee in real time and display the online/offline information corresponding to the user's name.

The invention discloses a fuzzy clustering-based time-aware position recommendation method for a position-oriented social network. The method comprises the following steps of 1, acquiring user sign-indata information including user information, position information and time information; 2, extracting access position geographic features through the position information, extracting user time features through the time information, obtaining user feature vectors according to the access position geographic features and the user time features, and then obtaining position recommendations based on auser fuzzy clustering algorithm; calculating the position attraction of each position in each time period according to the time information and the position information, and then obtaining position recommendation based on the position attraction; 3, predicting an access value of the user to each unsigned-in under time perception through a collaborative filtering method according to the position recommendation; 4, giving a target user and time, and screening each access value Top-which is not signed in; and recommending the user according to the position of N.

The invention discloses a site recommendation method based on time and geographical location information integrally. The site recommendation method based on time and geographical location information integrally comprises the following steps: 1, acquiring site attendance data of a user; 2, carrying out multi-center clustering on historical attendance sites of the user to obtain an active zone of the user, and calculating the probability that the user arrives at an unattended site on the basis of the distance from the center of the active zone of the user to the unattended site of the user; 3, calculating similarity of various time periods, filling up the attendance times of the user at the unattended site according to the similarity of the time periods by using existing attendance data, and calculating site similarity under time perception according to filled-up attendance data; 4, predicting the attendance times of the user at the unattended site on the basis of the probability that the user arrives at the unattended site and the site similarity under the time perception; and 5, recommending sites with top N predicted values for every use according to the predicted values in the step 4 so as to generate a final recommendation result. By the site recommendation method, the accuracy and the recall rate site recommendation can be improved.

The invention relates to a balanced and coordinated control system for real-time perception of pedestrians and motor vehicles, which belongs to the field of road traffic signal control of intelligenttransportation. The system comprises a center traffic signal control system, a plurality of pieces of intersection field equipment and a transmission network. The field equipment at a single intersection includes a traffic signal controller, a traffic signal lamp, a vehicle detector, a pedestrian crossing request button and a pedestrian crossing voice prompt column. The invention further providesa balanced and coordinated control method for real-time perception of pedestrians and motor vehicles. The system and the method of the invention well combine green wave coordinated control, delay coordinated control and pedestrian crossing request control, realize balanced and coordinated control of motor vehicles and pedestrians, and can obviously improve the travel experience of traffic participants.

The invention provides a discovery and real-time display system and method for an SDN (Software Defined Network) network topology. The method comprises the following steps that: after openflow switches are added into an SDN network, a connection relation acquisition module acquires port connection information among the openflow switches based on a protocol mechanism between an SDN controller and the openflow switches; when one openflow switch leaves the SDN network, the connection relation acquisition module updates corresponding port connection information; when a browse requester needs to browse the SDN network topology, a providing module sends a browse request to the connection relation acquisition module based on a second interface provided by a second interface module and a first interface provided by a first interface module; the connection relation acquisition module feeds back corresponding port connection information based on the received browse request; and the providing module provides the received port connection information for the browse requester in order to realize real-time perception and real-time display of network equipment.

The invention discloses a time perception-based microblog propagation model, and belongs to the technical field of computer communication. The model releases information to a blogger firstly; fans adopt analysis of different behaviors along with time perception; four fan types (S-Susceptible, L-Lurked, I-Infected and R-Removed) are defined; a propagation status of information among the fan types is analyzed; information propagation rules (an incomplete reading behavior, direct immunization, propagation and a lurked period) are defined; a probability of following propagation rule transfer amongthe fan types is defined; mathematic modeling is performed according to the propagation rules; and the time perception-based microblog propagation model is realized by utilizing simulation. The modelcan be closer to an actual condition of microblog information propagation and reflect a propagation process of microblog information more really; and users can timely obtain, propagate and shield theinformation according to characteristics of the information propagated in microblogs.

The invention provides an energy-saving control method of wireless access points (AP) of a wireless local area network (WLAN) system, and belongs to the technical field of communication. According to the scheme, the energy-saving mode of AP hibernation-wakeup is mainly employed, hibernation APs are selected based on network real-time perception data, the access selection problem of a new AP of the hibernation APs during unloading of a user is optimized through a reverse auction access AP selection algorithm, and the optimization of the energy consumption of the WLAN system is achieved. The method includes: firstly measuring the energy consumption of AP equipment, and determining an AP hibernation-wakeup threshold through a marginal effect analysis of the energy consumption; then sensing the network load state in real time through a central controller, obtaining an associative matrix of users and APs, and establishing a relation model between the energy consumption, the coverage and the user QoE and AP selection; and finally completing the access selection of accessing to the new AP of a to-be-unloaded user based on a reverse auction algorithm to realize hibernation of idle APs in the system. According to the method, the wireless coverage and the user QoE are satisfied, and the energy consumption of the WLAN system brought by redundant APs can be effectively reduced.

The embodiment of the invention provides a video frame processing method and device, a computer readable medium and electronic equipment. The video frame processing method comprises the steps of calculating initial time perception information and/or initial space perception information of each video frame in a to-be-processed video; obtaining initial time perception information and/or initial space perception information of a predetermined number of video frames in front of each video frame in the to-be-processed video; determining final time perception information of each video frame according to the initial time perception information of each video frame and the initial time perception information of the predetermined number of video frames; and/or determining final spatial perception information of each video frame according to the initial spatial perception information of each video frame and the initial spatial perception information of the predetermined number of video frames. According to the technical scheme provided by the embodiment of the invention, the kinematicity between the video frames can be considered, so that the TI and/or SI of the obtained video frames can be ensured to accord with objective description.

The invention discloses a commodity scoring model construction and recommendation method and system based on time perception. The method comprises the following steps of in the first stage of a model,using super-strong feature mining capability of a convolutional neural network to mine high-dimensional feature vectors for capacity learning users, commodities and rating information, introducing rating time features critical to project rating prediction; in the second stage of the model, training a random forest regression model through the high-dimensional feature vector learned by the convolutional neural network to predict the user rating on the project , so that recommendation is performed according to the predicted rating. Data of various forms can be utilized and recommended at the same time, the scoring accuracy of the scoring model is improved, and therefore accuracy of the recommendation method is improved.

The invention discloses a web temporal object model-based outdated webpage information automatic discovering method, belongs to the field of research of data quality, and relates to the technical fields of temporal Web, network information quality estimation, semantic comprehension and extraction of temporal information, constraint and reasoning of temporal information, automatic screening of consistency of webpage information and the like. Aiming at the phenomenon of low web data quality caused by temporal inconsistency, a Web temporal object model is established on the basis of different temporal sensitivities of different web-pages, network data temporal consistency constraint relation, reasoning mechanism and an algebraic operation rule are constructed, automatic screening is performed and outdated information in the Web webpage is promoted, and information with timeliness and relevancy is provided for a network user. The method can be widely applied to the aspects such as quality ordering of similar websites and search ordering of time perception, and the Web information quality is improved to a certain extent.

The invention discloses an automatic identification control system for markers, which comprises at least one control terminal and servers in communication connection with the control terminals respectively, and is characterized in that the control terminal comprises an image acquisition module which is provided with an image acquisition device for acquiring images of the markers and is used for acquiring feature code information of the fixed markers; The positioning system comprises a positioning unit and a GIS data unit and is used for collecting and generating spatial geographic position information and time information of the fixed marker and generating a specific geographic position; The attitude acquisition module is used for realizing real-time perception and acquisition of the attitude of the terminal; The communication module is used for communicating with the server; And the output module comprises a display unit and a printing unit, and is used for processing the informationgenerated after the processing of the server so as to generate a bill or an image which corresponds to the fixed marker and carries the terminal posture information, and displaying and/or outputting the bill or the image. The state information of a terminal operator and the information of the environment where the terminal operator is located can be collected in real time, and portable and real-time detection and processing of corresponding markers are achieved.

The invention relates to a method and a system for context perception computing based on a dummy perception capability part. A physical perception module acquires and sends real-time perception data of physical perception equipment; a logic perception module abstracts physical perception capability into logic perception capability, sends the logic perception capability and encapsulates and sends original perception data; a context server registers, manages and removes the logic perception capability and a self-adaptation entity need and binds the logic perception capability and the self-adaptation entity need according to different application types; a self-adaptation entity dummy perception capability part describes and sends context needs and read requirements of the self-adaptation entity, is bound with a corresponding logic perception unit, analyzes context messages and provides the analysis of the context messages to the self-adaptation entity; and a self-adaptation entity module sends the read requirements according to computing needs and complete self-adaptation service once the context messages are obtained. The invention supports the dynamic sharing of the context messages in a pervasive computing environment and the real-time property and the reliability of the computing of the self-adaptation entity.

The invention discloses a real-time task and resource scheduling method with a function of machine startup time perception in virtualized clouds to reduce impact of time overhead of starting hosts and creating virtual machines on timeliness of suddenly adding tasks, increase task completion rate and reduce energy consumption of a cloud service system. The technical scheme is that a free emergency virtual machine is arranged on each started host; when a new task arrives, mapping relationships between all waiting tasks and the virtual machines are cancelled and the new task is added into a waiting task queue; and then waiting tasks are scheduled one by one according to a principle of earliest deadline first, i.e., the task is mapped to the existing virtual machine, if the operation is infeasible, a new virtual machine is added for executing the task, and if the operation is also infeasible, the CPU frequency of the free emergency virtual machine is increased for executing the task. With the adoption of the method, the influence of delay caused by starting the hosts and creating the virtual machines on a task with relatively short deadline can be transferred and the success rate of task scheduling is increased as far as possible.

The invention discloses a method for implementing mobile internet real-time stream data acquisition and analysis, which comprises real-time acquisition, real-time parsing, data real-time access and real-time analysis. The real-time acquisition is that O domain data is acquired in real time from a light-splitting output point of network element equipment by a converging shunting equipment and afterthe O domain data is processed, the O domain data is sent to probe equipment; and the real-time parsing is that by the probe equipment, each port optical signal received from the converging equipmentis decrypted, a user number is refilled and data which can be read is obtained, and the data is transmitted in real time to an analysis link in a protocol data stream mode. The method has the beneficial effects that real-time acquisition on massive O domain data can be implemented with low investment, complex analysis is completed, real-time application is supported, and real-time perception on amobile user internet behavior is promoted, so that the foundation is laid for real-time scene marketing and service.

The invention relates to a video action recognition method based on a time perception structure, which is designed based on a time perception structure of full-packet three-dimensional convolution, uses a small number of parameters to model the multi-scale time information, and is a very efficient time modeling structure. A monitoring flow network is further arranged, the convergence speed of themodel is increased, the recognition accuracy of the model can be further improved on the basis of the time perception structure, the dependence on a pre-training data set is reduced, and the deployment can be rapidly achieved for a specific small-scale problem, and the method has robustness for behaviors of different time scales.

The invention provides a mobile terminal task migration method based on time perception in a collaborative environment. The mobile terminal task migration method comprises the following steps: step 1,acquiring computing task information in an edge cloud collaborative environment and a deployment situation of an edge server; step 2, evaluating the average migration delay of the calculation task under each migration strategy; step 3, evaluating the energy consumption level of each edge server; and step 4, evaluating the utility value of each migration strategy through a standardization and normalization method, and selecting an optimal migration strategy. According to the method, a migration strategy is given in real time based on time perception according to edge cloud resource information, average migration delay of tasks is ensured, energy consumption of an edge server is optimized, calculation migration time can be shortened, and service performance can be improved.

The invention discloses a traffic safety facility management and control system and method. The invention discloses a traffic safety management system based on Internet of Things, relates to the fieldof traffic management systems, depends on advanced technologies such as Internet of Things, big data, cloud computing and traffic geographic information systems, is used for traffic safety facility digital management, Internet of Things online management and control and event real-time perception, and is provided with an application platform for query, maintenance, statistical analysis, real-timedata application and facility management and service. Real-time monitoring of the traffic safety facility state can be achieved. The integrity of facilities is guaranteed to the maximum extent. Facility information is pushed to related traffic participants in real time. The related traffic participants are perceived in advance. Forecast is conducted in advance. Driving safety is guaranteed. Traffic accidents are prevented. The industry management level and efficiency are comprehensively improved, and manpower, material resources and time cost are saved.

The invention discloses a weather and time perceived personalized POI sequence recommendation method. The method comprises the following steps of 1, data preprocessing; step 2, POI popularity modeling; step 3, user interest modeling; and step 4, performing of personalized POI sequence recommendation of weather and time perception. The method has the beneficial effects that the method focuses on discussing the influence of weather and time factors on POI sequence recommendation, focuses on considering the weather factors, such as avoiding recommending outdoor POIs to users in rainy days, and focuses on considering the time factors, such as preferentially accessing gymnasiums by the users instead of accessing at night. The personalized POI sequence which is popular and maximizes the interestpreference of the user in a specific weather characteristic and time interval can be recommended to the user, so that the personalized POI sequence better conforms to an actual application scene.

The invention relates to a high-speed domain name resolution method based on stateless scanning. The method comprises: encrypting a UDP protocol header of the DNS query message; periodically sending DNS query messages, analyzing and verifying the recovered reply message; recording a DNS reply message of which the UDP protocol header conforms to the encryption feature and a corresponding IP; and verifying the IP and generating a reliable DNS service IP pool according to a result, when a domain name resolution request exists, selecting the IP as a resolution server to resolve the domain name corresponding to the request, continuously receiving the UDP message, verifying the UDP protocol header and the DNS protocol header, and recording the current UDP message information if the UDP message and the DNS protocol header pass the verification. According to the method, load balancing is carried out among different resolution servers, domain name resolution efficiency is improved, real-time perception of global domain name information change can be realized by a single device, accuracy and real-time performance of a PDNS collection system are greatly improved, and a data basis is providedfor threat intelligence association analysis and global DNS malicious pollution problem analysis.