35 results about "Social perception" patented technology

The invention discloses a user discovery and resource allocation method based on social perception in D2D communication and belongs to the mobile communication field. The method specifically comprises the following steps of firstly, establishing a D2D communication scene which meets the limitation of the social relationship and the physical location; secondly, carrying out pairing and optimization on D2D communication users in the scene according to a discovery and pairing algorithm of the D2D communication users; thirdly, further computing the entire system throughput CTotal of a base station; fourthly, taking the system throughput CTotal as a target function, combining a limiting condition and adopting a quantum-behaved particle swarm optimization algorithm to solve to obtain an optimal particle position to carry out system subcarrier and power allocation; and lastly, carrying out simulation verification on user discovery and resource allocation based on the social perception in the D2D communication. The method has the advantages that an adaptive abdication under the conflict condition of the residual energy and the request of user nodes is considered; the subcarrier allocation and the power allocation are combined, a resource co-allocation method is provided, and a simulation result shows that the D2D discovery and pairing algorithm based on social perception has better performance.

The invention discloses a routing method of social perception and probability prediction for a mobile opportunity social network. According to the method, two kinds of related centrality are provided in an initialization phase by researching the liveness, interest and mobility of nodes and the relationship between the nodes so as to simplify a network model; and in a routing phase, message transmission is carried out on the basis of comprehensive consideration of social perception and probability prediction depending on the simplified network model. In addition, a message transcript control strategy is adopted in the message transmission process to effectively control the number of transcripts of a message in the network and reduce the consumption of network resources. The simulation experiment results show that compared with the other three classical routing methods, the method disclosed in the invention has the advantages of effectively improving the delivery rate of the message and reducing the overhead rate of the network.

The invention relates to an urban agglomeration height space information and contour line extraction method. the method is characterized in that , for extraction of urban buildings, remote sensing data and social perception data are fused, a high/low density building area of a plot scale is established, and the extraction of the urban buildings is realized by combining a multi-view difference feature map; for extraction of urban building heights, dense point clouds are generated by matching every two of forward-looking, backward-looking and front images of a resource No.3, a digital surface model is solved by adopting a TIN linear interpolation method, the thought of point cloud classification is introduced, accurate ground points are obtained, and a digital elevation model is established.According to the invention, the forward-looking, backward-looking and front images of the resource No.3 are fully utilized, and a system framework for extracting urban building information and building height information is innovatively constructed, models of an urban contour line, an urban undulation degree and an urban growth height are obtained on the basis of the system framework, and an evolution pattern of urban transverse area expansion and longitudinal height increase is revealed.

The invention provides a method and a medium for extracting green degree space of an urban agglomeration. The method comprises the following steps: acquiring high-score remote sensing data of urban agglomeration and extracting land cover data of urban agglomeration; Obtaining the social perception data of urban agglomeration, and extracting the social function attribute data of urban agglomerationland; According to the cover data and social function attribute data, the land of urban agglomeration is classified, and the information about the land and greenness of urban agglomeration is obtained. According to the classification information, the greenness of urban agglomeration is extracted. The present invention solves the problem that only a single remote sensing data can obtain the land cover information in the related art, and the social function attribute of the urban green space cannot be obtained, and realizes the statistics and research of the urban agglomeration green space containing the social function attribute.

The invention discloses a space keyword query method based on social perception in distributed environment. The method comprises: through analyzing a Top-k query problem, providing an index for solving the problem and a query framework, an index structure introducing social information, using a retrieval characteristic of keywords, providing a Top-k query algorithm based on social perception on the basis of a SDPR distributed index structure, through inputting a query parameter, a result being first k objects with highest rankings in a data set, the objects satisfying a specific ranking function. Through space keyword query with weight, the method makes query more accurate, and a more accurate result can be obtained.

The invention particularly relates to a personalized dynamic vehicle sharing method and system based on price benefit and social perception, the invention provides the personalized dynamic vehicle sharing method based on price benefit and social perception, the social relationship concerned by users and the pricing mechanism are simultaneously applied to the vehicle ride-sharing matching service.In the matching process, under the premise of guaranteeing the basic travel constraint of passengers, not only the price income brought by new passengers to drivers is considered, but also the priority of passengers with certain social relations to be arranged on a vehicle is considered, and the comfort degree of passengers and the price income of drivers are taken into account under the conditionof meeting the basic travel needs of passengers. The invention can provide a whole set of optimization mechanism of matching process for users. By utilizing upper limit of price benefit and social relation, branch boundary algorithm and index mechanism to cut search space, the invention improves matching speed of passengers and vehicles, enhances system operation efficiency and improves riding experience.

The invention discloses a PM2.5 deep learning inversion method combining the remote sensing data and the social perception data. The PM2.5 deep learning inversion method comprises the steps of preprocessing the PM2.5 data of a ground station point, the remote sensing data, the social perception data and the auxiliary data; performing feature variable extraction and calculation on the multi-source data by using a geoscience space statistics and analysis method and a remote sensing information processing means; carrying out space-time matching on the multi-source data in a gridding mode, taking a grid with a ground station point true value as a training sample, and generating a multi-source data set with uniform space and time; normalizing the grid data set with the site PM2.5 true value, then inputting the grid data set into a deep learning model for training, and inverting the unknown grid PM2.5 concentration through the model after the grid data set passes the verification; and carrying out fine PM2.5 space-time distribution mapping on an inversion result. According to the method, the multi-source information can be effectively mined by using a deep learning technology, the defect of a traditional statistical model in a nonlinear problem is overcome, and the higher inversion precision and the finer space-time PM2.5 distribution are obtained.

The invention discloses a multisource heterogeneous data-based real estate information visualization system. The system is characterized by comprising a real estate information module, a regional function module, a traffic analysis module, a social perception module and a comprehensive evaluation module, wherein the real estate information module is used for displaying real estate information; theregional function module is used for carrying out statistical analysis on quantities and distances of infrastructure around real estates; the traffic analysis module is used for carrying out statistical analysis on traffic conditions and peak hours around the real estates; the social perception module is used for mining texts of social media data and displaying social perception conditions aroundthe real estates through word frequency word clouds, keyword extraction and topic models; and the comprehensive evaluation module is used for establishing a multiple linear regression model by applying statistical methods such as multiple linear regression analysis and the like, determining real estate evaluation indexes and methods, and obtaining pointed real estate cost performance-based transaction suggestions so as to support more reasonable house purchasing decisions.

The invention provides a method for sensing network sudden hotspots based on perception maximization. The method comprises the following steps: collecting historical sudden events in a network and corresponding post messages at first, defining reference time and difference between time of post messages of participates and the reference time, defining evaluation indexes for sensing the post messages according to perception maximization, and training a perceptron set; aggregating the post messages acquired in real time in the perceptron set into different clusters on the basis of a text similarity detecting method, wherein each cluster is regarded as a potential hotspot; and detecting every potential hotspot, and when the observation amount of the post messages corresponding to a certain potential hotspot at a certain time is not smaller than a threshold value, regarding that the potential hotspots burst out. All user nodes in a social network are regarded as the perceptron according tocommunication characteristics of information in the social network, all information which circulates in the social network is regarded as perceptual information, and the information which circulates in the social network, namely social perception, is sensed through the perceptron which monitors the social network.

The invention relates to an urban agglomeration living space construction time identification method, which comprises the steps of collecting Landsat5/7/8 data through a google earth engine platform, and calculating time sequence data of three indexes, namely, NDVI, MNDWI and SWIR; obtaining urban residential land boundary vector data through map data and crawler analysis, and carrying out data analysis and space connection in Arcgis; classifying and identifying the residential land before and after a specific time point through a random forest classification method; and identifying the construction time of the residential land in a specific time period year through a time sequence segmentation method to complete the identification of the construction time of the whole residential land. According to the method, the construction time of the urban residential land is identified by fusing the spectrum and texture information of the remote sensing data and the social perception data, so that the problems of a semantic gap and a time gap existing in the two data are solved, and scientific and technical means support is provided for researching horizontal and vertical expansion and space-time evolution of the urban residential land.

The invention provides an urban land function recognition method based on remote sensing pictures and interest point data. A conventional urban functional area recognition method only aims at single remote sensing image data or social perception data, and neglects overall functional attribute information of an urban area to a certain extent. In order to solve the problem, a multi-mode urban land function recognition framework is provided. The method comprises the following steps: constructing a deep multi-channel residual neural network for urban remote sensing image recognition, and exploring spatial geographic features in a remote sensing image; secondly, frequency function density of interest point distribution of different functional areas of the city is researched, and function distribution characteristics of the city area are extracted based on metric learning; and finally, fusing two features of different dimensions in the heterogeneous feature fusion module, thereby further improving the urban land function recognition performance. Experiments prove that the method has good practicability and can be widely applied to recognition of urban functional areas.

The invention relates to an environment adaptive routing method and system based on Bayesian classification and a medium, and the method comprises the steps: constructing a dynamic network environment learning model, and carrying out the dynamic perception of each node, and obtaining a dynamic perception information set of each node; selecting any encountering node pair, and obtaining a cooperation type vector between the two encountering nodes and cooperation degree information sets corresponding to the two encountering nodes one by one according to the dynamic sensing information sets of the two encountering nodes based on a Bayesian classification method; according to a preset adaptive data distribution strategy, completing data distribution of the two encountering nodes according to the dynamic sensing information set, the cooperation degree information set and the cooperation type vector of the two encountering nodes; and traversing each encountering node pair to complete data distribution of the social perception network. According to the method, the self-perception of a dynamic change network environment is effectively improved, the self-adaptability of a data distribution strategy and the self-adjustability of a cooperation degree incentive mechanism are enhanced, and the data distribution efficiency is remarkably improved.

The invention provides an infection transmission prediction method and system based on Internet of Things perception. The method comprises the steps of: obtaining first close contact population information of a first region according to a first information collection module; obtaining first positioning sensing information; obtaining first social perception information; constructing an Internet of Things perception model which comprises a first preprocessing function; obtaining a first action track which is the action track of an infected person; carrying out anti-aggregation analysis on the first close contact population to obtain a plurality of infection aggregation points; carrying out infection aggregation point analysis and infection time point analysis, and determining a first aggregation distribution characteristic and a first time distribution characteristic; and performing prediction according to an ARIMA model to obtain first prediction information and first propagation information. With the method and system adopted, the technical problem that perception speed and perception accuracy are low in the prior art due to complexity of an application environment and imperfection of a perception technology is solved.

The invention relates to a residential area extraction and type recognition method based on remote sensing and social perception data. The method comprises the steps of remote sensing image preprocessing, angle difference feature calculation, residential area Point of Interest recognition, residential area boundary extraction and residential area type recognition. Aiming at the blank of extractionand type recognition of urban residential quarters at present, remote sensing and social perception data are fused, a technical scheme for quickly and effectively carrying out the extraction and typerecognition method of the urban residential quarters is provided, and an accurate data source is provided for urban planning departments and urban researchers; the effect of extracting residential areas in real time can be achieved; in addition, due to the fact that text similarity analysis is combined, residential area surface vector files can be quickly and effectively provided for urban researchers and urban planning departments.

The invention discloses a modeling analysis method and system based on social perception data, and the system comprises a perception data obtaining module, an impact factor modeling module, and an explanatory analysis output module. The perception data obtaining module is used for collecting and obtaining related multipath original data for a traffic road section, and carrying out the primary preprocessing; the influence factor modeling module is used for establishing a relation model of called environmental influence factors and pedestrian road section traffic accident data, the explanatory analysis output module is used for explaining and analyzing predictive variables and influence factors in the relation model, and the perception data acquisition module is electrically connected with the influence factor modeling module. The influence factor modeling module is electrically connected with the explanatory analysis output module, the incidence relation between influence factors and pedestrian traffic accidents is established through social perception data, variable prediction and explanatory analysis output of the influence factors are carried out, and the method has the advantage that environment and pedestrian traffic accident analysis is carried out through the perception data.

The method comprises the following steps: determining a social network-combined MEC-D2D network architecture corresponding to a research area, a data transmission model, a consumption model and a social trust matrix; according to the social trust matrix and a data execution consumption calculation function and a data transmission consumption calculation function in the consumption model, determining a maximum long-term system network utility function and constraint conditions corresponding to the research area; a Lyapunov optimization algorithm is utilized to decouple the maximized system network utility function, and three deterministic optimization objective functions are obtained; and finally, according to the total amount of calculation task data corresponding to the research area and an optimization algorithm, solving the three deterministic optimization objective functions to obtain optimal network parameters. By applying the network parameters, the energy consumption of the equipment execution process and the equipment transmission process in the MEC-D2D network can be reduced for a long time.

The invention discloses a social perception-based mobile ad hoc cloud terminal cluster construction and service method, which comprises the following steps that: 1) user terminals are randomly distributed in a cell served by a base station, and periodically report terminal resource states of the user terminals to a base station controller by taking a fixed time slot as a unit; 2) the base station controller establishes and maintains a user encountering information graph and a terminal equipment resource table; and 3) after receiving the terminal resource state, the base station controller autonomously constructs an ad-hoc cloud terminal cluster by adopting an ad-hoc cloud terminal cluster construction algorithm based on non-uniform granularity according to the number requirement of the terminal clusters. According to the method, the terminals are classified according to the performance of the resources, the terminal clusters are formed by the nodes with similar performance, the tasks are cooperatively completed through near-distance D2D communication, and the matching of the tasks and the resources is effectively realized, so that the task scheduling speed is increased, and the terminal resource utilization rate of the network is increased.