61 results about "Mobility prediction" patented technology

The invention discloses a group switch method based on a mobility prediction. Multi-service group user ends which move along fixed routes in a major public transportation system need to apply to a target base station for group switch according to detected changes of a wireless channel. The method further provides a mobility prediction based on location information, which comprises the following steps: the process of reselecting a target cell is simplified by using a mobile historical database; and the target cell is enabled to obtain relative information of all group users in advance through a backup backbone network. Required channel resources are reallocated through strategies such as borrowing channels, etc. Therefore, the system switch speed of the group user terminal is greatly improved, and QoS of broadband wireless communications in the switch process is guaranteed. The method further discloses a group switch system based on the mobility prediction, which mainly comprises a location information unit, a switch judging unit, a channel borrowing and resource allocating unit and a channel allocating unit.

Mobile Edge Computing (MEC) has the advantages of high bandwidth and low latency and has attracted extensive attention in the study of next generation of mobile networks by providing service environment and computing power at the edge of mobile networks. The invention discloses a vehicle task unloading and user mobility prediction and edge cache fusion policy in a vehicle networking environment. An MEC-based unloading framework is built. Tasks can be unloaded to an MEC server for vehicle-to-infrastructure (V2I) communications or can be unloaded to an adjacent vehicle for vehicle-to-vehicle (V2V) communications. Considering task backhaul failure caused by link disconnection caused by user mobility, the Kalman filter algorithm is used to predict link connection estimation, and a user can select a stable service node during task request and task collection. Cache decisions are made before the service node first returns a task to a request vehicle. Access latency, traffic load and networkcost can be significantly reduced through content cache.

A multi-attribute handover judging method for a heterogeneous vehicle communication network comprises the following steps: a handover management entity reads information on a candidate network in a field network report buffer entity, and the diameter of the coverage region of the candidate network is calculated; a mobility prediction information management entity acquires position information and speed information of a mobile user, and sends the position information and the speed information to the handover management entity; possible residence time and throughput capacity in each neighbor access network of the mobile user is estimated, when the throughput capacity during handover is higher than the throughput capacity in a normal state, the candidate network is added in an alternative list; an optimal target access network is determined to be switched into the network by the handover management entity via an analytic hierarchy process and according to service quality requirements; when the intensity of the current switch-in network signal is lowered to a threshold value, a handover execution instruction is sent to carry out handover. The multi-attribute handover judging method provided by the invention avoids unnecessary handover when a traveling vehicle passes through a region covered by heterogeneous access network, reduces handover delay and ensures the continuity of the communication.

A corporate payment, liquidity, and cash management optimization service platform helps meet the need in corporate banking to leverage more of the value of the bank relationship with the corporation. The platform integrates into the supply chain processes of the corporate customer and may provide liquidity forecasting and optimization services. The platform provides a one-to-many model in which the bank serves many corporates with one system to save operating costs and gain economies of scale. In addition, the platform leverages existing bank services, while at the same time providing modular, configurable services in a secure, integrated solution.

System and method embodiments for mobility prediction in a wireless network enable the wireless network to determine the location of a wireless device with minimal transmissions from the wireless device. In an embodiment, the method includes negotiating with a mobile device to determine a mobility prediction algorithm and a condition upon which the mobile wireless device will report the actual location of the mobile device, training the mobility prediction algorithm using prior mobile wireless device location and timestamp information, determining a predicted location of the mobile device using the mobility prediction algorithm, and setting an predicted location for the mobile device at a time as the actual location for the mobile device at the time when failing to receive a location report from the mobile wireless device, wherein the mobile device transmits actual location information after the training period only if the condition is met.

The invention generally relates to a method and system for distribution of computational capacity for a plurality of end-devices in different localities using a decentralized edge architecture. The method and system clusters a plurality of moving nodes capable of offering highly virtualized computational and storage resources utilizing an Artificial Intelligence (AI) model. The clustering is performed by utilizing two prediction models: a mobility prediction model and a theoretical framework. The mobility prediction model learns timing and direction of movements such as mobility patterns of each of the plurality of moving nodes, as to ascertain computational capacity for the given locale at a certain time. The theoretical framework performs sequential to parallel conversion in learning, optimization and caching algorithms of the AI model under contingent circumstances. Upon clustering, the cluster of moving nodes is utilized to process a plurality of workloads co-operatively for the set of end-devices in the given locale.

The invention discloses a dynamic multipath routing algorithm based on mobility prediction, being applied to a high-speed mobile wireless Mesh network. The algorithm comprises the following steps: firstly predicting the route lifetime by utilizing the mobile information of nodes and introducing the ideal of route lifetime into the route discovery process of the DSR protocol; routing multiple paths from the source node to the destination node by utilizing the comprehensive evaluation value generated by non-relevance between the route lifetime and multipath routes and improving the route maintenance, selection and cache mechanism by utilizing the route lifetime. The invention can search for relatively stable routes for the nodes in the high-speed mobile wireless Mesh network, and the searched multiple paths have higher non-relevance, thus reducing the frequency of route discovery, effectively lowering the routing overhead, improving the performances of the original DSR protocols and ensuring the algorithm to be adaptive to the high-speed mobile network environment.

The invention provides a mobility prediction method based on fuzzy clustering in outdoor crowded places, and belongs to the field of mobile communication technology. The scene is divided into several prediction regions, and the prediction time is divided into several time periods, user moving trajectories are divided into different groups within each prediction region according to the prediction time, irregular trajectories are removed in a sequence mode, a sequence in a frequency mobility mode is found, the position of the next position is predicted by matching the user moving trajectories with a historical user moving trajectory, and thus the prediction accuracy is improved. By adoption of the mobility prediction method, the continuous communication service of the users in the outdoor crowded places is guaranteed, the unnecessary switching times are effectively reduced, and the user residence time is prolonged. According to the mobility prediction method, the user moving trajectories in the outdoor crowded places are analyzed and modeled to help to analyze and solve other related user behavior problems in the outdoor crowded places.

Predicting mobile station migration between geographical locations of a wireless network can be achieved using a migration probability database. The database can be generated based on statistical information relating to the wireless network, such as historical migration patterns and associated mobility information (e.g., velocities, bin location, etc.). The migration probability database consolidates the statistical information into mobility prediction functions for estimating migration probabilities/trajectories based on dynamically reported mobility parameters. By example, mobility prediction functions can compute a likelihood that a mobile station will migrate between geographic regions based on a velocity of the mobile station. Accurate mobility prediction may improve resource provisioning efficiency during admission control and path selection, and can also be used to dynamically adjust handover margins.

The invention provides a mobility-prediction-based wireless fidelity (WiFi) speed self-adapting selecting method, which belongs to the communication field. Firstly a vehicle WiFi device continuously detects the strength of access point (AP) signals nearby, the strength value of the detected AP signal is converted to a corresponding distance value, and the movement trend of the vehicle WiFi deviceis predicted according to a plurality of distance values; and a data speed of the WiFi device is selected according to the movement trend of the vehicle WiFi device and a distance-data speed table which is obtained through the experiment. By the method provided by the invention, the shaking of the data speed of the WiFi device during the moving process of a vehicle can be reduced, and the data transmission efficiency can be improved.

The invention discloses a mobility prediction-based crowd sensing user recruitment method and system. The method comprises the steps of sending a mobile crowd sensing task, wherein the mobile crowd sensing task comprises a budget, a target location, task starting time and task termination time; obtaining personal expectation values of multiple mobile users, wherein the personal expected values represent the probabilities of reaching the target location on time by the mobile users; according to the personal expectation values and a data uploading mode, determining success probabilities, whereinthe success probabilities represent the probabilities of successfully finishing the mobile crowd sensing task by the mobile users; determining maximum values of the success probabilities; and determining the mobile users corresponding to the maximum values of the success probabilities as recruitment objects. According to the technical scheme, the applicability of a mobile crowd sensing application and a user recruitment module are improved.

The invention provides a mobility prediction-based load balance optimization method applied to a heterogeneous network and belongs to the communication technical field. According to the method of thepresent invention, the influence of the previous state of a user on future position prediction is researched and compared; optimal decision tree input attribute features are selected, so that a decision tree model can be established to predict the position of the user at the next moment; a time series analysis method is adopted to predict the load status of a base station when the user arrives; and a resource allocation strategy is formulated in advance to optimize the load balance of a network. With the method of the invention adopted, the accuracy of mobility prediction can be improved; thepossible impact of each potential user in adjacent areas on the base station does not need to be monitored; and therefore, the burden of the network is reduced, the network performance of hot spot areas can be improved, and user service experience can be improved.

The invention relates to an article deliverer recommending method based on user mobility prediction. The method comprises the following steps: 1) data acquisition and arrangement: extracting effective sites from original GPS data of a mobile user and carrying out cluster on the sites to obtain user-interested sites and meanwhile, generating corresponding tracks; 2) candidate selection: extracting a candidate set of candidates according to relationship degree among users in a social network; 3) user meeting prediction: calculating meeting probability between the user and friends thereof through probability statistics of user historical tracks; 4) user position prediction: calculating the probability that the friends of the user visit some place through the probability statistics of the user historical tracks; and 5) deliverer recommendation: calculating the probability that the friends of the user visit some place before the user meets the friends, ranking the probability in a descending order, and selecting and displaying the top K friends. The method provides convenience for user shopping.

The invention provides a resource allocation optimization method based on mobility prediction in a heterogeneous network, and belongs to the technical field of communication. The method comprises thefollowing steps of clustering the historical moving track of a user; using the clustering result as the main position of the user; obtaining the demanding condition of the user on the network resourcein each main position; modeling the historical moving track of the user into a two-order HMM model; dividing the whole prediction region into the corresponding moving state according to the main position; using the main position as a hidden state value; using the time as the explicit state; using the two-order HMM prediction model to predict the next position of the user; according to the prediction position, arranging a target base station for performing allocation on the user equipment according to requirements by combining the network resource requirements of the user in the position. In the heterogeneous communication network, a mobile prediction technology is used for optimizing the resource allocation process, the continuous communication service of the user is ensured; the serviceexperience of the user is well improved; the network resource utilization rate is improved.

The invention discloses an underwater wireless sensor network positioning algorithm based on mobility prediction. The algorithm introduces an improved backtracking search optimization algorithm on thebasis of a conventional mobility prediction positioning method. The algorithm adopts three sensor nodes, namely a buoy node, an anchor node and an unknown node. The algorithm comprises the followingsteps of: (1) initializing a wireless sensor network; (2) positioning anchor nodes; (3) calculating anchor node speed information; (4) calculating unknown node speed information; and (5) positioning unknown nodes. The algorithm can adapt to the underwater wireless sensor network in practical application. The node positioning precision is effectively improved, and the calculation overhead is reduced.

The invention provides a deep learning-based mobility prediction method of network nodes in a vehicle-mounted Ad Hoc network. The method effectively utilizes traffic regulations to realize mobility prediction of multiple future time points of the vehicle nodes on mobility constraints of the nodes, history travel data of the vehicle nodes and personalized information of vehicles and drivers. The method includes: combining different types of vehicle motion models to establish a vehicle history travel data sample library and a traffic regulation constraint database, and simultaneously agreeing onsample travel data features; then utilizing a recurrent neural network to extract vehicle sample mobility deep-layer features, and establishing a mobility prediction model; then using a gradient-descent back-propagation algorithm for training of model parameters; and finally, utilizing real-time data information of current movement of vehicles to predict mobility. The invention relates to vehiclemovement model data analysis and neural-network model construction and parameter training realization methods. The prediction method utilizes non-linear prediction capability of deep learning, maps the vehicle running data features to vehicle movement, and realizes mobility prediction of the nodes in the vehicle-mounted Ad Hoc network.

The invention provides a bank mobility prediction method and a bank mobility prediction device. The method comprises the steps of acquiring the historical business data and the historical mobility data of a bank application service system; training a pre-established machine learning model according to the historical business data and the historical mobility data; and utilizing the trained machinelearning model to carry out bank mobility prediction. The bank liquidity is predicted by extracting the characteristic values of the bank liquidity business data and performing machine learning training. The bank is supported to fully utilize the residual liquidity, and the predicted bank liquidity is utilized to provide liquidity risk early warning in time.

A system, a method and a computer program product are provided to determine mobility pattern of one or more users for buildings, using machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain mobility features associated with the buildings in a geographic region, entry-exit data of the one or more users for the buildings in the geographic region The processor may be configured to determine, using trained machine learning model, one or more transport modes for the one or more buildings, based on the mobility features. The processor may be configured to determine, using a trained machine learning model, the mobility pattern of the one or more users based on the entry-exit data of the one or more users and the one or more transport modes for the buildings.

The invention discloses a cast steel liquidity predicting method. The method includes following steps: (1), using cast steel different in trademark for spiral sample experiments, and collecting neutral network training sample data; (2), building a neutral network model for cast steel liquidity predicting, and determining network topology structure of the neutral network model, wherein the type of a neutral network is a multilayer feedforward BP network; (3), extracting part of the sample data from the step (1), and training the neutral network model; (4), using remaining samples in the step (1) to perform simulation testing on the network model after being trained; (5), predicting liquidity of the cast steel of other trademarks through the neutral network model after being trained. Through the neutral network model, the predicting method is provided for cast steel liquidity during cast steel part casting process designing and is conducive to promoting digital, intelligent and energy-saving development of the casting industry.

This invention proposes a method for part mobility prediction based on a static snapshot. This part mobility prediction method consists of several steps: constructing mobility units from each 3D model in a set of 3D models with parts segmented according to their motion and grouping all of the mobility units according to their motion type; computing snapshot descriptors for every static snapshot in a mobility unit; learning a snapshot-to-unit distance measure for every motion types of the mobility units; getting the most similar mobility unit and its motion type for a query snapshot by using the snapshot-to-unit distance measure to select with the minimum distance value; generating multiple motion candidates for a query static snapshot according to the achieved mobility unit and its motion type, sampling the generated motion and getting the best motion parameter for the query snapshot. This invention can predict the part mobility from a static snapshot of an object.

The invention provides a gas reservoir water layer water body mobility prediction device and method and a controller, and the device comprises a rock core holder which is provided with a first space and a second space; the first space is used for placing a to-be-predicted rock sample; the second space surrounds the first space; a confining pressure pump is used for applying confining pressure to the rock sample to be predicted by injecting pressure into the second space; a high-pressure injection pump is used for injecting the simulated formation water in the intermediate container into the rock core holder; a back pressure pump is used for injecting pressure into the rock core holder; a controller is used for controlling the high-pressure injection pump and the back-pressure pump to pressurize the two ends of the rock core holder after the confining pressure reaches a preset confining pressure value; and when the pressure at the two ends reaches the stratum pressure set value and doesnot change, the high-pressure injection pump is controlled to be closed, the back pressure pump is controlled to reduce the pressure, and the water mobility is predicted according to the water yieldunder each pressure drop value. According to the scheme, quantitative prediction of the mobility of the water body of the water layer in the gas reservoir development process is achieved, and important guiding significance is achieved for gas reservoir development.

The invention provides a prediction model adjusting method and device, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring transaction data of a transaction object in a preset time period, and preprocessing the transaction data to obtain transaction feature data; based on the transaction feature data and a market mobility prediction model, obtaining a mobility prediction value of the transaction object, wherein the mobility prediction value is equal to the sum of the products of the prediction results of the sub-models and the corresponding weights; obtaining an actual liquidity value of the transaction object based on the liquidity parameter corresponding to the transaction object in the preset time period; and adjusting the weight corresponding to each sub-model according to the actual mobility value of the transaction object and the prediction result of each sub-model. The device is used for executing the method. According to the prediction model adjusting method and device provided by the embodiment of the invention, the accuracy of model prediction is improved.