199 results about "Transfer probability" patented technology

The invention discloses a pure electric automobile remaining mileage model predication method based on path information. The pure electric automobile remaining mileage model predication method based on path information comprises the following steps of analyzing driver history running data, extracting the path information and generating a state transferring probability matrix satisfying driver behavior characteristics; generating a predicated automobile speed on the basis of road information of a future path and the corresponding state transferring probability matrix; establishing a parameter estimation model to estimate running parameters affecting energy consumption and remaining mileage of an automobile; and establishing an RDR calculation model to predicate a vehicle remaining mileage,wherein an energy consumption predication model is used for calculating a vehicle energy consumption rate by using the predicated automobile speed obtained by an automobile speed predication model andthe running parameters estimated by the parameter estimation model as model input; a remaining energy predication model is used for estimating vehicle battery remaining energy; by integrating the vehicle energy consumption rate and the battery remaining energy, the vehicle remaining mileage can be predicated and can be displayed by using a remaining mileage display model.

The invention discloses an electric vehicle travel planning method based on multi-target optimization, generally comprising the following steps: (1) a travel planning problem model is established; (2) drivers provide travel information; and (3) an optimal scheme is solved based on a timed multi-target ant colony optimization algorithm. The problem model comprises a road network model, a vehicle model, and travel target and travel constraint definition. Travel information includes: not providing any information, providing constraint information, and providing optimization goal and constraint information. The ant colony optimization algorithm includes the steps of pheromone initialization, route transfer probability calculation, travel scheme search, air conditioner use determining, travel scheme ranking, pheromone updating, and loop optimization. A dynamic stochastic road network model is used to describe the traffic environment and plan the travel of electric vehicles, and target characteristics corresponding to different travel schemes can be reflected. The ant colony optimization algorithm ensures that a multi-target and multi-constraint optimized electric vehicle travel scheme is generated as the number of iterations increases.

The invention discloses a parking system path planning method based on an improved ant colony algorithm, and aims at solving the problem of AGV vehicle access path planning in an intelligent parking garage so that vehicle accessing can be completed in the shortest possible time, utilization rate of parking places can be enhanced, time of waiting for vehicle accessing can be reduced for social members and automatic management of parking equipment can be realized. The concrete planning steps are that an AGV working environment model in the intelligent parking garage is created by adopting a grid method; the conventional ant colony algorithm is optimized and improved by introducing of new node state transfer probability and an updating strategy of combination of local and global pheromones; and simulated testing is performed on the AGV vehicle access path planning process by applying the improved ant colony algorithm and the result is outputted. The method has high global search capability and great convergence performance, and can effectively enhance path search efficiency, shorten search path length and reduce the number of path turnings and can also enable the AGV to effectively avoid obstacles in the complex operation environment so as to search the optimal collision-free path.

The embodiment of the invention discloses a floating car track map matching method and a floating car track map matching device, and relates to the field of an intelligent traffic system. The matching error of the floating car track on a map can be reduced, and the matching accuracy can be improved. The method comprises the following steps that firstly, at least one road respectively corresponding to each track point in a track point sequence is obtained, then, the road matching probability between the track points and each road is calculated according to the distance from the track point to each road in the at least one road, next, the road transfer probability from each road corresponding to the track point to each road corresponding to a next track point is calculated, in addition, a plurality of floating car tracks corresponding to the track point sequence are traversed according to the at least one road respectively corresponding to each track point, and finally, the route tracks of a floating car matched on the map are obtained from the floating car tracks according to the road matching probability and the road transfer probability.

The invention relates to the technical field of mode recognizing, in particular to a real-time human body action recognizing method and device based on depth image sequence. The method comprises the steps of S1, extracting target action sketch from a target depth image sequence and extracting a training action sketch from a training depth image set; S2, performing gesture clustering on the training action sketch and performing action calibrating on the clustered outcome; S3, computing the gesture characteristics of the target action sketch and training action sketch; S4, performing the gesture training based on a Gauss mixing model by combining the gesture characteristics of the training action sketch and constructing a gesture model; S5, computing the transferring probability among all gestures of the clustered outcome in each action and constructing an action image model; and S6, performing action recognizing on the target depth image sequence according to the gesture characteristics of the target action sketch, the gesture model and the action image model. The real-time human body action recognizing method disclosed by the invention has the advantages of improving the efficiency of action recognizing and the accuracy and the robustness of the action recognizing.

The present invention relates to a random energy management method of double energy source mixed power automobile, belonging to the field of dynamic energy distribution method of mixed power automobile. Said method includes the following steps: firstly, inducing statistic law of actual power from lots of vehicle road running records, obtaining condition transfer probability matrix of power required by driver and obtaining single-step cost of conversion between arbitrary conditions, and creating Markov random model of power required by driver, then utilizing said Markov random model to make calculation and obtain optimum control quantity of energy output.

The invention discloses a map matching method and a map matching system, and relates to the field of navigation. The method comprises the following steps: determining a candidate point according to a tracing point of a driving vehicle, wherein the candidate point is a projection point of the tracing point on a road within a preset range; determining the direction of the road of the position of the candidate point; calculating the direction probability of the candidate point according to the direction of the road of the position of the candidate point; calculating the comprehensive matching probability of the candidate point according to the direction probability of the candidate point, the measuring probability of the candidate point and the transfer probability of the candidate point; and comparing the comprehensive matching probabilities of all the candidate points and determining the trace position point of the vehicle on the actual road. According to the method for performing map matching through the driving direction of the vehicle, the attribute of the existing road network data can be not changed, and the direction of the road position of the candidate point is acquired under the condition of not performing road network data preparation in advance, so that the direction probability is calculated and the accurate rate of map matching is increased.

The invention provides a multi-unmanned aerial vehicle (UAV) track planning method based on a culture ant colony search mechanism, which includes the following steps: (1) carrying out mesh generationon a standard space according to a grid method; (2) building a multi-UAV track planning model, including the number of UAVs, the start and end points and a threat model; (3) initializing the start point and the end point; (4) initializing an ant colony algorithm, including: initializing an ant colony and calculating a heuristic factor and a guide factor; and (5) assigning all ants to an initial node, and updating taboo knowledge; selecting next node for transfer according to the taboo knowledge and the state transfer probability until there is no optional node or a destination node is selected, updating historical knowledge, and updating pheromones according to the historical knowledge; and outputting a shortest path if the maximum number of iterations is achieved, and continuing the process until U multi-UAV optimal multi-path tracks are obtained. The problem that it is difficult to find the optimal flight tracks of unmanned aerial vehicles due to slow search and heavy computing burden is solved, and multi-UAV track planning is realized.

The invention relates to a method and device for identifying user's intention in voice interaction. The method comprises the steps of receiving current voice data information input from a user, identifying the voice data information to acquire a text data information corresponding to the voice data information, acquire a user intention classification model and target transfer probability matrix based on a user's log record, identifying the target intention category of the text data information based on the user intention classification model and the target transfer probability matrix, finding response information corresponding to the text data information in a database corresponding to the target intention category. Through the technical scheme, correct response information can be provided to the user, and the searching time can be shortened to enhance the searching efficiency and user's experience.

Disclosed is a network control system controller design method based on a hidden semi-markov model. The method uses the hidden semi-markov model to describe a network load state and then carries out modeling on a network control system in which time delay and packet loss exist and according to a robust control theory, a semi-markov jump linear system theory and a Lyapunov theory, the method uses interval expression of a state self-transfer probability to offer sufficient conditions for existence of an easily solvable state feedback robustness H <infinity> controller of the network control system and offer a design method for a control law so that multimode switching control of the network control system is realized.

The invention provides a method for modeling a wind power output time sequence. The method can be used for researches on the planning of a power system, the reliability evaluation of the power system, the medium / long-term scheduling of the wind power, and the like. The method is based on a historical wind power output time sequence, and comprises the following steps of: first analyzing the characteristics of the historical wind power output time sequence to obtain indexes of fluctuation characteristics and the like of wind power output of a wind power plant in a specified place; then filtering the historical wind power output time sequence, and performing wind process and fragment division, and counting a wind process transfer probability and the probability distribution of each fragment; and finally simulating and reconstructing the wind power output time sequence by adopting a sequential sampling method, and inspecting and verifying the reconstructed time sequence. The output time sequence of the wind power plant is accurately evaluated, wind power output characteristics are maximally simulated, and the method can be used for evaluating the reliability of wind power capacity, accurately determining the position of wind power in a power system and guiding the scheduling running of the power system.

The invention discloses a network service intelligent deployment method and a system, which relates to the field of network function virtualization. The method comprises the following steps: describing virtual resources in a tensor-based formal description mode of virtual resources; based on artificial intelligence technology and historical sample data, calculating the transfer probability of eachvirtual resource, generating a transfer tensor model, and predicting the change trend of the virtual resource utilization rate according to the transfer tensor model; according to the change trend prediction result, allocating the most suitable virtual resources to the virtual network function to ensure the normal operation of the virtual network function. The invention intelligently realizes thedeployment and resource allocation of the virtual network function in the telecommunication cloud platform.

The invention discloses a pseudo-measurement-based asynchronous track fusion algorithm with a feedback maneuvering target. Firstly, input interaction is carried out on a model set, and the filtering initial value of each model is calculated according to the model probability and the model transfer probability; secondly, a fusion center calculates one-step prediction values on the basis of the Kalman filtering algorithm, after new sensor measurement information in the filtering period is obtained, the one-step prediction values are distributed in a time shaft sequence, recurrence is conducted on a fusion moment, information such as sensor observation matrixes, noise and model prediction are added, and asynchronous track fusion is conducted; thirdly, secondary filtering is carried out for calculating model output, output interaction is performed in the fusion center to obtain a fusion center estimated value and an estimation error matrix, and the fusion center estimated value and the estimation error matrix are fed back to a sensor according with feedback conditions. The overall precision of the algorithm is improved by introducing a fusion structure with feedback so that a better effect can be achieved in multi-sensor maneuvering target tracking.

The invention belongs to the technical field of a multiple-input-multiple-output system and discloses a MassiveMIMO channel modeling method based on measured data. According to the method, a confocal elliptical model is established, and base station and dipole parameters are set; a birth and death rate of a scattering cluster is acquired according to the measured data to acquire a nine-state Markov chain state transfer probability matrix, an evolution process of the scattering cluster on an antenna array axis is described through utilizing a Markov chain, and characteristic parameters of each scattering cluster are distributed; and lastly, according to the geometric position relationships among the parameters, phase and Doppler frequency under the stadia and non-stadia conditions can be calculated, and channel impulse response is generated. The method is advantaged in that the birth and death process of the scattering cluster on the antenna array can be accurately described, non-stationary characteristics of a MassiveMIMO channel is reflected, spherical wave characteristics can be described, moreover, computational complexity is relatively low, the channel impulse response can be generated in relatively short time, and channel simulation efficiency is improved.

The invention discloses a decision tree behavior decision algorithm based on demonstration learning, and mainly solves the problems in the prior art that the present decision algorithm cannot simultaneously consider the integrated and complex scenes and the requirement of stability. The decision tree behavior decision algorithm based on demonstration learning comprises the steps that the state transfer law of demonstration trajectories is stored; a state transfer frequency matrix and a state transfer probability matrix are obtained; the reward is constructed; the decision tree assesses the motion to be generated; the transfer frequency matrix and the state transfer probability matrix are updated; and the process is repeated until assessment is passed. With application of the scheme, the objectives of the maximum rationality and safety of the driverless behavior decision can be achieved.

The invention discloses a method for predicting a time sequence of number of people served by base stations based on space-time transfer probabilities of mobile phones. The method comprises the following steps: calculating the total number of people within base station service areas of the mobile phones within an equal time period by using space-time orbit data of the mobile phones; dividing people moving orbits by using the space-time orbit data of the mobile phones, and calculating the number of people coming back and forth between the base stations within adjacent time periods in a research area; based on related theory of Bayesian and Markov chains, calculating the transfer probabilities of mobile phone users within target base stations to occur in the base stations at a current moment according to historical data; calculating the transfer probabilities of the mobile phone users within the target base stations to occur in the base stations within different time periods to construct a complete space-time transfer probability matrix in the research area; and predicting the number of people served within the base station ranges of the mobile phones in the research area with the relatively stable total number of people by using the complete space-time transfer probability matrix. The method disclosed by the invention has the advantages of low data acquisition cost, simple model structure and high prediction efficiency.

The invention provides an MRI image-based axillary lymph gland metastasis prediction system and relates to the technical field of computer aided diagnosis. The system comprises an input module, an area-of-interest extraction module, a lump segmentation module, a sub-visualization module, a feature extraction module, a feature dimensionality reduction module, a classification and diagnosis module,and an output module. The input module receives a to-be-diagnosed mammary gland DCE-MR image sequence input by a user. The area-of-interest extraction module extracts an area of interest from the mammary gland DCE-MR image sequence. The lump segmentation module segments a lump in the area of interest. The sub-visualization module carries out the visual display on each segmented image and extractsthe edge of a focus. The feature extraction module extracts relevant feature values according to the lump information and transmits the relevant feature values to the feature dimensionality reductionmodule. The feature dimensionality reduction module carries out feature dimensionality reduction on an extracted feature set. The classification and diagnosis module inputs each lump feature value into a classifier. After that, the automatic classification and recognition is carried out by a computer for judging whether a lymph gland has already been transferred or not. The output module displaysa transfer prediction result and a transfer probability. According to the invention, the accurate segmentation of breast lesions can be realized. The accurate diagnosis of mammary axillary lymph glandmetastasis can be effectively assisted.

The invention belongs to the technical field of network security, and particularly relates to a network security domain knowledge graph construction method and device for dynamic threat analysis, andthe method comprises the steps: describing a threat transfer relation caused by a system vulnerability and a network service; constructing a network dynamic threat analysis knowledge graph model by utilizing graph theory knowledge; calculating a threat transfer probability by combining a general vulnerability evaluation standard and Bayesian; and generating a network threat knowledge map by utilizing association rules among threats, vulnerabilities and services, and carrying out loop resolution. According to the invention, network attacks, system vulnerabilities and business applications influence each other; the network threat transfer probability is analyzed in combination with the general vulnerability scoring standard and the Bayesian formula, the constructed knowledge graph is corrected, the threat transfer loop among multiple nodes is eliminated, the attack full view can be completely displayed, the network evidence obtaining efficiency is improved, and a basis is provided for threat clue discovery and traceability evidence obtaining.

This invention relates to communication field and discloses one method, router device, business network to establish business connection, which comprises the following steps: determining this point to neighbor point transfer probability according to the linkage biological information concentration of each points and selecting router with maximum probability as this operation to next point router with its neighbor points as this point neighbor points.

The invention provides a non-overlapping vision field multi-camera monitoring network topology self-adaptation learning method, and relates to the field of computer vision. A weighted directed graph G=<V, E and W> is used, and the topology of a monitoring network is represented. According to the non-overlapping vision field multi-camera monitoring network topology self-adaptation learning method, the leaving position and the entering position of a target in a single-camera vision field are used as topological nodes V, and a Gaussian mixture model is utilized for modeling. The cross-correlation function computing method based on united surface similarity is provided, the connectivity of a certain pair of nodes is judged through a cross-correlation function, and therefore an edge set E is obtained. As for the connected node pair, transfer time distribution is calculated through the standardization cross-correlation function. Mutual information of the node pair is utilized for representing the transfer probability of the nodes, and therefore the weight set W is obtained. According to the non-overlapping vision field multi-camera monitoring network topology self-adaptation learning method, the false connection removal strategy is provided for removing probable false connection in the topology, the topology self-adaptation updating strategy is provided for ensuring the higher robustness of the topological structure to environmental changes.

The methods for determining the probability of detection of a thermally camouflaged target at various ranges by the sensor includes determining an “inherent” temperature difference, ΔTRSS, between the target and its immediate surroundings. Once ΔTRSS is determined, a scaled N50 cycle criterion, or the number of resolvable cycles needed by the sensor for a fifty percent probability of detection, is determined according to the relationship N50=A / (ΔTRSS)B+C, where A, B and C are constants that are predetermined according to whether the immediate surroundings are of a woodland or a littoral nature. The scaled N50 cycle criterion is then used in an empirical Target Transfer Probability Function (TTPF) defined by P=(N / N50)E / (1+(N / N50)E), where E=2.7+0.7(N / N50), in order to determine the probability of detection of the thermally camouflaged target.

The invention discloses a social network based mobile terminal user grouping method. The method comprises: according to history of communication between terminal users, quantizing communication contact to generate a social relational graph (STG); in combination with preference attributes of the terminal users, generating an attribute relational graph (ARG) taking preference degrees between the terminal users and attributes as weights; generating a social relation-attribute graph in combination with the STG and the ARG, designing an SAPLA algorithm to predict unknown attributes of the terminal users, and adjusting preference degrees of known attributes; and proposing an SARA algorithm by utilizing a random walk model, combining transfer probabilities between the terminal users and between the terminal users and the attributes, giving out a transfer probability matrix between the terminal users, with relatively low complexity, giving out a random walk distance matrix Rl by utilizing the transfer probability matrix, setting a target function in combination with the matrix Rl, and grouping the terminal users until the target function is converged. According to the method, the complexity of operation is lowered and the accuracy of grouping is improved.

The invention relates to a user behavior prediction method, which belongs to the field of computer technologies and solves a problem that the prediction result is inaccurate in the prior art. The userbehavior prediction method comprises the steps of constructing a t-moment behavior transfer probability matrix of a target user according to behavior data of a target user before the moment t; iteratively training a behavior prediction model of the target user based on the t-moment behavior transfer probability matrix and preset behavior influence factors; and predicting a next behavior of the target user based on the t-moment behavior transfer probability matrix, the preset behavior influence factors and a behavior prediction result of the target user at the previous moment according to thebehavior prediction model. According to the user behavior prediction method disclosed by the embodiment of the invention, behavior prediction is performed through combining related factors of user behaviors and a behavior transformation relation of the user, the behavior granularity of the user is refined, the user behaviors are comprehensively considered, model training is performed by combiningthe behavior transformation probability, and the prediction accuracy of the model is effectively improved.

The invention provides a tour route recommendation method combined with short term traffic flow forecasting. The method includes the steps that historical picture description information is downloaded from a picture sharing website, pictures are clustered through the DBScan clustering algorithm to obtain interest points large in picture density, historical tour routes of the historical picture description information are extracted, time sequence modes, at different time intervals, of the interest points are built according to the historical picture description information, a probability transfer matrix of a Markov model is generated according to the historical tour routes in a historical tour route set in a region, the probability transfer matrix of the Markov model is updated according to pictures and the picture description information uploaded by a user in real time, and the interest point maximum in transfer probability is recommended to the user according to the updated probability transfer matrix of the Markov model. The method is combined with short term traffic flow of the interest points for route recommendation, and has the function of dispersing passenger flow in scenic spots.

The invention relates to the field of intelligent transportation, in particular to a destination prediction method and device. The method comprises the following steps: presetting a destination prediction model, wherein the destination prediction model records the target transfer probability between every two historical location points in each historical running track of a vehicle in each set timeperiod; monitoring the current running track of the vehicle to determine a time period corresponding to the current running track; and based on the time period corresponding to the current running track, using the preset destination prediction model to calculate the prediction probability between the current running track and each historical location point in each historical running track, and determining a corresponding historical location point of which the prediction probability satisfies preset conditions as a predicted destination. The time factor is taken into consideration both in theestablishment of the destination prediction model and in the destination prediction. Therefore, the accuracy of destination prediction is improved, and the driving experience of users is enhanced.

The invention discloses a resume analysis method based on an n-gram model. The method comprises the steps that resume samples are collected in advance; commonly used field keywords are classified into different types, and a classification dictionary is formed; the n-gram model is used to conduct statistics of a transfer probability of converting each commonly used field keyword into each sample related word; a target keyword matched with the commonly used field keyword in a to-be-analyzed resume is searched; if the transfer probability corresponding to the target keyword is larger than a preset threshold, the transfer probability corresponding to each commonly used field keyword can be updated according to the target keyword; prefix labels and postfix labels are added to effective keywords in the to-be-analyzed resume; and text contents of the to-be-analyzed resume are extracted by segmentation and then output. According to the invention, the automatic resume analysis can be conducted based on the n-gram model and dictionary segmentation technologies; information extraction accuracy can be increased, and different document formats can be supported; and an abundant talent resource base can be provided for recruitment websites and company HR departments.

The invention belongs to the crossing field of computer science and traffic engineering, and relates to an indoor pedestrian microscopic simulation method based on a cellular automaton. The method comprises following steps of firstly, carrying out gridding on an indoor pedestrian region, thus obtaining a cellular space corresponding to a cellular automaton model; dividing the cellular space into some convex polygon regions; secondly, judging whether there are pedestrians in each region; stating the temporary destination of each pedestrian; calculating the transfer probability of each pedestrian; simulating movements; observing whether conflicts appear or not; finally, solving the conflicts; and updating the practical position of each pedestrian until the pedestrians arrive at the corresponding destinations. According to the method, the simulation model can correspondingly respond to complex walk environments and not merely distinguish the pedestrians and barriers; moreover, the self-organization phenomena displayed in the regional pedestrian flow indoor evacuation process are simulated; the model simulation effect is effectively improved; and the method is more suitable for simulating and analyzing movement evolution of the pedestrian flow in the indoor complex environments.

The invention puts forward a community discovery method used for a complex network. An algorithm designs a node transition probability through the analysis of a network topology structure, the significance of the node for the network community is evaluated on the basis of a random walk method, then, the node with the high significance is taken as a core to construct the network community, and finally, a community structure is regulated through a community edge trimming method. Compared with an existing method based on random walk, CDATP (Community Detection Algorithm Based on Asymmetric Transfer Probability of Nodes) exhibits the node design transition probability in the network, and the degree of importance of the node for the community is evaluated through the local transition of the node.