48 results about "History of computing" patented technology

The invention relates to a modeling method for a parallel smart case recommendation model. The method comprises the following steps of obtaining existing patient cases from an electronic case database, carrying out denoising, clustering and word segmentation on the patient cases, and establishing a patient case corpus database; defining that TFIDFi, j shows the importance degree of a word or an expression in a case of the patient case corpus database, establishing an LSI vector space model according to the TFIDFi, j, and moreover, establishing a BOW word bag model according to all words and expressions in the patient case corpus database; calculating history case vectors and to-be-processed case vectors in the patient case corpus database through utilization of the LSI vector space model and the BOW word bag model; calculating cosine similarity among the history patient cases and storing the cosine similarity; and calculating the cosine similarity between the to-be-processed case vectors and the history patient case vectors, and searching similar cases of to-be-processed cases according to the cosine similarity. The model established through adoption of the method provided by the invention is high in accuracy and low in error. A recommendation result is high in quality.

A method of valuing real estate properties includes the steps of calculating a premium or discount to rental parity for a historically stable time period and the current time period. Another method of timing a real estate market is also disclosed. Another method of searching for relevant property based on the personal income and / or expense of the buyer is also disclosed.

The invention discloses an environment monitoring platform based on mobile internet and a monitoring method. The environment monitoring platform and the monitoring method improve accuracy, reliability and instantaneity of environment monitoring by fully taking advantages of the mobile internet technology and have the advantages of 1) utilizing the latest mobile internet technology, connecting a lower computer with a server and connecting the server with a monitoring terminal through mobile internet, simplifying deployment topology, saving cost, simultaneously being convenient for user monitoring, supporting any smart phones installed with browsers, and solving the problem that instructions cannot be issued when the internet protocol (IP) address of the lower computer is flexible; 2) combining monitoring modes of real-time remote inquiry, server routing inspection, lower computer routing inspection and real-time report in complementary mode, ensuring instantaneity and stability of the monitoring and avoiding the phenomenon of monitoring failure caused by one mode; 3) concluding attributes of a group of monitoring objects, being capable of fast introducing a new monitoring object through the attribute definition, building a data structure through the monitoring objects, being capable of obtaining comparison results of unstable data and historical data in real time without recomputing the historical data during the comparison, and ensuring instantaneity of the response; 4) adopting the server pushing technology between the server and a user terminal, keeping long-time connection between the server and the client side, enabling the client side to display the latest monitoring data once the monitoring data are updated, and having instantaneity compared with the conventional monitoring system monitoring through a real-time polling data base; and 5) enabling the platform to be capable of adopting an Saas mode, having generality and supporting environment monitoring of different industries.

The invention discloses a whole-network load prediction method based on local load predicted value comprehensive evaluation. The whole-network load prediction method is characterized in that historical data in a recent sample period are obtained and used as a historical data sample space, then the average proportionality coefficient of each region at a time point t in the historical data sample space is calculated, the proportionality coefficient of each region at the same time point t on a to-be-predicted day is predicted, a multi-index evaluation system of the time point t is built, a comprehensive evaluation index of the time point t is built according to the multi-index evaluation system, q regions with higher priorities at the time point t are selected by means of the comprehensive evaluation index, the selected q regions are used for predicting whole-network system loads at the time point t respectively, the optimal comprehensive models of q different predicted values at the time point t are built, final predicted results of the whole-network system loads are obtained by conducting solving, the optimal comprehensive models are built for whole-day T time points of the to-be-predicted day respectively, and a whole-day load prediction sequence is obtained. The whole-network load prediction method can improve the accuracy of short-term load prediction of a power system.

The invention discloses an information recommendation method and device, relates to the fields of computer technology and artificial intelligence and improves the accuracy for recommending information to users. The method includes calculating the user similarity of optional two historical user identifiers in historical user identifiers according to network service evaluation records fed back by historical users; acquiring a target user identifier; determining a historical user identifier group has high similarity with the target user identifier according to the target user identifier and the calculated user similarity; determining target information in the network service evaluation records corresponding to the historical user identifier group according to the historical user identifier group, and recommending the target information to a target user corresponding to the target user identifier. The method is adaptive to information recommendation.

The invention is applicable to the technical field of computers, and provides an article recommendation method and a device. The method comprises the following steps of according to the similarity between a scored article and a to-be-scored article in historical scoring data, calculating the influence factor of the historical scoring data on the predicted score of the to-be-scored article; inputting the calculated influence factor into a pre-established restricted boltzmann machine model; calculating the predicted score of a user on each to-be-recommended article through the restricted boltzmann machine model; generating a recommendation list; and outputting recommended articles to the user according to the generated recommendation list. In this way, the cold start problem during the new article recommending process can be solved. The recommendation accuracy is improved.

The invention provides a trajectory-data-based method and system for recommending a taxi cruising path. The method comprises: (1) network data are initialized and regional grid division is carried out; (2) according to historical trajectory data, a historical traffic charge is calculated; (3) with combination of real-time trajectory data, a traffic charge is calculated and updated; (4) when a taxi arrives at an intersection, a sub regional traffic electric field force applied on the taxi is calculated by using the traffic charge obtained at the step (3) based on an urban traffic Coulomb law, a road network data base is inquired to obtain all road sections of the current intersection, and one road section with the smallest included angle with the traffic electric field force direction is used as a recommended road section; and (5) during the driving process at the recommended road section, if the taxis does not pick up any passenger or the passenger gets off the taxi, the step (4) is carried out; and if the taxi picks up a passenger, recommendation is stopped temporarily. According to the invention, the method has a clear idea and the effect is obvious. The empty driving cruising of the taxi can be reduced and thus the earnings of the taxi driver can be increased; and the urban traffic efficiency can be improved.

The invention relates to artificial intelligence, and provides a data product recommendation method and device, a computer device and a storage medium. The method comprises the steps of receiving a data product recommendation instruction, wherein the data product recommendation instruction carries a target identifier and target customer group information corresponding to the target identifier; establishing a target feature matrix according to the target customer group information; obtaining a historical feature matrix corresponding to each historical target identifier, calculating the similarity between the historical feature matrix and the target feature matrix, and determining a historical target identifier corresponding to the target identifier according to the similarity; and obtainingdata product information corresponding to the historical target identifier, and sending the data product information to a target terminal corresponding to the target identifier. By adopting the method, the data product recommendation efficiency and pertinence can be improved.

The invention discloses an in-service intelligent electric energy meter batch fault early warning method and system. The method comprises the steps of 1, dividing all in-service intelligent electric energy meters into running batches according to batch dividing rules in batches; 2, processing verification inspection data and running data of the intelligent electric energy meters; 3, calculating the historical fault rate and the on-site inspection failure rate according to a statistical period, taking the historical fault rate and the on-site inspection failure rate as batch fault early warningresearch and judgment trigger conditions, if a set threshold is reached or exceeded, entering the step 4, and if the set threshold is not reached, returning to the step 2; 4, outputting a batch faultjudgment result; 5, judging whether the running batches meet a batch fault judgment condition or not, if yes, entering the step 6, and if not, returning to the step 2; and 6, generating an intelligent electric energy meter running batch fault disposal scheme. The method has the advantages that the workload of verification personnel is reduced; the resource waste is avoided, and the investment isreduced; and on the premise that the metering accuracy and reliability of the intelligent electric energy meters are ensured, the resources are ensured to be saved and efficiently utilized.

Embodiments for efficiently computing complex statistics from historical time series data are provided. A hierarchical summarization method includes receiving at least one stream of data and creating data blocks from the at least one stream of data. In another embodiment, a method for computing statistics for historical data includes accessing at least one online stream of historical data, the online stream of historical data including metadata, and creating data blocks from the at least one online stream of historical data. Each data block includes a pair of timestamps indicating a sampling start time and a sampling end time, a number of data samples spanned by the data block, a SUM(X) statistic, a SUM(XX) statistic, and a SUM(XY) statistic computed for the data samples spanned by the data block. Other methods are also presented, such as methods for efficiently and accurately calculating statistical queries regarding historical data for arbitrary time ranges, among others.

Embodiments of the present invention disclose a method and a system for processing historical performance data of a storage device based on a box graph. The method comprises: obtaining historical performance data information generated by a storage device; calculating the quartile of the historical performance data by using a box graph theory, and obtaining an outlier; and taking a calculation result as a data sample for storage. According to the embodiments of the present invention, the quartile of the historical performance data can be calculated by using the box graph theory to obtain the outlier, so that the defect of the lack of analysis on the outlier in the prior art is overcome, the accuracy of the historical performance data analysis is improved, and according to the analysis result, the current status of the storage device can be accurately mastered, and prediction of the future operation status of the storage device can be facilitated.

A system for a vehicle navigation accurately calculates travel times between locations and serves a vehicle driver request for the shortest time route. A navigation server compiles data of common road segments between two locations that are contained in route requests and subsequently calculates travel time between the two locations. When subsequent route requests contain further information pertaining to the same locations, the navigation server updates the travel time. Consequently, the navigation server can calculate the travel times of different routes from the same source vehicle location and destination location. When a vehicle driver requests directions from the vehicle's current location to a destination, the navigation server then provides directions for the shortest time route to the vehicle driver.

The invention discloses a regional meteorological condition similarity-based large power network load prediction method. The method comprises the steps of firstly obtaining load prediction values of regions in a to-be-predicted day and a load and meteorological history data of a sample space recently; aggregating the regions with similar meteorological conditions according to a probability distance-based synchronous back-substitution elimination technology, dividing an aggregated region into q sub-regions with relatively large meteorological condition difference, then calculating an average proportional coefficient of the q sub-regions at a t moment point in a historical data sample space, and predicting proportional coefficients of the sub-regions at the same t moment point in the to-be-predicted day; and predicting a whole network system load at the t moment point by using the q sub-regions, building an optimal comprehensive model at the t moment point for q different prediction values, performing solving to obtain a final prediction result of the whole network system load at the t moment point, and building optimal comprehensive models for T moment points in the whole to-be-predicted day, thereby obtaining a whole day load prediction sequence. According to the method, the short-term load prediction accuracy of a power system can be improved.