144 results about "Preference analysis" patented technology

A database of user preference information is extracted and compiled from multiple websites by web-crawling robots without cooperation or specific participation by users. Users who interact with a website are frequently required to register and create a login or userID name that uniquely identifies them. Thereafter, when an individual rates an item, it is often recorded and published under their userID name such that other users can see how a specific individual rated the item. Although there is no requirement that a specific user register on different websites utilizing the identical userID, it is extremely common that this practice occurs and the use of identical userIDs on multiple sites is used herein to expand preference analysis beyond a single site. Once the database exists, users can request or be passively offered suggestions that result from preference associations across multiple websites as performed by a preference analysis and suggestion function.

The application provides a software recommending method and a system for solving the problems of complex operation steps for downloading a software by a user and consumption of a large amount of time for looking up the required software. The software recommending method comprises the steps of: detecting an installed software and / or a run web application at a client terminal; analyzing the installed software and / or the run web application at the client terminal, and obtaining personalized data of the user at the client terminal, wherein the personalized data includes age data, and / or character data, and / or sex data; and according to the personalized data of the user at the client terminal, providing a corresponding software recommending mechanism. In such a software recommending way special for different personalities of different users, as the software or the web application installed or ran by the user is subjected to user preference analysis, the recommendation is more purposeful, and the recommended software is more useful for the user; in addition, the user does not need to look up the required software in numerous softwares by complex operations.

The invention discloses an adaptive access network selection device and an adaptive access network selection method, which belong to the technical field of communication. Own macro and micro characteristics of a terminal are sensed, a service sensitivity variable is determined according to a user application status and preference analysis, network application priorities and quality of service (QoS) sensitivity priorities are sequenced based on information such as the characteristics of the terminal, application needs, network statuses and the like, adaptive modeling is performed on different networks according to historical data, the QoS characteristics of a user terminal accessing the networks are acquired, an access network is judged according to the guidance information of an intelligent information management module and the actual output of an intelligent network simulation module and inter-network switching is performed. By the device and the method, heterogeneous networks are accessed adaptively optimally and selectively to effectively realize the user transparency orientation of heterogeneous properties of the access network and the terminal universality orientation of application service characteristics.

The invention discloses a preference program recommending device which comprises a user interface module, a tuner module, a preference analysis module and a recommending module, wherein the user interface module is used for receiving channel indication signals corresponding to television channels; the tuner module is used for receiving digital television signals, and the digital television signals comprise program table information and current program information corresponding to the television channels; the preference analysis module is used for analyzing current program keywords of the current program information so as to determine program types corresponding to the current programs, and accumulating preference weight values corresponding to the determined program types in a program type statistical table, wherein the program type statistical table is used for recording the program types and the preference weight values corresponding to the program types; and the recommending module is used for selecting recommended programs from the program table information according to the program types with higher preference weight values in the program type statistical table, and generating a program detailed list according to the recommended programs.

Methods and apparatuses for automatic treatment planning, including recommendation systems, quality assurance, error prevention, text mining, text matching, and treatment planning optimization.

The invention discloses an IPTV (internet protocol television) program recommendation method based on context recognition for multiple users. By means of clustering analysis to program viewing time, the time slots at which the viewing times of users are concentrated relatively are acquired, different users' preferences to programs at different time slots are computed, similarity of the preferences to programs at the different time slots is analyzed, the time slots of the similar programs viewed by users are combined into a new context, and then recommendation is made according to the information of the context. Therefore, to some extent, problems about multiple users in IPTV portal service are solved, and recommendation quality is improved.

The embodiment of the invention discloses a method and a device for data rasterization and a method and a device for user behavior analysis. The method for the data rasterization comprises the following steps of acquiring corresponding user associated data according to user behavior data produced in a target time period and located in a target area; computing a two-dimension number corresponding to the user associated data according to position information in the user associated data; acquiring a corresponding two-dimension index number from a two-dimension index number set by taking the two-dimension number as a query condition; associating a raster mark with the user associated data so as to obtain corresponding raster data. The efficiency of the data rasterization is increased, and user behavior rule or preference analysis based on mass of diversified real-time raster data is realized.

A method of operation of a navigation system includes: identifying a non-default selection for a selected route; determining a contextual parameter corresponding to the non-default selection; and generating with a control circuit a user preference profile based on the contextual parameter of the non-default selection for representing a preference of a system user for navigation information.

The invention relates to an intelligent clothing business system, which comprises an integrated data acquisition module, a purchase preference analysis module, a purchase preference storage module and a customer demand forecasting module. The integrated data acquisition module in communication with a POS (point-of-sale) system, a clothing try-on system and a customer database of a clothing retailer is used for respectively acquiring and storing POS historical purchase record, clothing try-on data and customer data, the purchase preference analysis module is used for analyzing the POS historical purchase record, the clothing try-on data and the customer data and generating customer purchase preference analysis results, the purchase preference storage module is used for building a database for storing the customer purchase preference analysis results, and the customer demand forecasting module is used for forecasting future or current customer demands. The clothing purchase preference of customers is systematically learnt and analyzed by making full use of the POS historical purchase record, the clothing try-on data and the customer data instead of relying on subjective evaluation and experience of the clothing retailer, the analysis results are more accurate, and competiveness of the clothing retailer in the clothing market is improved.

The invention discloses a user traffic prediction system in a wireless network, which comprises four subsystems, namely, basic feature extraction, user movement trajectory prediction, user traffic preference analysis and regional traffic prediction subsystems. Firstly, the user traffic is analyzed to extract user features initially. According to the user's moving trajectory data in the region, thenext step direction of the user is predicted based on the convolution neural network model. According to the traffic situation of users in the region, the next period traffic of users is predicted based on the circulating neural network model. Combined with user movement trajectory prediction and traffic prediction, the traffic distribution of the whole region in the next period is predicted. Theinvention predicts the network traffic of each wireless access point in the next period of the area by analyzing the wireless network connection and the traffic usage of the wireless network users inthe area. It can be used to solve the problems of bandwidth and channel assignment of multiple routers in wireless network. The problem of traffic usage prediction for specific users is solved. It can also be used to predict the trajectory of the user's movement.

Provided are a method and mobile terminal for performing a personalized search, capable of providing search results optimized for a user in consideration of location and user preference. The method includes acquiring a question keyword from a user and information about the location of a mobile terminal, making a local search on the basis of the question keyword and the location information to generate local search results, displaying the local search results and storing a use record of the user of the mobile terminal corresponding to the displayed local search results, generating a user preference analysis model using the location information and the use record, then applying the generated user preference analysis model to the local search results, and deducing personalized final local search results from the local search results. Thus, it is possible to provide the local search results optimized for the user.

The application discloses a system and method for recommending vehicle models. The system includes: a user classification unit, a user preference analysis unit, a user browsing record summery unit and a vehicle model recommendation unit. The method comprises the following steps: the user classification unit classifying registered users from multiple dimensions, and recording the number of users under each user class; the user preference analysis unit analyzing each browsing record of every user to obtain preference data of users; the user browsing record summery unit summarizing and analyzing user browsing records under each user class; the vehicle model recommendation unit, based on the user class which a current user belongs to and the preference data of the current user, calculating the recommendation score of all vehicles that are browsed by the users under the user class where the current user belongs, and recommending the vehicles that have higher recommendation scores to the current user. The system and the method make better pertinence and higher accuracy.

A database of user preference information is extracted and compiled from multiple websites by web-crawling robots without cooperation or specific participation by users. Users who interact with a website are frequently required to register and create a login or userID name that uniquely identifies them. Thereafter, when an individual rates an item, it is often recorded and published under their userID name such that other users can see how a specific individual rated the item. Although there is no requirement that a specific user register on different websites utilizing the identical userID, it is extremely common that this practice occurs and the use of identical userIDs on multiple sites is used herein to expand preference analysis beyond a single site. Once the database exists, users can request or be passively offered suggestions that result from preference associations across multiple websites as performed by a preference analysis and suggestion function.

The disclosure provides a user preference analysis method and device based on big data. The method comprises the steps of: acquiring interactive behavior data of a user and a content, wherein the content has at least one tag; carrying out preprocessing on the interactive behavior data, generating a feature data set, and using the feature data set as an input feature value of a gcForest model; using a quasi probability vector output by each layer of cascaded forest in the gcForest model and features of the feature data set as input features of a next layer of cascaded forest; and according to aquasi probability vector output by a last layer of cascaded forest of the gcForest model, acquiring a preference probability of the user on the tag. The user preference analysis method provided by the disclosure can provide a more accurate user preference analysis result on the basis of big data samples.

The invention discloses an online education personalized pushing method and system based on a knowledge graph. The method comprises the following steps of constructing the knowledge graph according tothe entities in teaching material information and a relationship between the entities; automatically labeling the teaching material information according to the knowledge graph to obtain the entity label information; obtaining the learning behavior information and / or learning feedback information of the user; obtaining the teaching material information corresponding to the current learning objectaccording to the learning behavior information and / or the learning feedback information, and taking the entity label information marked by the corresponding teaching material information as the to-be-analyzed label information; performing learning preference analysis according to the learning behavior information or the to-be-analyzed label information thereof, and / or performing learning masterydegree analysis according to the learning feedback information or the to-be-analyzed label information thereof, so that the personalized pushing of the teaching material information is carried out according to the learning preference and / or the learning mastery degree, and the teaching effect is better.

The invention provides a Hadoop-based user preference evaluation method and a system. The method comprises the following steps of S1: acquiring network access information of full amount of users in current network within a certain time period; carrying out data cleaning, so as to filter data which do not meet the requirements; S2: storing network access information of the users locally counted to a distributed file storage system HDFS (Hadoop Distributed File System) of a Hadoop platform, meanwhile, on the basis of a user preference evaluation algorithm, realizing user preference evaluation with massive data computing ability of a MapReduce, and generating user preference scores; S3: establishing a ''user-application'' performance value data table in a Hive database, and importing the obtained user performance scores into the data table so as to conveniently inquire with the Hive; and S4: generating a recommended application list and a target user group according to the network access information of the users and the ''user-application'' performance data table, so as to achieve important user attention and similar application recommendation. According to the Hadoop-based user preference evaluation method and the system disclosed by the invention, the problem that user's preference to the application cannot be precisely analyzed by a traditional user preference analysis method, thereby resulting to low success rate of marketing is solved.

The invention discloses an information recommendation method of calculating user preference similarity based on a context ontology tree. According to the method, differential influences of various context types and concrete examples thereof on user preferences are analyzed, and a context-based user preference extraction method is designed; then ontology is utilized to carry semantic expression on contexts, an ontology tree expression-based context similarity calculation method is constructed, and the precision of finding similar user sets in collaborative filtering recommendation is improved; and on the basis of the above-mentioned user preference extraction, the extracted contexts are introduced into a collaborative filtering recommendation process, the similarity between the context user preferences is calculated, a collaborative filtering recommendation method based on user context preference analysis is designed, and problems of sparseness, cold starting and the like of existing recommendation methods are solved.

The invention discloses a fee-paying channel preference analysis and prediction method for power clients based on an RFM model. The method comprises that a fee-paying record of the clients is extracted from a marketing service system; an analysis date is set, and a time interval R of latest fee paying, the fee paying frequency F of an analysis period and the average fee-paying amount M of the analysis period of each client in each fee-paying channel are extracted from the client fee-paying record; the R, F and M values of the each client in each fee paying channel are standardized; the R, F and M weight coefficients of each fee paying channel are calculated according to an entropy method, and a calculation formula of the RFM model of each fee-paying channel is determined finally; and a preference score of each client in each channel is calculated according to the RFM model. Thus, fee-paying channel preference of each client can be identified accurately, and a practical service demand of certain fee-paying channel in certain region can be reflected directly.

A user preference analysis method and device are provided for providing a user with customized content through preference analysis based on the user's content consumption activity. The user preference analysis method includes displaying content data on a screen of the device in response to a user input; recording content information about the content data displayed on the screen; analyzing a user preference based on the recorded content information; and storing a user preference analysis result for the content data.

Value-added information is generated by collecting information relating to apparatuses from a plurality of users, and service is automatically and adaptively provided in a manner that satisfies each user's own preference.Since a second electronic apparatus of a given user is controlled based on control information of a second electronic apparatus of another user to which first electronic apparatus information of the user is similar, electronic apparatus control service is performed in a manner adaptively matching preference of the user without complex signal processing such as user preference analysis. The electronic apparatus of the user is controlled based electronic apparatus information of the similar user with whom the user shares activity information such as transfer and purchases of apparatuses in common, electronic apparatus control service is performed in a manner adaptively matching preference of the user without complex signal processing such as user preference analysis.

The invention discloses a comprehensive analysis system for electricity payment channels. The system comprises a payment channel information management module, a channel payment condition management module, a user preference analysis module, a channel geographic distribution management module and a channel simulative construction management module. According to the system disclosed by the invention, the development idea of the current big data age is combined; a data mining technology is introduced to analyze mass payment data of electricity customers; an improved KNN algorithm is adopted in the aspect of evaluation index selection, a customer payment behavior analysis model, a channel simulative construction model and a GIS-based visualized location model are innovatively constructed, and a big data-based comprehensive analysis system for payment channels is developed on such basis.

The invention discloses a mobile Internet public opinion monitoring method and system based on a URL. The method comprises following steps: obtaining a URL library from a signaling system of a mobile network service provider, and filtering URLs obtained from the URL library to obtain effective URLs; establishing association between an IMSI of a mobile terminal and the effective URLs, simulating operation of a mobile terminal browser, performing crawler acquisition according to the effective URLs, and performing user behavior and preference analysis of the mobile terminal according to an acquisition result; and performing public opinion monitoring according to a user behavior and preference analysis result. The beneficial effects of the method and system are that firstly, manual control and operation can be prevented; and users can use the method and system without professional knowledge, and the technical threshold is low; secondly, the number of the URLs in need of acquisition is greatly reduced so that the pressure of crawler acquisition is greatly relieved; and thirdly, web crawlers can effectively acquire content of the URLs in the mobile network.

A student dietary behavior analysis method based on campus card data comprises the steps of data obtaining, dietary time rationality analysis on student dietary data and dietary balance analysis and Wechat pushing of dietary suggestions. The step of Wechat pushing of dietary suggestions includes data preprocessing and collaborative filtering application based on multiple target optimization. The foods recommended by adopting dietary time rationality analysis on student dietary, dietary balance analysis and dietary preference analysis can meet the dietary demands of students at a taste angle, the nutritional demands of students can be improved at a health angle, the students are guided to reasonably intake the foods according to the health conditions of the students, the health level is improved, and rationalization proposals are provided for a mess hall administration department.

Embodiments of the present invention provide a method and system for de-anonymization of online user identity, user tracking techniques, user behavior and preference analysis, customization of user interfaces, and combinations thereof. Fingerprinting attributes may be collected from a client device during anonymous browsing to identify the user, and based on tracked activities from the browsing session, a user profile for that user may be created and / or updated. When a user using the client device with the same fingerprinting attributes initiates a login session, the information from the stored user profile may be used to create a customized user interface.

Embodiments of the present invention provide a method and system for de-anonymization of online user identity, user tracking techniques, user behavior and preference analysis, customization of user interfaces, and combinations thereof. Fingerprinting attributes may be collected from a client device during anonymous browsing to identify the user, and based on tracked activities from the browsing session, a user profile for that user may be created and / or updated. When a user using the client device with the same fingerprinting attributes initiates a login session, the information from the stored user profile may be used to create a customized user interface.

An information navigation apparatus monitors a user's preferential tendencies among huge amounts of digital content using as objective a criterion as possible, and displays content information that would facilitate the user's content selection based on the monitored data. The apparatus is capable of accommodating the user's modification of his or her preferential tendencies on the spot. The information navigation apparatus comprises a content selection history memory unit for storing a user's content selection history, a content information database for storing content information about digital content, a preference analysis unit for analyzing the user's preferences based on said content information and said user's content selection history, and display means for displaying the result of analysis of the user's preferences by said preference analysis unit.

The invention provides a user travel preference analysis method based on data of the Internet of vehicles. According to the method, spatial attributes of travel destinations of a user are learned by performing reverse geographic encoding on GPS information of an accumulation point of the user based on a model assuming that the proportion of each type of POI points close to the accumulation point of user resident points in all POI points of the location indicates the probability of the user going to each type of POI points, then preference of the user is speculated according to travel behaviors of the user, the type of the user at each POI point is sequentially scored with respect to a suggested evaluation index, acquired index weight values are computed to acquire a score of the user after the type of the POI points is weighted, and finally the scores of the user at all types of POT points are arranged according to a certain sequence, and thus the travel preference of the user is acquired.

The embodiment of the invention provides a credit card preferential information recommendation method based on a user consumption portrait. The credit card preferential information recommendation method comprises the following steps: recording card information and transaction detail information of at least one credit card of a user; extracting the consumption type preference, the consumption placepreference, the consumption amount and the consumption frequency of the user from the transaction detail information; And performing two-layer classification on the user according to the consumptiontype preference, the consumption place preference, the consumption amount and the consumption frequency of the user, and recommending credit card discount information to the user according to the two-layer classification. The embodiment of the invention further provides a credit card preferential information recommendation system based on the user consumption portrait, computer equipment and a computer readable storage medium. Consumption preference analysis can be carried out according to the transaction detail information of the credit card of the user, and credit card discount information truly interested by the user is intelligently recommended.

The invention provides an optimized design and scheduling method and an optimized design and scheduling system for a distributed comprehensive energy system. The method comprises the following steps of firstly, constructing a mathematical model of each device of the distributed comprehensive energy system, then taking the annual total cost and annual carbon emission of the distributed comprehensive energy system as target functions, and determining constraint conditions to obtain a multi-target optimization model; optimizing and solving the multi-objective optimization model by using computersoftware to obtain a non-inferior solution set of the multi-objective optimization model; obtaining a comprehensive optimal solution in the non-inferior solution set as an optimal design and scheduling scheme by adopting a multi-dimensional preference analysis linear programming method and a sorting method close to an ideal solution; according to the invention, comprehensive optimization of designand scheduling of the A-level data center distributed comprehensive energy system is realized. The overall optimization of economic benefits and environmental benefits is realized while the energy supply availability and the power supply utilization rate of the system are improved.

Methods and systems for performing preference analysis, and, more particularly, methods and systems for performing preference analysis, are described. Certain embodiments of the invention include a system for performing preference analysis, operable in connection with software to receive preference period payment data relating to one or more invoice payments from a debtor to a creditor made during a predetermined preference period; analyze said preference period invoice payment data in accordance with predetermined ordinary course parameters to determine whether one or more of said invoice payments falls within or outside a universe of invoice payments made in the ordinary course of business; analyze said preference period invoice payment data in accordance with predetermined new value parameters to determine whether an amount of one or more or a portion of an amount of one or more invoice payments determined to fall outside of said universe of invoice payments made in the ordinary course of business was made in exchange for new value provided by said creditor to said debtor, wherein an amount of one or more of or a portion of an amount of said invoice payments falling outside said universe of invoice payments made in the ordinary course of business and determined not to be made in exchange for new value is determined to be a potentially voidable preference payment amount; and create a record of said potentially voidable preference payment amount.