199 results about "Social behavior" patented technology

Here, we introduce Z-webs, including Z-factors and Z-nodes, for the understanding of relationships between objects, subjects, abstract ideas, concepts, or the like, including face, car, images, people, emotions, mood, text, natural language, voice, music, video, locations, formulas, facts, historical data, landmarks, personalities, ownership, family, friends, love, happiness, social behavior, voting behavior, and the like, to be used for many applications in our life, including on the search engine, analytics, Big Data processing, natural language processing, economy forecasting, face recognition, dealing with reliability and certainty, medical diagnosis, pattern recognition, object recognition, biometrics, security analysis, risk analysis, fraud detection, satellite image analysis, machine generated data analysis, machine learning, training samples, extracting data or patterns (from the video, images, and the like), editing video or images, and the like. Z-factors include reliability factor, confidence factor, expertise factor, bias factor, and the like, which is associated with each Z-node in the Z-web.

Systems and methods are provided for combined social behavior tracking, online surveillance and web bot software technologies via a mobile device or computer for tracking online consumer behavior and data, cookies, embedded advertisements, predicting online consumer behavior, buying patterns by monitoring online activities, online communications, search inquiries, social networking, social plugins, social applications, advertisements, purchasing, behavior, and buying patterns, consumer address books and contact lists, blogs, chat rooms, friends, acquaintances and strangers, instant messaging, text chat, internet forum, service providers, travel and hospitality, real estate, educational services, ancillary services (as defined herein) and delivery system for behavior targeting and filtering of coupons, mobile services, products, goods and services, advertisements and service providers and related company information on a three dimensional geospatial platform using multi-dimensional and scalable geospatial mapping associated with entities providing and / or members of the service and / or social networking.

Collection and analysis of network transaction information which includes the mobile device's usage, location, movements coupled with data from non-wireless network sources allow for the automation of analysis for the detection of anti-social behaviors.

The present invention is related to mammalian nutrition and effects thereof in individuals with age associated cognitive decline such as Age Associated Memory Inpairment (AAMI) or a dementing illness such as Alzheimer's disease or related dementia, or Mild Cognitive Impairment, such as improving performance in, or reversal, prevention, reducing and delaying decline in, one or more of cognitive function, memory, behavior, cerebrovascular function, motor function, and / or brain physiology are seen. In particular, the present invention utilizes medium chain triglycerides, in one embodiment, administered as part of a long-term treatment regimen, to preserve or improve learning, attention, motor performance, cerebrovascular function, social behavior, and to increase activity levels, particularly in aging mammals.

The invention relates to a pilotless automobile control system and method with the social behavior interaction function. The pilotless automobile control system analyzes the driving intention of other vehicles, and has control over the traveling state of the automobile with the pilotless automobile control system according to the driving intention of other vehicles. According to the pilotless automobile control system and method with the social behavior interaction function, social behavior interaction can be carried out according to the driving intention of other vehicles, and therefore traveling safety of the pilotless automobile is improved.

The invention discloses an Internet financial risk monitoring system based on knowledge map, which comprises a data source module, a multi-label graph module and an analysis module. The data source module extracts entities according to different data sources, fuses entity knowledge, constructs relationships, integrates all the basic data sources from different business systems, and organizes theminto unambiguous and well-defined entity knowledge and definite relationships among entities according to business logic. The multi-tag graph module constructs a multi-tag knowledge map according to the knowledge acquired from the data source, and maps the social behavior and attributes of the members into the network map to form the behavior attributes association map of the members; The analysismodule analyzes the potential risk factors and characteristics of members in the process of Internet finance by constructing a good knowledge map. The invention changes the existing analysis dimension of the wind control model, thereby optimizing the traditional method that only the analysis dimension is added to improve the model precision.

The present invention relates to a method for detecting video spammers and promoters in online video social systems. Using attributes based on the user's profile, the user's social behavior in the system, and the videos posted by the user as well as the target (responded) videos, the feasibility of applying a supervised learning method to identify polluters (spammers and promoters) is investigated.

The invention discloses an information provision method and an information provision system for a social network. The method comprises the following steps of: acquiring the social behavior information of a first user and a second user in a real world, wherein social behaviors comprise meeting, traveling together or passing-by; and suggesting social network related information to the first user and / or the second user by combining the social behavior information in the real world. By the method and the system, virtual social contact and social contact in the real world can be well fused, the user can be prevented from obtaining a great amount of invalid information, and the waste of system resources of a mobile communication terminal also can be avoided.

The invention discloses a friend relation mining method based on user behaviors in a social network. The friend relation mining method comprises the following steps: (1) respectively establishing a bipartite graph and a directed transition network, namely user-restaurant and user-taste based on record data of existing social behaviors of users; (2) respectively extracting characteristic variables for characterizing social behaviors between two users about a node or a connection side according to a network topology relation; (3) carrying out 10-fold cross-validation on all sample data by using a machine learning classifier model xgboost, training and establishing a user relation predictor model; and (4) taking the average value of 10-fold verification results as a final evaluation result of the model. The friend relation mining method is capable of mapping social behaviors of people to the network, reflecting common variables of the social behaviors by using network topology characteristics and enabling the result of the predicted friend relation between the users to be high in accuracy, and is favorable for guiding the users to find appropriate new friends and helpful for businesses to recommend more valuable information.

The invention discloses a method and a system for obtaining reliability of users in social networking services. The method comprises the steps of collecting a first social behavior generated between the real world and other users by users in social networking services; accumulating associated data of the first social behavior; and obtaining the reliability information of the users in social networking services according to the associated data of the first social behavior accumulated. Through the invention, the reliability information with more reference value can be obtained for users to quote or inquire.

The invention discloses a social network construction and information recommendation method, an apparatus and a server thereof. The social network construction method comprises the following steps of acquiring historical behavior characteristic data of a first user; according to the historical behavior characteristic data, analyzing a second user which carries out an assigned social behavior with the first user; acquiring a target date and a target date label associated with the second user; acquiring first information used for determining information to be recommended; according to the target date, determining a recommended date of the information to be recommended; taking the first user and the second user as nodes, taking a social relation corresponding to the assigned social behavior as an edge, and taking the target date, the target date label, the first information and the recommended date as social attributes so as to construct a social network. The determined social network is used to carry out information recommendation so that pertinence of a recommended object can be increased. Simultaneously, for users who have social interactions in daily lives and do not exist in a friend list, information recommendation can be performed.

The present invention relates to combination therapies for treating Alzheimer's disease or an amyloidosis-associated pathological condition comprising co-administering a therapeutically effective amount of a first compound, and a therapeutically effective amount of a second compound. In certain embodiments, the first compound or the second compound inhibits AB peptide polymerization; is an anti-inflammatory; improves cognitive function, mood, or social behavior; is associated with Tau or alpha-synuclein; or regulates amyloid peptide washout.

The invention provides a friend recommendation method and a friend recommendation device. The recommendation method includes A, building a social complex network including multiple nodes; B, receiving recommendation requests sent by a target user to be recommended with friends and recognizing a target node corresponding to the target user in the social complex network; C, according to analysis of social complex network and nodes having edges with the target nodes and / or nodes possibly having edges with the target nodes, taking at least one of the nodes according to the analysis result as a friend recommended to the target user. In the social complex network, one node corresponds to one user; if two nodes have edges, then social behavior exists between the users corresponding to the two nodes. In application of the friend recommendation method, the registered personal background information of users can be avoided, and potential friends in social significance can be recommended for the users by analyzing the social complex network.

Systems and methods are disclosed for customizing a user's experience with an application such as a search engine application. The user's experience is customized based on inferring a mood and / or interests of the user at least in part from an analysis of the user's posts on one or more social media sites. The search engine application is configured to include a user-following engine which follows a user's activities on social media websites. By tracking a user's posts and other activity on social media websites, and possibly those of his or her friends, the user-following engine is able to draw inferences about a user, including for example the user's emotional state, current trending interests, future plans, likes / dislikes and aspirations. The user-following engine may then customize the user's search experience based on these drawn inferences.

The invention provides a user group classification method, a storage medium and a terminal, and aims to solve the problem of poor usage efficiency of user groups in the prior art. The method comprisesthe steps of obtaining friend-making relationships and social behavior data among users, and user attributes of the users; by taking the users as points and the friend-making relationships among theusers as edges, establishing a first friend-making relationship network; based on the user attributes of the users, performing value assignment on the points in the first friend-making relationship network, and based on the social behavior data among the users, performing value assignment on the edges in the first friend-making relationship network, thereby obtaining a second friend-making relationship network; and based on the second friend-making relationship network, classifying the users to obtain the user groups which the users belong to. Therefore, the usage efficiency of the user groupsis improved.

The invention relates to a method for building a friend relationship transitive tree in a social network, which belongs to the technical field of computer data mining. The friend relationship transitive tree is built for each self node, and self nodes and friend nodes are added. A social behavior probability generating model is set up for each time period, the prior parameters of the intermedium preference probability distribution and friend relationship strength distribution of the self nodes and the candidate intermediaries of each self node and new friend nodes are initialized, the candidate intermediaries is continuously interated and updated, a candidate intermediary z with the most sampling frequency is designated as the intermediary between a self node u and a new friend node y, and z to y are added into the social network of the self node u. The method models user behaviors in the social network on the basis of friend relationship transitivity; and a flat social network layering presentation method is provided, so that the reason and an internal structure of the social network are deeply analyzed, and the future development and variation of the social network are predicted.

The invention relates to a mobile Internet-based big data mining method. The mobile Internet-based big data mining method includes the following steps that: updated customer social behavior data related to customer basic data are obtained; the customer social behavior data are standardized; the standardized data are utilized to establish or update a behavior category data model; a prediction algorithm is adopted to establish or update the prediction model of a customer behavior stage; and data indicating whether customer behaviors enter a follow-up stage are obtained and are adopted as validation data feedback, and the data model and the prediction model are outputted. According to the method of the invention, based on service features of each stage of service demands, a data processing process from data extraction, data modeling, prediction modeling to prediction analysis output feedback can be formed; the result of previous processing is received and is adopted as the input of the next iteration, the self-learning functions of the prediction model and the data model can be formed; and based on incrementally updated data content and data categories, flexible and reliable data processing processes for service prediction in different sectors can be realized. The invention also provides a mobile Internet-based big data mining system.

The invention discloses a time sequence perception dynamic social scene recommendation method. The method comprises the following steps: obtaining basic data for analysis from historical consumption behaviors and social behavior records of a user; modeling a user time sequence consumption behavior and a time sequence social behavior according to the basic data so as to restore the decision processof the user in the historical consumption behavior by utilizing the obtained dynamic user personal preference and dynamic social background information, estimating the relative sorting of the commodities in combination with the decision function of the user, and realizing the training of related parameters in the decision function of the user; for a new commodity, calculating a preference score of the user for each commodity based on the decision function completing parameter training, and then predicting a result selected by the user in a stable matching mode and recommending the result. According to the method, the accurate portrait of the user can be realized, the performance of decision analysis of the user and even commodity recommendation can be improved, and the effect of multiplepurposes is realized.

The invention discloses a method for user identification between social networks based on seed node propagation, and belongs to the technical field of social networks. The method is applied to multiple fields such as advertisement recommendation, address book combination and network security. According to the method, a propagation model of seed node expansion is used, more and more matched node pairs around a seed node can be gradually discovered in an iterative manner, attribute information of users, friend link information and social behavior information are sufficiently considered at the same time, and a method for identification between the social networks is effectively realized. By adopting the identification method provided by the invention, the identification accuracy reaches 85%, the recall rate reaches 61%, and an F1 value reaches 71%, thereby being better than existing benchmark algorithms.

The invention provides a streaming media proxy cache replacing method and device. The method comprises the steps that principal component attribute data are selected from attribute data influencing popularity of streaming media files by utilizing the principal component analysis method; the popularity predicted value of streaming media objects is confirmed according to the principal component attribute data and a multivariate linear regression method, and the streaming media objects include cached streaming media in a proxy server and streaming media to be replaced into the proxy server; the comprehensive value of the streaming media objects is confirmed according to video peak signal-to-noise ratio of the streaming media objects, delay time of the streaming media objects from an original server to the proxy server and the popularity predicted value; and cache replacement is performed according to the comprehensive value of the streaming media objects and cache space of the proxy server. Streaming media proxy cache server attribute data, streaming media file attribute data and social behavior attribute data are utilized, and different environments can be adapted by adjusting weight of a streaming media quality factor and a starting delay factor so that replacing performance can be enhanced.

The invention relates to an electronic program guide (EPG) system for providing social network service, which can be used for providing information interaction function used for social behavior for one or more user(s). The EPG system comprises a media server system and a terminal system, wherein the media server system is used for retrieving and analyzing the social behavior information of the user and the program information so as to generate corresponding EPG information; the generated EPG information is sent into the terminal system through a transmission network; and after being received by the terminal system, the EPG information can be presented by an EPG showing module. The EPG system can be used for recognizing the identity of the registered user and managing the social behavior circle which the user belongs to, thus effectively guaranteeing the privacy of the personal information of the user. Meanwhile, the interaction information of the registered user can be screened, so that the personalized information sharing demand of part of the users can be met.

The invention provides a social network friend recommendation method fusing a trust degree, and relates to user similarity, confidence factor calculation and fusion. The social network topology-basedrecommendation focuses on known friends and ignores potential interested friends; the interest-based recommendation focuses on recommendation of strange users, thereby difficultly getting trust of users; and both the social network topology-based recommendation and the interest-based recommendation do not consider behaviors of the users in a social network, thereby greatly influencing the accuracy, reliability and comprehensiveness of a recommendation result. The invention provides a recommendation method comprehensively considering social network topology, user interests and social behaviors.Firstly, social similarity is calculated out according to common neighbors in the social network of the users, interest similarity is calculated according to keywords, and linear combination is performed. The social topology and the social behaviors of the users are comprehensively considered, a relationship confidence degree and a behavior confidence degree are calculated out, and fusion is performed to form a confidence factor. Finally, the similarity and the confidence factor are fused, so that the trust degree of similarity calculation is improved, and a Top-N recommendation list is generated.

This application discloses an emoji recommendation method and apparatus. The method includes: displaying a first user interface of a social network client application; detecting occurrence of a trigger event that corresponds to a preset condition for triggering delivery of an emoji recommendation from the social network server to a first user; retrieving one or more emoji recommendations from the social network server, wherein the one or more emoji recommendations are selected from an emoji library for the first user in accordance with social behavior information of the first user; and displaying the one or more emoji recommendations on the first user interface, including displaying one or more editing controls to adjust one or more parameters for calculating a correlation degree of the user and a respective emoji based on one or more attributes of the one or more emoji recommendations retrieved from the social network server.

The invention relates to the field of microblog news credibility, in particular to a news authentication method and a news authentication system based on a microblog information source. The method comprises the following steps of extracting the new information source as an information source to be authenticated, and obtaining the user information of a user corresponding to the information source to be authenticated; obtaining the mutual fans proportion, authenticated fans proportion and fans-to-attention number proportion of the user, and obtaining the social relationship credibility value of the user according to the three proportions; obtaining the user activity and history microblog average influence of the user, and taking the product of the user activity and the history microblog average influence as the social behavior credibility value of the user; obtaining the evaluation public opinion index of a microblog, finding the comment microblogs of the microblog, obtaining the comment public opinion indexes of the comment microblogs, and taking the comment public opinion index of the microblog and the public opinion indexes of the comment microblogs as a social evaluation credibility value; carrying out linear weighing summation on the three credibility values to obtain a comprehensive credibility value.

Systems and methods for performing behavioral detection using three-dimensional tracking and machine learning in accordance with various embodiments of the invention are disclosed. One embodiment of the invention involves a the classification application that directs a microprocessor to: identify at least a primary subject interacting with a secondary subject within a sequence of frames of image data including depth information; determine poses of the subjects; extract a set of parameters describing the poses and movement of at least the primary and secondary subjects; and detect a social behavior performed by at least the primary subject and involving at least the second subject using a classifier trained to discriminate between a plurality of social behaviors based upon the set of parameters describing poses and movement.

The invention proposes a computer-assisted infant cultivation method for solving the problem of low computation efficiency of the artificial evaluation in the prior art. The invention comprehensively and scientifically evaluates according to the physical and psychological development situations of the children at the age of 0-6 and provides scientific infant raising knowledge. The invention combines the currently-popular preschool education methods, such as the multiple intelligences system, the sensory integration training, the Montessori, induces and concludes five evaluation indexes for the preschool education, including the gross motor, fine motor, language ability, cognitive ability and the social behavior ability; the computer-assisted evaluation is processed towards the children according to the five indexes; then the computer makes a family guidance plan and generates a training plan according to the evaluation results; finally, the grouping training is conducted according to the training plan; the children at the age of 0-3 are cultivated through games; the children at the age of 3-6 are processed the all-around cultivation training in the aspects of physical build, intelligence quotient and emotion quotient. The computer-assisted infant cultivation method has the advantages of scientific nature, practicality, guidance, universality and sociality.

The invention discloses an intelligent home energy management method based on social network behavior perception. The method comprises S101) acquiring user network social data and external environment data, S102) performing user network social behavior perception, S103) performing user environment demand estimation, S104) performing a user demand updating judgment, S105) performing event drive electrical appliance equipment control strategy optimization, and S106) updating a control strategy of a smart home control module according to a result of the step S105), and shifting to the step S101) to continuously monitor the user network social data. Through monitoring of user's network social software and mail management software, user network social behaviors are identified and predicted in real time, a demand of a user for home environment is estimated and updated, scheduling strategies of various kinds of electrical appliance equipment of smart home are made, the domestic electrical appliance equipment are actively controlled, a comfort requirement of the user for the home environment is satisfied, and electric cost is reduced at the same time.

An analytics reporting computing device for generating a region report of a geographic region is described. The analytics reporting computing device is configured to receive a request for a region report, the request identifying a geographic region including a plurality of sub-regions and at least one selected region characteristic, and identify each sub-region. The analytics reporting computing device is also configured to retrieve transaction data and influence data associated with the geographic region, the influence data including electronic data representing user online social behavior. The analytics reporting computing device is further configured to, for each sub-region, determine a respective index score of the selected region characteristic based upon portions of the transaction data and influence data associated with each sub-region. The analytics reporting computing device is further configured to generate the region report ranking each of the sub-regions according to their index scores, and transmit the region report for display.