30 results about "Social computing" patented technology

Methods of applying adaptive social computing systems are disclosed. The social computing systems include capabilities to generate adaptive recommendations and representations of social networks derived, at least in part, from inferences of the preferences and interests of system users based on a plurality of usage behaviors, spanning a plurality of usage behavior categories. The behavioral categories include system navigation behaviors, content referencing behaviors, collaborative behaviors, and the monitoring of physical location and changes in location. Privacy control functions and compensatory functions related to insincere usage behaviors can be applied. Adaptive recommendation delivery can take the form of visual-based or audio-based formats.

Systems and methods for collaborative and interactive computer applications. A downloadable server-client collaborative mobile social computing application and methods for using the same that connect users based on both their physical location and mutual geographic proximity. A wide variety of Web-enabled devices may be used by members to access the system and interact with other members using both geographic proximity and user-defined preferences to match different users. The system is characterized by its location based services and high degree of user configurable options to provide users with both an entertaining experience and rich social interactions.

A social computing system and method includes a model creator configured to create an initial model of a user and a model enhancement module configured to analyze and record interactions of the user with other users in a social network to update and adjust the initial model to provide an enhanced model for the user. An interaction module is configured to permit interaction between user by employing one of the initial model and the enhanced model.

Executing a program structure for spanning a thread of control and a thread of execution across multiple peers in a peer-to-peer network comprises generating a program structure comprising a plurality of program instructions. A first of a plurality of network peers then executes a portion of the program instructions which initiates the execution of code hosted by said first network peer, where said portion comprising fewer than all program instructions. The first network peer then migrates one or more of the program instructions, including one or more controlling program instructions, together with any requisite data, some of which may include control data, to at least one other of the plurality of network peer. The at least one other network peer then continues execution of the program instructions in accordance with the controlling program instructions and control data until one or more of the objections of the program structure are achieved.

Providing an end-to-end citizen engagement, in one aspect, may comprise obtaining data of multiple disintegrated sources from one or more of communication and social computing channels via one or more adapters. Data refactoring and management, integration and process orchestration of the data according to a data model as data attributes of the data model may be provided. One or more analytics may be performed based on the data attributes stored according to the data model and input specified to the one or more analytics. One or more results computed by performing the one or more analytics may be provided. One or more application logics supporting one or more front-end applications may be produced. One or more front-end applications for automated sensing of user activities and sensor-based personal assistant capability may be provided.

Interpersonal relationship is a significant field in social network research, and is increasingly attended by many scholars. The word 'connection' is increasingly popular, and the 'connection' has become an indispensable social resource of people. The digital modeling and searching method for personal relationships and events belongs to an application foundation type research field of social computing, and provides support service for establishment and application of a practical digital personal relationship network. The digital modeling and searching method comprises the following steps of: defining an event concept model, and excavating and analyzing the relevant personal relationship of the event concept model based on a method for establishing a relevant role chain, establishing a personal relationship concept model based on a characteristic ternary tree structure, providing a digital system implementation method of the personal relationship concept model, constructing a personal family relationship network, and constructing a personal social relationship network according to personal life cycle event connection; and excavating and computing family culture, family connection relationship, social relationship connected with the family and the connection number and connection degree of the social relationship, comprehensively reflecting the personal connection information, and providing a specific searching method.

The invention discloses a network link prediction method based on multiple semantic influences of multiple neighbor nodes, relates to data mining and topological structure analysis, and belongs to a research problem in the field of social computing. The method comprises the following steps: data analysis: analyzing node interest characteristics and network structure characteristics based on node behaviors and node relationship data in a social network; and model training: obtaining an embedded vector of each node by the model in combination with multiple semantic influences of multiple neighbor nodes; predictive analysis: measuring the probability of existence of friend links by using the similarity between the embedded vectors of the node pairs. According to the method, the constant influence scores of the neighbors are not used, and the special semantic influence of each neighbor on the node is simulated. Local-level and global-level semantic influences of neighbor nodes in network embedding training are jointly simulated, and a joint embedding vector based on the semantic influences of all the neighbor nodes is trained for each node.

The invention relates to a group evolution method based on ACP theory under CPSS, belonging to the field of social computing and communication information technology. The technical proposal of the invention comprises the following steps: firstly, defining the node relationship in the social network and quantifying three main influencing factors of the social relationship, including the intimacy degree, the trust degree and the individual persistence degree among the individuals, so as to obtain the herd degree of the individuals. Secondly, the model of group evolutionary game is established, including the game process between individuals and the behavior renewal rules after individual game. Finally, Q reinforcement learning algorithm is introduced to guide the agent to constantly learn andupdate strategies. The invention provides a realizable dynamic model research method for studying the evacuation law of a swarm in a future intelligent environment.

Certain aspects of the present disclosure provide techniques for providing assistance to users within a social computing environment to generate questions and answers. In some cases, a user can opt to have a question optimizer generate a question based on the input the user has provided. In other cases, the user can opt to have an answer optimizer generate an answer based on the user provided input. Each optimizer includes a generative model trained with deep learning and artificial neural network to translate the user input with, for example, a long short-term memory model. The generated question and/or answer is displayed to the user in an interactive user interface and posted by the user to the social computing environment.

In a method for utilizing multiple social computing services of a user, a processor accesses a first networking service of a user and a second networking service of the user, wherein the first networking service includes a first group of contacts connected with the user and the second networking service includes a second group of contacts connected with the user. A processor retrieves the first group from the first networking service and the second group from the second networking service. A processor creates a set of contacts, wherein the set of contacts includes each contact of the first group of contacts with a corresponding link to information about that contact, and each contact of the second group of contacts with a corresponding link to information about that contact, and wherein a contact of the set of contacts has an associated relationship, established externally from either networking service, with the user.

Embodiments of the invention provide a method and apparatus for establishing a synchronized interactive multimedia communication among a plurality of users. The method includes generating, at a first device, first information associated with a multimedia content selected by a first user. The first information is generated based on parameters. The method includes transmitting the first information to a second user. The first and second user is associated with a social computer network. Further, the method includes, at second devices, receiving the first information from the social network. The method includes processing the first information to establish a synchronized multimedia interactive communication between the second and the first user. The presentation of the multimedia content in the synchronized interactive multimedia communication is synchronized among the first device and the second device(s). The synchronized interactive multimedia communication is performed along with the presentation of the multimedia content.

The invention provides an open source community issue solution personnel allocation baseline determination method and system, and relates to the technical field of collaborative and social computing, and the method comprises the following steps: a feature screening and extraction step: screening issue features according to the attributes of a target open source community, determining the human resource condition of the community, and building a simulation model; an open source community simulation step: training a reinforcement learning model according to the historical data and the simulation model of the target open source community; and a reinforcement learning model deployment step: inputting the to-be-allocated issue of the target open source community and the necessary community state information into the trained reinforcement learning model to obtain an issue solution personnel allocation baseline. According to the invention, learning can be carried out according to the developer state of the open source community and the specific information of the issue, so that a proper issue solution personnel allocation baseline is determined, and the operation efficiency of an open source software ecosystem is improved.