49 results about "Social network model" patented technology

A method and system are provided for targeting ads by effectively combining behavioral targeting and social networking. In one example, the method includes receiving a behavioral targeting model to predict a propensity of each consumer in a network to select (e.g., click) an ad of a particular category based on a behavior of each consumer, training a social network model to predict a propensity of a particular consumer to select an ad of the particular category based on features derived from a social network of the particular consumer, and training an ensemble classifier to decide when to trust the behavioral targeting model and when to defer to the social model for predicting a propensity of the particular consumer to select an ad of the particular category.

A computer implemented method, apparatus, and computer program product for managing organizational resources. The process combines social group data with management information data to form social network data, wherein social group data is derived from interactions among a plurality of users of a social group. The process analyzes the social network data to identify associations among the plurality of users, and generates a multidimensional social network model using the associations among the plurality of users. Thereafter, the process presents a set of recommendations for allocation of the organizational resources, wherein the set of recommendations are derived from the social network model.

The invention provides a user attribute and social network detection system based on space-time locus. A user behavior mode is analyzed to predict true identity attributes of a user, and data processing, social network modeling, characteristic extraction and classification prediction subsystems are included; space-time locus data is analyzed; according to the space-time locus data, an original method based on the point mutual information is proposed to establish a social network model of the user; an original non-negative tensor factorization (NTF) algorithm is proposed to automatically extract hidden characteristics of the user; the hidden characteristics of the user are utilized to predict user attributes through utilizing multiple types of classifiers. The system is advantaged in that the system is applied to user attribute authenticity detection, can be further applied to user social network detection and can be further applied to precise information push and friendly recommendation according to predicted attributes and the social network.

Systems, methods, and techniques for providing a dynamic platform for educators and businesses to employ a networking-based approach to course management and / or training through the use of social networking models. The computer-aided system and method facilitate global user collaboration and communication across a network-based learning environment through the use of various feature sets including, for example, a rewards tool. The systems and methods hereof support course creation and implementation, as well as the formation of groups, Conexus and user-defined groups. The system and method can categorize and sort these groups and courses into subsets based on subject matter bases, which thereby enables user to share information and collaborate, not just in their personalized groups, but also with learners positioned all over the world.

A method and system of deputizing people for transportation needs in a social networking model through an online people deputation system comprising of updating a calendar entry of people for person, package and project travel services listing, balancing the supply of desirable travelers with the demand by other users to serve them in transportation needs, delegating travelers for transporting people and packages from one place to another place and / or for performing tasks in a remote location and paying for services based on peoples' availability, request and response mechanism. Furthermore, the method also embodies real-time travel booking, location based searching, filtering and sorting people along with service reviews, ratings and comments for each.

A method is disclosed that enables the selection of a team of people in an organization, such as a business enterprise, to participate in a task that involves communicating with each other, in which the selection of the team seeks to maximize the team cohesiveness. The illustrative embodiment of the present invention incorporates the use of a social network model to describe the communication pattern in the organization. Based on the relationship between the organization's social network structure and the cohesiveness between the people in the organization, the technique of the illustrative embodiment estimates the dyadic cohesiveness of each pair of people, which is defined as the expected value of relationship strength between each evaluated pair of people. One component of the relationship strength is the number of interactions between the two people in the pair. The technique of the illustrative embodiment then uses the cohesiveness estimates to select teams.

The invention discloses a data processing method and device. The method comprises that a first social network model with a first association between representation nodes is obtained; the first socialnetwork model is expressed as a first adjacent matrix according to a preset representation manner; any two nodes directly associated with a first node in the first social network model are recorded asbeing direct associated, and a second adjacent matrix is generated; the structure similarity and the characteristic attribute similarity of the any two nodes with direct association in the second adjacent matrix are obtained; a fusion similarity is determined according to the structure similarity and the characteristic attribute similarity, the determined fusion similarity is screened, and a third adjacent matrix is generated on the basis of the screened fusion similarity; and on the basis of the third adjacent matrix, a second social network model of a second association between the representation nodes is generated.

A social network model, based on data relevant to a user, is used for semantic processing to enable improved entity recognition among text accessed by the user. An entity extraction module of the server, with reference to a general training corpus, general gazetteers, user-specific gazetteers, and entity models, parses text to identify entities. The entities may be, for example, people, organizations, or locations. A social network module of the server builds the social network model implicit in the data accessed by the user. The social network model includes the relationships between entities and an indication of the strength of each relationship. The social network module is also used to disambiguate names and unify entities based on the social network model.

The invention relates to a social network marketing seed user selection method considering the influence of an existing product, comprising: step 1, modeling a social network into a social graph G=(V,E, W), wherein a vertex set V represents a set of all social users in the social network, an edge set E represents a set of social relationships between the social users, and W represents a set of weights on all sides; step 2, initializing a seed user set S as an empty set, as described in the specification, wherein an initialized user set U is a set of all the user in step 1, as described in thespecification; and step 3, calculating the marketing influence of all users in the set U in step 2. The above-mentioned social network marketing seed user selection method considering the influence of the existing product considers the influence of the existing product on marketing product promotion, measures the marketing influence of social users in terms of social relations and existing products, uses the marketing return rate as the optimization goal and uses the two-way optimization method to select the seed user set to maximize the marketing return rate.

This disclosure provides a document access method and system. The document access method and system are based on a social network model which interconnects members of the social network as a function of trust. This framework provides a basis for documents to be accessed by members which are not directly specified by a document's owner, while providing a certain degree of document security.

The invention provides a public opinion information and viewpoint co-evolution model construction method based on an evolutionary game. The method belongs to the field of evolutionary games, and comprises the following steps: step 1, selecting a 100 * 100 regular mesh network as a social network model, enabling each individual on the social network to occupy one mesh in the regular network, and endowing each individual with an attribute value; step 2, taking each individual as a central individual, and carrying out cyclic collaborative evolution on the central individual; 3, a timer is used for timing operation, in each round of evolution process, when the specified time is up, the collaborative evolution process is stopped, information is infiltrated into the individual with the highest reputation value, and meanwhile the reputation value of the individual is increased; then, the collaborative calculation operation is continued; and step 4, circularly carrying out the step 2 and the step 3 until the collaborative evolution of all central individuals is completed. The method promotes emergence of positive cooperation behaviors among individuals in the social network, and has practicability.

System and means generates synthetic forms of social media data such as data from microblogging services (e.g., Twitter) and social networking services (e.g., Facebook). This system and means jointly generate interaction graph structures and text features similar to input social media data. First, an interaction graph is generated by mapping social network interactions in input (real) social media data to graph structures. This interaction graph is fitted to a social network model (or a composite model) by minimizing the distance between the input and the synthetic interaction graphs (of potentially different sizes). The distance is measured statistically or based on the performance of social media analytics. Various patterns (such as anomalies), interaction types and temporal dynamics are generated synthetically. Second, text features are extracted from input social media data with topic modeling and statistical analysis of word tuple distributions. Based on these features, synthetic social media text is generated. Third, synthetic graph structures and text features are combined to generate the synthetic social media data. The system is particularly useful in generating data to be used for developing and testing new social media analytics or for generating or analyzing social bot network behavior and campaigns in social media, and for sharing test data with others without rate and privacy concerns.

The invention discloses a user communication circle relation identification method based on a communication frequency and a communication index, belonging to the technical field of operator communication circle reputation and home package recommendation marketing. The method comprises a step of calculating a communication frequency and a communication index between every two users, a step of establishing a communication circle model corresponding to the users according to the communication frequency, the communication index and a contact time period, wherein the communication circle model comprises a work circle model, a life cycle model and a comprehensive circle model, a step of establishing a user social network model based on communication circle information corresponding to the users, and a step of constructing a home relation model based on the user life circle model. According to the method, problems of poor marketing pertinence, a low cost-benefit ratio and easily caused user complaints of an existing single-client group sending mode are effectively solved, according to the method, and the rate of marketing success is significantly improved through the identification and classification of user social network relations and home relations.

An information processing system includes a content providing device (20) providing content appropriate for a user. The content providing device (20) includes: a model storage unit (40) containing a plurality of different models depending on the user attribute; a model determining unit (34) for selecting a model corresponding to the user attribute from the models stored in the model storage unit (40); a Bayesian reasoning unit (30) for reading out the model determined by the model determining unit (34) from the model storage unit (40) and using the read-out model to obtain the content appropriate for the user through probabilistic reasoning; and a recommending unit (22) for recommending the content obtained by the Bayesian reasoning unit (30) to the user. The content providing device (20) further includes a Bayesian learning unit (32) for learning models by using a user response to the content received from an operating unit (24).