541results about How to "Improve recommendations" patented technology

A search and recommendation system employs the preferences and profiles of individual users and groups within a community of users, as well as information derived from categorically organized content pointers, to augment Internet searches, re-rank search results, and provide recommendations for objects based on an initial subject-matter query. The search and recommendation system operates in the context of a content pointer manager, which stores individual users' content pointers (some of which may be published or shared for group use) on a centralized content pointer database connected to the Internet. The shared content pointer manager is implemented as a distributed program, portions of which operate on users' terminals and other portions of which operate on the centralized content pointer database. A user's content pointers are organized in accordance with a local topical categorical hierarchy. The hierarchical organization is used to define a relevance context within which returned objects are evaluated and ordered.

CCRM is a business method and computer software system, to be used by Enterprises selling portfolios of products/services, aiming to optimize the expected value of transactions (or contracts) with consumers or business customers. At a transaction level, CCRM estimates the probability of choice of potential offers by the customer. These offers may be presented alone with possible variation of their attributes (such as price), or in combinations/sets, or in sequences. CCRM calculates the probability of consequent conversion and realization of the sale. Probabilities of choice and conversion are forecasted based on a disaggregated customer choice model, taking into account customer characteristics and stated preferences as well as product/service attributes such as price. Offers are then scored and ranked by expected value based on their revenue, cost and choice probability. Finally, CCRM recommends which offer(s) to present to the customer, at which price(s) and in which display/sequence order, to maximize a business objective function such as the expected value of the transaction/contract.

A novel system and method of predicting a user's rating of a new item in a collaborative filtering system is described. The invention incorporates social network information in addition to user ratings to make recommendations. The distance between users in the social network is used to enhance the estimate of user similarities for collaborative filtering. The social network can be constructed explicitly by users or deduced implicitly from observed interaction between users.

Computer-implemented processes are disclosed for clustering items and improving the utility of item recommendations. One process involves applying a clustering algorithm to a user's collection of items. Information about the resulting clusters is then used to select items to use as recommendation sources. Another process involves displaying the clusters of items to the user via a collection management interface that enables the user to attach cluster-level metadata, such as by rating or tagging entire clusters of items. The resulting metadata may be used to improve the recommendations generated by a recommendation engine. Another process involves forming clusters of items in which a user has indicated a lack of interest, and using these clusters to filter the output of a recommendation engine. Yet another process involves applying a clustering algorithm to the output of a recommendation engine to arrange the recommended items into cluster-based categories for presentation to the user.

A process, system and computer software are rovided to facilitate at least one recommendation to one or more users (420) and/or one or more applications (430) using multidimensional data (410). In particular, the multidimensional data (410) which define a multidimensional space (400) is accessed. The multidimensional space (400) can have more than two dimensions, each capable of providing variable information. Then, information from the multidimensional space is retrieved. Further, the recommendation is generated based on the retrieved information. In addition, it is possible to generate a recommendation-specific query (440). This can be performed by generating the recommendation-specific query (440) to access a multidimensional cube and retrieve data stored therein. Then, the recommendation can be issued based on teh data retrieved from the multidimensional cube.

Computer-implemented processes are disclosed for clustering items and improving the utility of item recommendations. One process involves applying a clustering algorithm to a user's collection of items. Information about the resulting clusters is then used to select items to use as recommendation sources. Another process involves displaying the clusters of items to the user via a collection management interface that enables the user to attach cluster-level metadata, such as by rating or tagging entire clusters of items. The resulting metadata may be used to improve the recommendations generated by a recommendation engine. Another process involves forming clusters of items in which a user has indicated a lack of interest, and using these clusters to filter the output of a recommendation engine. Yet another process involves applying a clustering algorithm to the output of a recommendation engine to arrange the recommended items into cluster-based categories for presentation to the user.

A process for investment in intellectual property, comprising providing an accounting for an intellectual property investment; providing a valuation with respect to the intellectual property investment; performing financial analysis related to the intellectual property investment and making a recommendation based upon the financial analysis; and managing the investment based upon the accounting, valuation, and analysis for the investment. The financial analysis includes computing one or more financial ratios or indices, comparing financial information relating to the IP investments to one or more other IP investments, and making a financial transaction recommendation with respect to the IP investment. The analysis and recommendation process may stand alone or may be used in conjunction with pre-existing, non-IP-based securities analysis and recommendation/estimation processes.

The invention discloses a music recommendation method, which comprises: an association value among music is obtained by acquiring and analyzing related data sources of the music beforehand, and is saved in music-associated network; when needed to recommend the music to a user, the music related with the interest of the user are acquired to serve as a recommendation seed; an association value of the recommendation seed and the music is obtained in the music-associated network; and the music which has a maximum association value with the recommendation seed is selected and recommended to the user. The invention also discloses a music recommendation device. The method and the device enlarge the selectable range of music recommendation and are convenient to recommend to a user more music possibly loved by the user. In addition, the method and the device can feedback preference information of the user to the music-associated network to improve the grasp of the user interest, thereby realizing the personalized music recommendation to specified users to a certain extent and enhancing the effect of the recommendation.

An avatar having artificial intelligence for identifying and providing relationship or wellbeing recommendations is provided. The avatar acts as an electronic representation of a user. The avatar searches available information and makes recommendations to the user based on information received from the user or other sources regarding the user's relationship with another person or the user's wellbeing. In this way, the avatar continually learns more about the user to improve future recommendations to enhance the user's wellbeing and relationship with the other person.

An invention for displaying patterns of utilization of a resource wherein the resource includes a plurality of correlated or uncorrelated objects. The method consists of providing a number of graphical formats from which a format is selected for display of patterns of utilization. Additionally, a query is submitted regarding a particular utilization of the resource. Along with the selected format and query inputs, the invention receives information regarding utilization of the resource from a system. Once the invention receives the inputs and the utilization information from the system, the invention processes the information to a format that conforms with the inputs. The invention then displays the processed information in the selected graphical format. The invention also allows the selection of a second graphical format from the graphical formats for altering the display to show the processed information in the second selected format.

The invention provides a mobile data traffic package recommendation algorithm based on user historical data according to data mining analysis technology. The mobile data traffic package recommendation algorithm comprises the following steps of: 1) a target user finding period comprising the processes of a, acquiring a processed generated data set which comprises a training set and a prediction set, b, executing a random forest classification algorithm for finding a latent data traffic package improving user as a target user, and c, ending; 2), a data traffic package recommendation period comprising the process of a, acquiring a processed generated prediction set, b, executing a K-means clustering algorithm for obtaining a slightly similar user cluster, c, obtaining the target user obtained in the process 1)-b, d, executing a TopN recommendation algorithm on the target user in a same cluster according to a similarity function of the user, and e, ending. The mobile data traffic package recommendation algorithm is used for finding the latent user with a latent data traffic improvement requirement according to data mining technology and executing a recommended plan on the user. Compared with a traditional method, the mobile data traffic package recommendation algorithm has advantages of higher accuracy, higher efficiency, simple realization, low cost, etc.

A decision support system includes a measurement device configured to continuously measure a physiological parameter of a patient. An insulin delivery device provides insulin to the patient per an initial basal profile and the parameter measurements. A storage device holds historical data of insulin delivery to the patient. A processor determines deviations of the delivery of insulin from the basal profile for one or more time period(s) using the historical data, computes a respective first basal-profile adjustment for each of the one or more time period(s) using the determined deviations, and annunciates the computed first basal-profile adjustment(s). A method of recommending a basal-rate adjustment includes measuring the parameter, infusing the patient with insulin and storing the historical data, determining the deviations from the basal profile, computing the first basal-profile adjustments, and annunciating the computed first basal-profile adjustment(s).

The invention discloses a method for friend recommendation based on similar associations in a social network and belongs to the field of data mining and information retrieval. Social associations in the social network are found through social information of users, a rule for calculating association similarity is raised from the two aspects of the structure and the attribute, the users are classified through the topological structure of user nodes in the associations, the roles of the nodes in the network are defined by analyzing the roles and the status of the user nodes in the belonging associations and other associations, and the users of the same type or various types corresponding to the similar associations are recommended to the users of various types in the target association to serve as friend recommendation sets. By the adoption of the method, traditional similarity calculation between single users is expanded into similarity calculation between the associations, and the traditional friend recommendation operation between the users is expanded into the operation that the users are classified through role discovery and the users of the same type or various types are recommended to the users of various types in the target association. The method can be widely applied to the related fields of the social network, electronic commerce and the like.

The invention discloses an electronic book recommendation method, electronic equipment and a computer storage medium. The electronic book recommendation method is used for recommending electronic books to a first user. The method comprises the steps of searching for at least one second user similar to attributes of the first user; determining an electronic book set used for complementary recommendation according to reading history data of at least one second user; selecting the electronic books from the electronic book set to be recommended to the first user. As can be seen, considering similarities among attributes of the similar users, provided is the novel electronic book complementary recommendation method in which the electronic books are screened from the reading history data of thesimilar users to be recommended to the first user, and the types of the recommended electronic books are richer.

An apparatus, system and method for a neural engine for recommending picks in an on-line fantasy sport draft and in on-line fantasy trades. The apparatus, system and method may include at least one computing memory having associated therewith a plurality of rules, wherein at least ones of the plurality of rules include historical performance information for at least two fantasy sports teams in at least two fantasy sports leagues, wherein one of the at least two fantasy sports leagues is associated with the on-line fantasy sports draft, and expert information regarding the picks in the on-line fantasy sports draft. The present invention may additionally include at least one computer processor that applies ones of the plurality of rules drawn from the at least one computing memory to arrive at a recommendation.

A system, method, and computer program product discover relationships among items and recommend items based on the discovered relationships. The recommendations provided by the present invention are based on user profiles that take into account actual preferences of users, without requiring users to complete questionnaires. An improved binomial log likelihood ratio analysis technique is applied, to reduce adverse effects of overstatement of coincidence and predominance of best sellers. The invention may be used, for example, to generate track lists for a personalized radio station.