Telefonaktiebolaget Lm Ericsson (publ)

Simon Moritz

Tony Larsson

Mattias Lidström

Tor Kvernvik

Jonas Björk

Richard Carlsson

Jonas Bjork

Vincent Huang

Yi Cheng

Rickard Cöster

Nicolas Seyvet

Åsa Bertze

Joakim Söderberg

Tor Bjorn Minde

Martin Svensson

Hjalmar Olsson

Jawad Mohamed Zahoor

Hjalmer Olsson

Carl-Fredrik Sundlöf

Xianwei Shen

Christina Moritz

Abhiroop Gupta

Erik Mellegard

Olle Isaksson

Anna Nabseth

Henrik Makitaavola

Christoffer Davidsson

Erik MELLEGÅRD

Embodiments herein relate to a method performed by a network node in a communication network for handling data of objects in the communication network. The network node determines a position of an object based on a signal strength or a signal quality of a beamforming transmission, wherein the beamforming transmission comprises transmitted radio beams that swipe a surrounding. The network node determines position by analysing the signal strength or signal quality of the transmitted radio beams and comparing signal strength or signal quality from a previous beamforming transmission that swipe the surrounding. The network node further provides an output indicating the determined position of the object.

Network node and method performed therein for handling data of objects in a communication network

A method is provided for analyzing data storage applied on at least one data storage type. The data to be stored is transmitted in at least one data stream between at least one application instance and the at least one data storage type. The method includes accessing, from the at least one data stream, data selected according to pre-defined rules. Data access patterns are aggregated on the basis of the selected data, where the data access patterns are indicative of the at least one storage type applied. Classifiers are obtained by applying trained classifiers to the aggregated data access patterns. Differences between the obtained classifiers and the trained classifiers are analyzed to determine, that the obtained classifiers are indicative of at least one data storage type other than a presently used data storage type, in case at least one predefined threshold value is exceeded when analyzing the differences.

Method and system for analyzing accesses to a data storage type and recommending a change of storage type

A network anomaly detector detects a network anomaly by monitoring a communication network and provides an indication of the detected network anomaly to a network anomaly analyzer. The network anomaly analyzer receives the indication of the detected network anomaly and, on the basis of data representing the detected network anomaly and additional data, e.g., from outside the communication network, performs classification of the detected network anomaly. Depending on the classification of the detected network anomaly, the network anomaly analyzer provides a report of the detected network anomaly to another node. If for example the detected network anomaly is classified as expected behavior, reporting of the detected network anomaly may be suppressed.

Classification of detected network anomalies using additional data

It is presented a method for controlling an autonomous device () of a cellular network (). The method is performed by a network device () and comprises the steps of: predicting () a need to increase coverage of the cellular network or a need to increase capacity of the cellular network, comprising the steps of: inputting live data features into a trained classifier (); and outputting a launch class from the classifier (); and activating () an autonomous device () of the cellular network, to improve the cellular network. Corresponding network devices, computer program and computer program product are also presented.

Method and device for controlling an autonomous device

A method of building a geo-tree includes collecting a plurality of data items having geographic and contextual tags, associating the geographic tags with the contextual tags, clustering the collected data items based on the contextual tags, classifying the clusters based on the contextual tags, building a geo-tree with each classified cluster being associated with a node on the tree and storing the geo-tree.

Method of building a geo-tree

A server (--) for supporting a recommendation () to a user device () is disclosed. The server comprises a matching unit () configured to match a first location profile associated with a current location () of the user device with at least one other location profile, wherein the matching is based on at least one item consumed in the current location in a first time interval (&#x3b1;) and at least one item consumed in the other location in at least one second time interval (A-A, B-B, N-Nn) which is different from the first time interval. A recommender system (), a recommender engine computer program () and a computer program product () are also disclosed.

Matching a first location profile with at least one other location profile

A method for operating a system to provide temporal context for recommending items for consumption by a user device is described. The method comprises maintaining a record of items consumed by the user device or a group of devices within a reference period, together with the time of consumption of each item, and a content descriptor associated with each item. Temporal consumption periods are identified within the reference period, each consumption period spanning the consumption of one or more items with similar content descriptors, and each consumption period is associated with its respective content descriptor. An aggregated list is created of consumption periods recorded over a plurality of reference periods. Clusters of similar consumption periods are identified in the aggregated list, and recurring temporal patterns for user device behavior are identified in each cluster. A profile is created for each user device based on the clusters and the recurring temporal patterns for each cluster, and this profile is used to provide the temporal context at the user device.

Method and apparatus for providing temporal context for recommending content for consumption by a user device

The present invention provides an improved recommender system. In some embodiments, the recommender system automatically builds a user profile for a user based solely on the action or actions the user takes with respect to certain documents and the contents of the documents. That is, the profile is based on implicit ratings. In addition to maintaining a user profile for each user, each document in a set of documents will have its own document profile, which is also referred to as a document vector. Advantageously, in some embodiments, the user profile will consist of the same attributes as the document vectors. This advantageous feature enables the recommender system to compare users and documents in order to generate recommendations.

System and methods for updating user profiles and providing selected documents to users

A method and arrangement for processing data when training a data model involving multiple iterations of data records in a dataset (c,) stored in a database (). Memory space (d,) is allocated in the database for maintaining the data model during the training operation. The data records in the dataset are read () directly from the database for each iteration, and the data model is trained () inside the database by repeatedly applying the read data records in the training operation and updating () the data model. It is also checked () whether the updated data model has converged according to a predefined convergence condition. The data model is eventually saved () once the data model has converged.

Method and arrangement for processing data

Application servers and methods of operating the same are provided for generating a personalized recommendation of items to a first user. An updated rating value N(t) of an initial rating value N(0) is determined for each rated item based on an age of each rating. The updated rating value N(t) is based on a difference between the value of the initial rating N(0) and a neutral rating value R, and on a predetermined half-life of the ratings. The updated rating value N(t) converges towards the neutral rating value R with an increase in the age t for each rating.

Rating and novelty decay

A system for generation of processed data for use in third party relationship monitoring is described. The system includes a communications system providing services to subscribing users. The communications system includes a rules database for storing rules, a data mining agent for mining and storing data relating to subscribing users, a content generator for generating protected user-related data from the mined data and communicating said user-related data over an interface, and a rights object generator for generating a usage rights object in response to the rules stored in the rules database and communicating said usage rights object over the interface. A tamper proof processing arrangement is connected to the interface. The tamper proof processing arrangement receives the user-related data and usage rights object from the communications system and processes the user-related data under control of the usage rights object. A signal output generator generates an output signal representative of processed data received from the processing arrangement.

Method for user privacy protection

A method and a server () for handling database queries directed to a semantic database () with stored information according to a preset ontology structure and annotated as element identifiers comprising triplets with a subject, a predicate and an object. In the server (), a data analyser () collects statistics from the database and defines semantic rules from the information in the database. When a database query is received with a first set of sub-queries, a query optimiser () rewrites the query as a second set of sub-queries in the triplet format based on any of the ontology structure, the collected statistics and the defined rules. A Reduction Rate RR is also calculated for the sub-queries relating to the number of distinct subjects and objects appearing in the database with the predicates of the sub-queries. The sub-queries of the second set are finally provided as a modified query in an order according to decreasing Reduction Rates for execution in that order when searching the database.

Method and server for handling database queries

A method of providing content () associated with a weight-value, the content () previously provided to a current computer associated with a current user () that is represented by a first node () in a social network (). The method comprises the steps of: i) enabling the current computer () to display the content (), in dependence of the weight-value, ii) obtaining an input of the current user (), iii) updating the weight-value of the content (), in dependence of the input of the current user (), iv) determining a receiving computer associated with a second node () in the social network (), and v) providing the content () to the receiving computer. Corresponding computers, computer program and computer readable medium are also described.

Providing content by using a social network

In one aspect, the invention provides a system that predicts the location of an entity, such as a friend of a user of a mobile device, and displays to the user this prediction information on a display screen of the mobile device. In some embodiments, the information may be displayed to the user in an augmented reality view (e.g., the prediction information may be displayed on top of an image as seen through a camera).

Systems and method for predicting the future location of an entity

A recommendation engine of a recommender system provides a mobile device user with a personalized recommendation based on, at least in part, the user's current situation. In some embodiments, the recommender system determines the user's current situation by obtaining information identifying the user's present context(s) (e.g., location context, noise context, time context, etc.). For example, assume the user presently has the location context of 'at home' and the noise context of 'TV on.' From these contexts, the recommender system can categorize the user as being in the &#x201c;at home relaxing&#x201d; situation.

Method for providing a recommendation such as a personalized recommendation, recommender system, and computer program product comprising a recommender computer program

Growing community of inventors

Stockholm, Sweden

Simon Moritz