International Business Machines Corporation

Maplebear Inc.

Swati Rallapalli

Dinesh C Verma

Vijay Ekambaram

Kuntal Dey

Seema Nagar

Theodoros Salonidis

Rahul Urgaonkar

Jorge J Ortiz

Bong Jun Ko

Christian Makaya

Xiping Wang

Supriyo Chakraborty

Bongjun Ko

Keith William Grueneberg

Nirmit V Desai

Mudhakar Srivatsa

Dwip N Banerjee

Raghu Kiran Ganti

Patrick Tam Vo

Prashant Anant Paranjape

Shreeranjani Srirangamsridharan

Mahmood Saajan Ashek

Syed Ali Hashim Moosavi

Nidal Qwasmi

Shehzad Noor Taus Priyo

Michael J Giancola

A method for targeted advertisement includes transmitting a pre-filter to the user device, responsive to contextual information from a user device, to determine, using a processor, one or more inferences based on physical browsing information, collected at the user device, in compliance with one or more privacy policies of the user. The method also includes receiving one or more inferences determined by the pre-filter from the user device and transmitting one or more targeted advertisements to the user device based on one or more inferences.

Recommendations based on private data using a dynamically deployed pre-filter

Methods and systems for execution of distributed analytics include building a global linked structure that describes correspondences between dataset metadata structures, analytics metadata structures, and location metadata structures and that encodes compatibility between respective datasets, analytics, and locations. A set of analytics and compatible datasets for execution is determined based on the dataset metadata structures, analytics metadata structures, and global linked structure. An optimal execution location is determined based on the determined set of analytics and compatible datasets, the location metadata structures, and the global linked structure. The set of analytics and compatible datasets are deployed to the optimal location for execution.

Linking, deploying, and executing distributed analytics with distributed datasets

A data mining method, system, and non-transitory computer readable medium include obtaining a subset of public records of data in a public domain and performing data mining, via private domain data, within the subset of the public records of data to find data in the public domain corresponding to a particular individual.

System, method, and recording medium for data mining between private and public domains

A provenance method, system, and non-transitory computer readable medium for a plurality of eidetic systems having logs, include crawling the logs of each node of a plurality of nodes of the eidetic systems to cluster segments across the logs of temporally correlated events into clustered segments and analyzing the correlated segments to interleave an order of processes in the logs and assign a probability to the order of the processes occurring.

System, method, and recording medium for distributed probabilistic eidetic querying, rollback, and replay

A data mining method, system, and non-transitory computer readable medium, include defining a set of filter constraints as a filter function for clustering users' private records of data of a private domain, selecting a subset of users' public records of data from a filtered set of data from a public domain that is common with the users' private records of data, and creating a data file including the matched user of the private domain to the public records of the user of the private domain, where the set of the filter constraints comprises a function that captures the subset of the users' public records of data who are of interest to the private domain, and only performs data mining with that set of information from the public domain.

Pixel image data of a scene is received in which the pixel image data includes a two-dimensional representation of an object in the scene. Point cloud data including three-dimensional point coordinates of a physical object within the scene corresponding to the two-dimensional representation of the object is received. The three-dimensional point coordinates include depth information of the physical object. The point cloud data is mapped to an image plane of the pixel image data to form integrated pixel image data wherein one or more pixels of the pixel image data have depth information integrated therewith. A three-dimensional bounding box is predicted for the object using a convolutional neural network based upon the integrated pixel image data.

Three-dimensional object localization for obstacle avoidance using one-shot convolutional neural network

A model trading method, system, and computer program product include extracting a feature-model list from a first application and a feature-model list from a second application on a device, creating a price model for a price for each feature-model of the feature-model list of the second application that matches a feature-model of the feature-model list for the first application, and facilitating feature-model trading between the first application and the second application based on the feature-model list and the price model.

Model trading in a device

Various embodiments request discount offers on a mobile device within a store. In one embodiment, the mobile device detects it is being shaken and in response, sends a request for a discount offer to a server. The mobile device determines its location within the store. The mobile device receives a discount offer based on the location of the mobile device within the store and information associated with the mobile device. The discount offer is displayed and feedback is communicated to the server based on the detected device movement. The feedback is an indicator that indicates acceptance, rejection or a request for a different discount offer. The detected device movement include at least one of motion intensity, direction of motion and number of shakes. If the motion intensity of being shaken is greater than a predetermined threshold, an indication of objection is emitted.

Adaptive coupon rendering based on shaking of emotion-expressing mobile device

An input dataset for training a new machine learning model is received by a processor. For each of a plurality of trained machine learning models, a hash function and a sketch of a training dataset used to train the machine learning model is retrieved. A sketch of the input dataset is computed based on the hash function and the input dataset, along with a distance between the sketch of the training dataset and the sketch of the input dataset. The computed distances of the trained machine learning models are ranked from smallest to largest, and a seed machine learning model for the input dataset is selected from the trained machine learning models based at least in part on the ranking. A training process of the new machine learning model using the selected seed machine learning model and the input dataset is initiated.

Ranking and updating machine learning models based on data inputs at edge nodes

A provenance method, system, and non-transitory computer readable medium for a plurality of eidetic systems having logs, include a log-segment clustering circuit configured to crawl the logs of each of the eidetic systems to cluster segments across the logs of temporally correlated events into clustered segments, a probabilistic interleaving circuit configured to analyze the correlated segments to interleave an order of processes in the logs and assign a probability to the order of the processes occurring, and a probabilistic linearization circuit configured to create a probability tree which includes a total probability that a process in the clustered segments causes a next process in the clustered segments until an end of the temporal event of the clustered segments for each of the interleaved order of processes interleaved by the probabilistic interleaving circuit.

Various embodiments determine a sale price of an item via a smart price tag associated with the item. In one embodiment, the smart price tag is detected as being shaken. Responsive to detecting the smart price tag as being shaken, a request for a current sale price of the item for sale is sent to a back end price server. The current sale price of the item for sale is received from the back end price server and displayed for a predetermined period of time. The current sale price may be displayed on the smart price tag or a separate display sign. The current price is displayed until expiration of a predetermined period of time unless a lock request is detected which locks the price of the item for sale at the current sale price. If a price unlock button is pressed, the sale price of the item is unlocked.

Method, medium, and system for real-time pricing through smart-price-tags

Shopping related data is obtained by using a weight sensor on a shelf to determine a reduction in weight of product on the shelf, and noting the time, and then detecting weight added to a near-by located shopping cart using a sensor, and noting the time. This data is communicated to a processor, which determines a probability that a product has been moved from the shelf to the cart if the reduction in weight upon the shelf is the same weight as the increase in weight upon the cart. Using this data, it is possible to determine a time interval during which a shopper considered purchasing the product.

Growing community of inventors

Ossining, NY, United States of America

Swati Rallapalli