International Business Machines Corporation

Doordash, Inc.

Pandian Mariadoss

Lee A Carbonell

Tsz Shing Cheng

Jeffrey Lynn Edgington

Jeff L Edgington

Tsz Simon Cheng

Methods, computer program products, and systems are presented and can include for instance: determining a location of interest; and obtaining image data from one or more camera device about the location of interest.

Obtaining camera device image data representing an event

A floor operations automation system can include an intelligent video module, profiles, decision rules, and a decision module. The intelligent video module can be configured to generate video analytics data from video captured by video cameras within a retail location. The profiles can contain data that represents a business practice or policy of the retail location and/or user-specified preferences for decision-related variables. The decision rules can express actions to be performed in response to predefined conditions within the retail location. The decision module can be configured to decide upon action to be performed, based upon the video analytics data, the profiles, and the decision rules. The decision can be made without direct input from a human agent of the retail location. The actions can affect a business system and/or a human agent associated with the retail location.

Automatic floor-level retail operation decisions using video analytics

In an approach to determine performance information of a target item operating under a particular set of context information, a method, in response to receiving a request for performance information of a target item, and operating with a first computing device, identifies context information of the first computing device. The method determines whether a knowledge base includes a response that correlates to the request for performance information of the target item operating within context information similar to the first computing device. The method, in response to determining that the knowledge base includes the response that correlates to the request for performance information of the target item, sends the performance information to the first computing device, and initiates a communication channel between the first computing device and a second computing device operating the target item and having similar context information of the first computing device.

Assisted smart device context performance information retrieval

Systems and tools for sharing medical costs between prospective patients seeking treatment, and existing patients of a medical network. Prospective patients may actively query medical costs for specific conditions and treatments for the specific conditions previously experienced by existing patients. Existing patients contributing to the documents accessible by the medical network may upload anonymous versions of EOBs, medical bills and medical documents to the medical network in exchange for rewards. The prospective patients may communicate and query the desired information using natural language inputs to instruct a client computing system to search the medical network for relevant treatment information. The prospective patient may use natural language commands or other inputs to filter the query results by condition, location, cost, quality of service, service provider, insurance provider, or any other parameter that may be detailed by the medical documents accessible through the medical network.

Medical network

A method for monitoring safety conditions within an environment includes monitoring an environment by identifying one or more users accessing the environment based on existing and generic profiles selected based on visual recognition and analysis techniques, and consensually monitoring activity within the environment. A context of a situation of the one or more users accessing the environment is determined, based on a set of predetermined rules tailored to the environment, identified users of the one or more users, and monitoring data from monitoring the activity of the one or more users within the environment. Responsive to determining the context of the situation within the environment is an unsafe, based on the monitoring data and the set of predetermined rules, a mitigating action is selected from a set of mitigating actions corresponding to the determined context of the situation, and the mitigating action that is selected is automatically deployed.

Virtual safety guardian

A method, computer system, and a computer program product for cognitive vetting is provided. The present invention may include determining that an identified person is not expected. The present invention may include retrieving historical information relevant to a past interaction with the identified person. The present invention may then include enabling a present interaction with the identified person. The present invention may lastly include determining a recommendation based on an analysis of the retrieved historical information and the present interaction.

Cognitive vetting system for unsolicited residential visitors

Validation of asset movement can begin with the definition of a virtual tripwire for video cameras of a video surveillance system that monitor a defined area of interest through which RFID-identified assets are conveyed. The virtual tripwire can visually define a boundary within the view field of the video camera. The video camera can detect the movement of an asset through a virtual tripwire and an asset management system can be notified of the potential misdirection of the asset. The asset management system can obtain the asset's RFID data from a RFID handling system that monitors the area of interest. The validity of the detected movement can be determined using RFID data and an asset movement specification that defines pathing rules for assets and virtual tripwires. When the movement of the asset is determined to be invalid, a record of suspect movement data can be generated for the asset.

Validating asset movement using virtual tripwires and a RFID-enabled asset management system

A system for performs video analytics by receiving a video stream from a video capture device over a network to a server remotely located from a video capture device. The server extracts the one or more metrics by analyzing the video stream. The server compares the extracted one or more metrics from the video stream from the video stream against at least one previously established value defined at the server as part of assessing a previously established condition, defined at the server, to generate either a TRUE or a FALSE result. Responsive to a TRUE result, the server automatically performs a notification action that conveys a notification to a remotely located device of a previously designated user when the previously established condition is automatically detected by the analytics engine. Responsive to a FALSE comparison result, the server does not performing the notification action to the remotely located device.

Network based video analytics through an application program interface (API) with metric triggered notifications

One or more processors receive recording data of a meeting between a professional and a client. One or more processors analyze the recording data to make one or more determinations. One or more processors identify one or more characteristics of the professional based on the one or more determinations. One or more processors match the one or more characteristics of the professional to one or more preferences of an individual seeking one or more professionals. One or more processors build a profile of the professional based on the one or more characteristics and store the profile in a database. One or more processors search the database for one or more profiles that provide a match of the one or more preferences of the individual seeking one or more professionals and display the one or more profiles.

Growing community of inventors

Allen, TX, United States of America

Pandian Mariadoss