International Business Machines Corporation

Kyndryl, Inc.

Kim Alice Eckert

Rhonda L Childress

Ryan D McNair

Jente Benedict Kuang

Minh Q Pham

Michael Bender

David B Kumhyr

Cesar Augusto Rodriguez Bravo

David Alonso Campos Batista

John Richard Feezell

Computer-implemented methods for a user-friendly and self-managed CAPTCHA system. Aspects include storing a copy of an image selected from a set of images as a source image. Aspects further include generating a reference image by applying an image obfuscation technique to the image and a challenge image by applying a different image obfuscation technique to the image. Aspects include dividing the challenge image into partitions and placing the partitions randomly on a virtual canvas. Aspects include displaying the reference image and the virtual canvas on a user device requesting to access a protected resource. Aspects include receiving a solution image comprising the partitions of the challenge image arranged by a user from the user device. Aspects also include generating a similarity score by comparing the source image and the solution image. Aspects further include determining that the similarity score is below a threshold value and performing a security action.

User-friendly and self-managed challenge-response authentication

An approach is disclosed that determines that a change is needed to a remote system that is managed by a change management system that manages changes to many remote systems. A change management time window when the change is scheduled to be performed at the selected remote system is identified and a monitoring request is sent to the remote system. The monitoring request causes the remote system to run a monitoring process. The change management system receives an activity notification that was identified by the monitoring process. In response to the activity notification matching the change needed, the change scheduled at the selected remote system is canceled by the change management system.

Automatic identification of changes on servers with scheduled maintenance

Disclosed embodiments provide techniques for providing vehicular recommendations based on driver habits. Embodiments utilize a variety of input data, including, but not limited to, static vehicular data, dynamic vehicular data, and/or environmental data. In embodiments, empirical rules are used to adjust recommended maintenance schedules based on the input conditions. Additionally, the adjusted recommendations along with unscheduled maintenance data are input to a machine learning system, such as a neural network. The machine learning system is used to further revise the maintenance schedule, estimate end of life of the vehicle, and issue recommendations for when to sell a vehicle and recommendations on attributes of a new vehicle for acquisition.

Vehicle recommendations based on driving habits

A computer-implemented method includes: monitoring, by a user device, a location of the user device; determining, by the user device and based on the monitoring, that the user is within a threshold distance or a threshold arrival time of the service provider location; and outputting, by the user device, user information to the service provider based on the determining that the user is within the threshold distance or the threshold arrival time of the service provider location. The user information indicates services to provide to the user by the service provider upon the user's arrival to the service provider location. The outputting causes the service provider to receive the user information for serving the user upon the user's arrival to the service provider location.

Automated service request system

A method for providing haptic feedback to participants of multi-party phone conversations that includes opening a communications session with a conference system for at least two users each having user specific communications devices, user specific conduct measuring devices, and user specific haptic feedback device registered with the conference system. Analyzing content of the communications session from content received by the conference system through the user specific communications device for at least one of the users; and capturing status for said at least two users from data measured by the user specific conduct measuring device for the at least two users. Determining with the conference system if the content of the communications session and the status of said at least two users calls for input by the user through said user specific communications device. Sending a feedback signal from the conference system to the user specific haptic feedback device.

Haptic feedback during phone calls

Methods, systems, and computer program products are provided for monitoring an entity for personal water retention management. Health data for the entity is monitored via one or more sensors. Changes in the monitored health data are tracked over time. Based on the monitored health data, occurrence of a water retention triggering event associated with a provided medical recommendation is determined. When the water retention triggering event is determined to have occurred, the medical recommendation is provided to the entity.

Monitoring individuals for water retention management

Systems, methods and tools for improving healthcare communication between physicians and patients by utilizing audio recordings systems capable of collecting voice data of patient conversations with healthcare providers. The communication system converts the recorded voice data into text using voice to text conversion software, analyzes the voice data using a natural language processor to parse for key words and phrases relating to the patient's health and concerns. Voice data may be additionally analyzed by cognitive analysis systems and machine learning algorithms designed to identify the sentiment that the patient is portraying while discussing the patient's concerns about health-related experiences or symptoms and cross-referenced with social media and other external websites or applications, confirming a patient's sentiment or providing additional key words and phrases unraised by the patient when communicating with the physician.

Automated system and method for improving healthcare communication

Method for improving healthcare

Systems and methods for computer-based escalation detection are disclosed. In embodiments, a method includes: determining an occurrence of an interaction event between a first party and a second party within a recording including audio data; analyzing the audio data; determining, based on the analyzing the audio data, an escalation during the interaction event to generate escalation data; saving the escalation data; partitioning each interaction event into a plurality of sections, wherein a first section represents a start of the interaction event, and another section represents an end of the interaction event; assigning a sentiment score for each of the plurality of sections; and calculating an overall sentiment score for the interaction event by combining the sentiment scores for each of the plurality of sections, wherein the saved escalation data includes the overall sentiment score.

Computer-based escalation detection

A method, executed by one or more processors, includes identifying at least one product for delivery and create a shipping manifest for the at least one product. The method includes extracting from the shipping manifest, a required amount of storage space for the at least one product and one or more environmental conditions required for storage of the at least one product at the receiving location. Furthermore, the method includes identifying a storage space location for storage of the at least one product at the receiving location, wherein the identified storage space location provides the required amount of storage space and the one or more environmental conditions required for the at least one product.

Managing delivery of environmentally sensitive products

At an application executing in a system, a usage pattern of the system and an entry in a data use history of the system are analyzed. Responsive to the analyzing, a data item is identified for caching at the system, wherein the data item is accessible to the system from at a remote data processing system over a data network at a present time, and the data item will be requested from the system at a future time when no network connectivity will be available to the system. A determination is made whether a caching control prevents the caching of the data item at the system. Responsive to the caching control not preventing the caching of the data item, the data item is cached on the system.

Smart cache for offline data availability

Systems an methods of computer-based escalation detection are disclosed. In embodiments, a method includes: determining an occurrence of an interaction event between a first and second party within a recording including audio data; analyzing the audio data; determining an escalation during the interaction event to generate escalation data; partitioning each interaction event into a plurality of sections; assigning a sentiment score for each of the plurality of section; calculating an overall sentiment score for the interaction event, wherein the saved escalation data includes the overall sentiment score; graphing the overall sentiment score for the interaction event with a plurality of additional overall sentiment scores from respective additional interaction events to produce a graph of sentiment scores over time; and detecting a pattern of increasing of decreasing overall sentiment scores over time based on the graph.

Escalation detection using sentiment analysis

A method for managing a rechargeable battery. The method includes a computer processor identifying a rechargeable battery within a first device. The method further includes a computer processor identifying a battery maintenance policy associated with the rechargeable battery. The method further includes a computer processor determining a first set of models for implementing the identified battery maintenance policy on the identified rechargeable battery based on the identified battery maintenance policy and one or more environmental factors corresponding to the first device. The method further includes a computer processor installing the first set of models in the first device. The method further includes a computer processor performing an intervention action based, at least in part, on a current state of the first set of models and one or more current environmental factors corresponding to the first device.

Growing community of inventors

Austin, TX, United States of America

Kim Alice Eckert