International Business Machines Corporation

Adp, Inc.

Henry C Will, Iv

John Jason Auvenshine

Stefan George Wilk

John P Lamb

Lisa Seacat DeLuca

John A Gunnels

Ramya Raghavendra

Timothy James Hahn

Catherine Helen Crawford

Uday Kumar Reddy Gangireddy

Bruce E Villard, Jr

Jarrod R Anderson

The present disclosure relates to a system and method of providing analysis of chatbot conversation paths, and more particularly, to a system and method which provides visual and data observation of conversation paths and related information to provide a more efficient means of analysis. The method includes: receiving, by a computer system, a plurality of conversational transcripts, converting, by the computer system, the plurality of conversational transcripts into a visualization which includes a plurality of branches representing different conversation paths for the plurality of conversational transcripts; and displaying, by the computer system, the visualization with the plurality of branches.

Systems and methods of conversation analysis

Disambiguating user utterances is provided. Disambiguation of an utterance of a user is performed using up to a defined number of user intents in a set of possible user intents having highest confidence scores between a first confidence score threshold level and a second confidence score threshold level in response to determining that each user intent in the set of possible user intents does have a corresponding confidence score less than the second confidence score threshold level. Each of the up to the defined number of user intents is located in a user intent mapping table. A human interpretable label corresponding to each of the up to the defined number of user intents located in the user intent mapping table is extracted. Extracted human interpretable labels are assembled into a set of user intent options. The set of user intent options is sent to a client device of the user.

Chatbot disambiguation

Filtering user intents corresponding to user utterances is provided. A list of allowed user intents is generated, using a natural language understanding model of a chatbot, based on identifying one or more of a set of user intents corresponding to a user utterance within a filtered user intent mapping table. It is determined whether a user intent having a highest confidence score in the set of user intents corresponding to the user utterance is contained in the list of allowed user intents. In response to determining that the user intent having the highest confidence score in the set of user intents corresponding to the user utterance is contained in the list of allowed user intents, content corresponding to the user intent having the highest confidence score is sent, using the chatbot, to a client device of a user who submitted the user utterance as a response to the user utterance.

Filtering user intent eligibility

An example operation may include one or more of determining an energy state of a system, generating a wireless energy transfer request based on the energy state, transmitting the wireless energy transfer request to another system, receiving wireless energy transfer information from the other system, performing a wireless energy exchange with the other system based on the wireless energy transfer information, and receiving a data block associated with the wireless energy exchange from the other system.

Wireless energy transfer

A computer-implemented method for automated delivery of a medical item. The method receives registration information for a plurality of trained users. The registration information includes a registration code indicating that a user is trained in a use of a medical item. The method tracks locations of the trained users via an end user device of the trained users. The method receives a medical alert indicating a medical emergency at a location. The method identifies a medical item that would assist in the medical emergency. The method identifies a trained user near the location corresponding to the medical emergency trained in use of the medical item. The method dispatches an autonomous delivery device to deliver the medical item to the location corresponding to the medical alert. The method alerts the trained user that the medical item is being dispatched to the location of the medical emergency.

Automated medical item delivery apparatus

A first feature set for an accident is identified, based on one or more historical accident reports. The accident is geolocated to obtain road data for a location of the accident. Weather data for the accident is obtained, based on the accident location. Hidden data for the accident is obtained, based on the accident location and the time of the accident. The first feature set is combined with the road data, weather data, and hidden data to produce a complete feature set for the accident. A model feature set is generated, based on a combination of the complete feature set and a plurality of other complete feature sets produced based on historical accident reports for a plurality of other accidents.

Generating driving behavior models

Data in different, respective ranges of spreadsheet file cells is compared, and a scope of a formula determined with respect to selected cells of the ranges of cells, wherein the formula pulls input data from selected cells of one range of cells and either pulls input data or generates output data to selected cells of the other range of cells. A review flag is automatically generated in association with data in a flagged cell in response to determining: that the flagged cell is omitted from a consecutive plurality of input data rows or columns; that the selected formula input cells are not consecutive within one of the ranges of cells; and that a high percentage of data values in corresponding cell rows or columns match but that and a location of the flagged cell is shifted from a corresponding cell within the other range.

Automated structured cloud datatester

Aspects optimize an alarm time as a function of biometric sleep data. Biometric sleep data is generated from monitoring a sleeping person. A readiness period of time is determined as required for a selected caregiver to complete a task prior to tending to the sleeping person. A probability that the sleeping person will wake within the readiness time period from a current time is determined from the biometric sleep data of the sleeping person. Accordingly, an alarm is initialized (given, broadcast, etc.) to the selected caregiver in response to determining that the wake probability meets a threshold certainty value.

Codependent alarm device

An approach for analyzing data collected by a sensor-enabled device over a network is provided. Specifically, in a typical embodiment, a set of usage data will be received from a device over a network. The set of usage data may be collected via at least one sensor integrated with the device, and the set of usage data may pertain to use of the device by a user. Regardless, the set of usage data will be compared to a set of diagnostic information stored in at least one computer storage device. The set of diagnostic information typically pertains to a condition (e.g., medical) treated by use of the device (e.g., dental, cardiac, renal, etc.). Based on the comparison, at least one determination (e.g., diagnosis, treatment plan, level of compliance with applicable standards, etc.) will be made and a set of reports will be generated based thereon.

Analyzing data from a sensor-enabled device

A method includes sensing by multiple overload detection sensors connected to a power cord, a type of overload detection. The type of overload detection includes: thermal detection, voltage drop detection, and current reading detection. The method further includes powering the overload detection sensors from a same power supply as the electrical power cord by direct wiring or inductive coupling. An overload detection is triggered by one or more actionable events including: a ground fault circuit interrupter (GFCI) trip, a visual signal, an audible alarm, radio frequency identification (RFID) communication signaling, a wired or wireless communication.

Overload detection for electrical wiring

A method of locating a smartphone or electronic device may include determining a location of a such device (e.g. smartphone), continuously monitoring time and location of the smartphone, predicting expected locations of the smartphone, and issuing alerts regarding the location of the smartphone.

Method for device to report when it may be missing

An apparatus includes a power cord and multiple overload detection sensors connected to the power cord based on a type of overload detection. The type of overload detection includes one or more of: thermal detection, voltage drop detection, and current reading detection. The overload detection sensors are powered from a same power supply as the electrical power cord by direct wiring or inductive coupling. An overload detection triggers one or more actionable events powered by the power cord. The actionable events include circuitry for one or more of: a ground fault circuit interrupter (GFCI) trip, a visual signal, an audible alarm, radio frequency identification (RFID) communication signaling, a wired or wireless communication.

Growing community of inventors

Dover, NJ, United States of America

Henry C Will, Iv