Other

Amazon Technologies, Inc.

William Michael Siler

Stephen Michael Ash

Elena M Bosque

Rajkumar Haridoss

Steven L Goldman

Kushal Yelamali

Rajesh Patel

Amjad Al-Rikabi

This disclosure describes a natural language question (NLQ) query service within a service provider network that provides row level security (RLS) for autocomplete during entry of NLQs and fuzzy matching in NLQ answering. The rules take the form of per-user predicates such as Tim can only see rows with region=US. In configurations a complex extraction and preprocessing pipeline to extract distinct combinations of values against RLS predicate 'rule keys' is used. Those distinct values are indexed along with grouped rule keys to enable pushing down predicates at auto-complete time. This enables pushing part of RLS rule handling to ingestion time of a dataset rather than handling all RLS rule handling at query time, enabling meeting of latency goals. In configurations, a single logical document of unique cell values is split into multiple documents with a subset of rule keys to handle scalability limits.

Row level security in natural language question answering

A new alarm system for pulse oximeters, based on fuzzy logic, will differentiate false alarms, caused by artifact, from true alarms. Numeric input variables and corresponding fuzzy sets (oxygen saturation HIGH (high O2), NO (normal O2) and YES (desaturation) and rate of change of oxygen saturation (HIGH, MEDIUM and LOW) and their membership functions are defined. An output fuzzy set ARTIFACT is defined. Input voltages from the pulse oximeter are sampled and converted to digital form. The sampled voltages are converted by the membership functions into confidences that each fuzzy set descriptor for oxygen desaturation and reate of change apply. Rules are specified which result in confidences that the fuzzy set descriptors for ARTIFACT apply. Further rules govern the issuance of alarms for oxygen desaturation or for artifacts, momentary or continuous, so that the nurse can take appropriate action. The fuzzy logic alarm system program is written in Quick Basic 4.5, by Microsoft (R). The advantage of using the fuzzy logic alarm system for a pulse oximeter used in infants is that there will be at least 34% fewer false alarms. Pulse oximeter alarms which better reflect the actual situation will improve the specificity of the alarm system and may decrease the potential 'Cry Wolf' response of the caretaker, which now exists.

Fuzzy logic alarm system for pulse oximeters

Growing community of inventors

Germantown, TN, United States of America

William Michael Siler