Abstract: A computing system is described that includes a natural language processing (NLP) node configured to receive an input data stream during a communication session with a customer; select a primary NLP engine for the communication session from a plurality of NLP engines based on accuracy scores, use case requirements, and/or performance constraints; and route the input data stream to the primary NLP engine. The NLP node may select one or more of the other NLP engines to operate as secondary NLP engines in training stages or as standby NLP engines during the communication session. The output from the primary NLP engine may be used to generate responses to customer queries within the input data stream. At a communication session boundary, the NLP node may select the most appropriate one of the NLP engines to operate as the primary NLP for a subsequent communication session.

Abstract: Techniques are described that include detecting customer personal information within any appropriate set of data, such as customer communications produced by customer-facing services offered by an organization. Once detected, the customer personal information may be tokenized within the customer communications, making the data appropriate for external systems, such as cloud-hosted applications. The disclosed techniques include a masking service that may be plugged into an on-premises pipeline of any customer-facing service that makes requests to an off-premises, cloud-hosted application. The masking service may apply rule-based detection and/or machine learning-based detection to detect both structured and unstructured customer personal information included in customer communications. The masking service may further tokenize or otherwise obfuscate or replace the detected customer personal information.

Abstract: Techniques are described that include detecting customer personal information within any appropriate set of data, such as customer communications produced by customer-facing services offered by an organization. Once detected, the customer personal information may be tokenized within the customer communications, making the data appropriate for external systems, such as cloud-hosted applications. The disclosed techniques include a masking service that may be plugged into an on-premises pipeline of any customer-facing service that makes requests to an off-premises, cloud-hosted application. The masking service may apply rule-based detection and/or machine learning-based detection to detect both structured and unstructured customer personal information included in customer communications. The masking service may further tokenize or otherwise obfuscate or replace the detected customer personal information.

Abstract: Techniques are described that include detecting customer personal information within any appropriate set of data, such as customer communications produced by customer-facing services offered by an organization. Once detected, the customer personal information may be tokenized within the customer communications, making the data appropriate for external systems, such as cloud-hosted applications. The disclosed techniques include a masking service that may be plugged into an on-premises pipeline of any customer-facing service that makes requests to an off-premises, cloud-hosted application. The masking service may apply rule-based detection and/or machine learning-based detection to detect both structured and unstructured customer personal information included in customer communications. The masking service may further tokenize or otherwise obfuscate or replace the detected customer personal information.

Abstract: Described are stable, starch-rich liquid animal feed suspensions having a high dry matter content and which do not require added heat or suspension agents for starch gelatinization and stabilization of the suspensions. Enzymatic hydrolysis and mechanical grinding are used to release starch and produce a gel-like suspension from a starting grain product, such as seeds or kernels of corn, wheat, barley, millet, oats, or rice, or flours made from the grain seeds or kernels combined with a plant processing by-product such as dried distillers grain solubles, condensed beet molasses solubles, whey, and corn steep liquor. The products produced through the processes of the present invention are flowable, dark brown to golden, gel-like suspensions with a pH of 5-7 and viscosities of 500-1000 cP at ambient temperature. In addition, the products had comparable nutritional profiles to a commercial liquid feed supplement.