Abstract: A method of authorizing content for use, e.g., in association with a conversational bot. The method begins by configuring a conversational bot using a machine learning model trained to classify utterances into topics. Utterances that are not recognized by the machine learning model (e.g., according to some configurable threshold) are then identified. Using a clustering algorithm, one or more of the identified utterances are then processed into a grouping. Information identifying a topic associated with the grouping is then received and, in response, the machine learning model is updated to include the topic.

Abstract: A method to select a response in a multi-turn conversation between a user and a conversational bot. The conversation is composed of a set of events, wherein an event is a linear sequence of observations that are user speech or physical actions. Queries are processed against a set of conversations that are organized as a set of inter-related data tables, with events and observations stored in distinct tables. As the multi-turn conversation proceeds, a data model comprising an observation history, together with a hierarchy of events determined to represent the conversation up to at least one turn, is persisted. When a new input (speech or physical action) is received, it is classified using a statistical model to generate a result. The result is then mapped to an observation in the data model. Using the mapped observation, a look-up is performed into the data tables to retrieve a possible response.

Abstract: A technique for semantic search and retrieval that is event-based, wherein is event is composed of a sequence of observations that are user speech or physical actions. Using a first set of conversations, a machine learning model is trained against groupings of utterances therein to generate a speech act classifier. Observation sequences therein are organized into groupings of events and configured for subsequent event recognition. A set of second (unannotated) conversations are then received. The set of second conversations is evaluated using the speech act classifier and information retrieved from the event recognition to generate event-level metadata that comprises, for each utterance or physical action within an event, one or more associated tags. In response to a query, a search is performed against the metadata. Because the metadata is derived from event recognition, the search is performed against events learned from the set of first conversations.

Abstract: A method and computing platform to imitate human conversational response as a context transitions across multiple channels (e.g., chat, messaging, email, voice, third party communication, etc.) where inputs to the system are categorized into identified speech acts and physical acts, and a conversational bot is associated to the channels. In this approach, a data model associated with a multi-turn conversation is provided. The data model comprises an observation history, wherein an observation in the observation history includes an identification of a channel in which the observation originates. As turns are added to the multi-turn conversation, a conversational context across multiple channels is persisted using the data model. Using this approach, an AI-supported conversation started in one channel can move to another conversation channel while maintaining the context of the conversation intact and coherent.

Abstract: A conversational bot system uses a set of conversations that have been annotated to identify speech acts, wherein a speech act is a labeled grouping of utterances. To facilitate processing, a data model associated with a multi-turn conversation is received. The data model comprises an observation history. Upon receipt of query that includes a sequence of at least two or more utterances, an utterance ranking algorithm is applied. The algorithm selectively reorders the utterances in the sequence into a ranked order of importance that reflects a lowest to highest priority of response. In response to applying the utterance ranking algorithm, the data model is then updated to reflect the ranked order. In one embodiment, updating the data model positions the highest priority utterance as a most recent utterance in the observation history. The updated data model is then used to attempt to generate a coherent response to the query.

Abstract: A method and computing platform to imitate human conversational response as a context transitions across multiple channels (e.g., chat, messaging, email, voice, third party communication, etc.) where inputs to the system are categorized into identified speech acts and physical acts, and a conversational bot is associated to the channels. In this approach, a data model associated with a multi-turn conversation is provided. The data model comprises an observation history, wherein an observation in the observation history includes an identification of a channel in which the observation originates. As turns are added to the multi-turn conversation, a conversational context across multiple channels is persisted using the data model. Using this approach, an AI-supported conversation started in one channel can move to another conversation channel while maintaining the context of the conversation intact and coherent.

Abstract: A technique for semantic search and retrieval that is event-based, wherein is event is composed of a sequence of observations that are user speech or physical actions. Using a first set of conversations, a machine learning model is trained against groupings of utterances therein to generate a speech act classifier. Observation sequences therein are organized into groupings of events and configured for subsequent event recognition. A set of second (unannotated) conversations are then received. The set of second conversations is evaluated using the speech act classifier and information retrieved from the event recognition to generate event-level metadata that comprises, for each utterance or physical action within an event, one or more associated tags. In response to a query, a search is performed against the metadata. Because the metadata is derived from event recognition, the search is performed against events learned from the set of first conversations.

Abstract: A method to select a response in a multi-turn conversation between a user and a conversational bot. The conversation is composed of a set of events, wherein an event is a linear sequence of observations that are user speech or physical actions. Queries are processed against a set of conversations that are organized as a set of inter-related data tables, with events and observations stored in distinct tables. As the multi-turn conversation proceeds, a data model comprising an observation history, together with a hierarchy of events determined to represent the conversation up to at least one turn, is persisted. When a new input (speech or physical action) is received, it is classified using a statistical model to generate a result. The result is then mapped to an observation in the data model. Using the mapped observation, a look-up is performed into the data tables to retrieve a possible response.

Abstract: A conversational bot system uses a set of conversations that have been annotated to identify speech acts, wherein a speech act is a labeled grouping of utterances. To facilitate processing, a data model associated with a multi-turn conversation is received. The data model comprises an observation history. Upon receipt of query that includes a sequence of at least two or more utterances, an utterance ranking algorithm is applied. The algorithm selectively reorders the utterances in the sequence into a ranked order of importance that reflects a lowest to highest priority of response. In response to applying the utterance ranking algorithm, the data model is then updated to reflect the ranked order. In one embodiment, updating the data model positions the highest priority utterance as a most recent utterance in the observation history. The updated data model is then used to attempt to generate a coherent response to the query.

Abstract: A method to select a response in a multi-turn conversation between a user and a conversational bot. The conversation is composed of a set of events, wherein an event is a linear sequence of observations that are user speech or physical actions. Queries are processed against a set of conversations that are organized as a set of inter-related data tables, with events and observations stored in distinct tables. As the multi-turn conversation proceeds, a data model comprising an observation history, together with a hierarchy of events determined to represent the conversation up to at least one turn, is persisted. When a new input (speech or physical action) is received, it is classified using a statistical model to generate a result. The result is then mapped to an observation in the data model. Using the mapped observation, a look-up is performed into the data tables to retrieve a possible response.

Abstract: A technique for semantic search and retrieval that is event-based, wherein is event is composed of a sequence of observations that are user speech or physical actions. Using a first set of conversations, a machine learning model is trained against groupings of utterances therein to generate a speech act classifier. Observation sequences therein are organized into groupings of events and configured for subsequent event recognition. A set of second (unannotated) conversations are then received. The set of second conversations is evaluated using the speech act classifier and information retrieved from the event recognition to generate event-level metadata that comprises, for each utterance or physical action within an event, one or more associated tags. In response to a query, a search is performed against the metadata. Because the metadata is derived from event recognition, the search is performed against events learned from the set of first conversations.

Abstract: A method to select a response in a multi-turn conversation between a user and a conversational bot. The conversation is composed of a set of events, wherein an event is a linear sequence of observations that are user speech or physical actions. Queries are processed against a set of conversations that are organized as a set of inter-related data tables, with events and observations stored in distinct tables. As the multi-turn conversation proceeds, a data model comprising an observation history, together with a hierarchy of events determined to represent the conversation up to at least one turn, is persisted. When a new input (speech or physical action) is received, it is classified using a statistical model to generate a result. The result is then mapped to an observation in the data model. Using the mapped observation, a look-up is performed into the data tables to retrieve a possible response.

Abstract: An electrical circuit comprising a line driver for providing Ethernet signals is disclosed. The line driver comprises a voltage mode line driver for producing 1000BT and 100BT Ethernet signals and an active output impedance line driver arranged parallel to the voltage mode line driver. The line driver is capable of producing 1000BT or 100BT or 10BT Ethernet signals, wherein either the voltage mode line driver or the active impedance line driver is active.

Abstract: An electrical circuit comprising a line driver for providing Ethernet signals is disclosed. The line driver comprises a voltage mode line driver for producing 1000BT and 100BT Ethernet signals and an active output impedance line driver arranged parallel to the voltage mode line driver. The line driver is capable of producing 1000BT or 100BT or 10BT Ethernet signals, wherein either the voltage mode line driver or the active impedance line driver is active.

Abstract: Aspects of a method and system for a power reduction scheme for Ethernet PHYs are provided. An Ethernet PHY in a link partner may disable transmission via a transmit DAC integrated during an inactive connection, 10Base-T autonegotiation operation, and/or active 10Base-T connection with no data packet transmission. The DAC may be a voltage mode or current mode DAC. The PHY or a MAC device may determine when to disable transmission via the DAC. In this regard, the PHY or the MAC device may generate appropriate signals for disabling the transmission. The DAC may be enabled for transmission by the PHY or the MAC device when a connection becomes active or when an active 10Base-T connection is ready to transmit data. Moreover, the PHY may enable transmission via the DAC when operating in a forced 10Base-T mode of operation and the connection to the link partner is active.

Abstract: Aspects of a method and system for a power reduction scheme for Ethernet PHYs are provided. An Ethernet PHY in a link partner may disable transmission via a transmit DAC integrated during an inactive connection, 10Base-T autonegotiation operation, and/or active 10Base-T connection with no data packet transmission. The DAC may be a voltage mode or current mode DAC. The PHY or a MAC device may determine when to disable transmission via the DAC. In this regard, the PHY or the MAC device may generate appropriate signals for disabling the transmission. The DAC may be enabled for transmission by the PHY or the MAC device when a connection becomes active or when an active 10Base-T connection is ready to transmit data. Moreover, the PHY may enable transmission via the DAC when operating in a forced 10Base-T mode of operation and the connection to the link partner is active.

Abstract: An integrated receiver with channel selection and image rejection substantially implemented on a single CMOS integrated circuit is described. A receiver front end provides programmable attenuation and a programmable gain low noise amplifier. Frequency conversion circuitry advantageously uses LC filters integrated onto the substrate in conjunction with image reject mixers to provide sufficient image frequency rejection. Filter tuning and inductor Q compensation over temperature are performed on chip. The filters utilize multi track spiral inductors. The filters are tuned using local oscillators to tune a substitute filter, and frequency scaling during filter component values to those of the filter being tuned. In conjunction with filtering, frequency planning provides additional image rejection. The advantageous choice of local oscillator signal generation methods on chip is by PLL out of band local oscillation and by direct synthesis for in band local oscillator.

Abstract: An integrated receiver with channel selection and image rejection substantially implemented on a single CMOS integrated circuit is described. A receiver front end provides programmable attenuation and a programmable gain low noise amplifier. Frequency conversion circuitry advantageously uses LC filters integrated onto the substrate in conjunction with image reject mixers to provide sufficient image frequency rejection. Filter tuning and inductor Q compensation over temperature are performed on chip. The filters utilize multi track spiral inductors. The filters are tuned using local oscillators to tune a substitute filter, and frequency scaling during filter component values to those of the filter being tuned. In conjunction with filtering, frequency planning provides additional image rejection. The advantageous choice of local oscillator signal generation methods on chip is by PLL out of band local oscillation and by direct synthesis for in band local oscillator.

Abstract: An integrated receiver with channel selection and image rejection substantially implemented on a single CMOS integrated circuit is described. A receiver front end provides programmable attenuation and a programmable gain low noise amplifier. Frequency conversion circuitry advantageously uses LC filters integrated onto the substrate in conjunction with image reject mixers to provide sufficient image frequency rejection. Filter tuning and inductor Q compensation over temperature are performed on chip. The filters utilize multi track spiral inductors. The filters are tuned using local oscillators to tune a substitute filter, and frequency scaling during filter component values to those of the filter being tuned. In conjunction with filtering, frequency planning provides additional image rejection. The advantageous choice of local oscillator signal generation methods on chip is by PLL out of band local oscillation and by direct synthesis for in band local oscillator.

Abstract: An electrochemical sensor for organic molecules such as ethylene includes an electrochemical cell, gas sample inlet means and means for detecting current produced by the oxidation of the organic molecule at the anode of the cell. The sensor is capable of sensing multiple organic molecules in some embodiments. A voltage is applied to the anode of the cell to provide energy to drive the oxidation reaction and produce a corresponding current. The sensor of the invention can be made as a small, hand-held unit that is capable of real-time detection of various organic species.