Abstract: Methods, systems, and apparatus, including computer-readable media, for artificial intelligence enhancements for document interfaces. In some implementations, a system receives data indicating a user interaction of a user at a user interface that displays a document. In response, the system determines a scope of data corresponding to a particular portion of the document. The system retrieves data for the determined scope corresponding to the particular portion of the document. The system performs one or more analysis processes on the retrieved data to generate analysis results for the retrieved data. The system sends a request to one or more artificial intelligence and/or machine learning (AI/ML) models, wherein the request comprises (i) at least a portion of the retrieved data, (ii) the analysis results, and (iii) a predetermined instruction. The system provides text generated by the one or more AI/ML models for presentation in the user interface with the document.

Abstract: Methods, systems, and apparatus, including computer-readable media, for using artificial intelligence models to detect and mitigate ambiguity in natural language text. In some implementations, a system receives a text input from a user. The system classifies the text input as containing an ambiguity. Based on classifying the text input as containing an ambiguity, the system sends (i) a response to the text input generated using a first interpretation or meaning and (ii) one or more alternative interpretations or meanings. The system receives data indicating user input that selects one of the one or more alternative interpretations, and in response the system sends a second response generated using the selected alternative interpretation or meaning.

Abstract: Methods, systems, and apparatus, including computer-readable media, for determining and revealing interpretations of artificial intelligence models. In some implementations, a system receives a prompt from a user. The system obtains code or instructions generated by a artificial intelligence or machine learning (AI/ML) model, where the code or instructions specify criteria to retrieve data from a data source to respond to the prompt. The system generates a set of results from the data source based on the generated code or instructions, and obtains a response to the prompt that an AI/ML model generates using at least a portion of the set of results. The system also generates an interpretation statement that indicates how the prompt was interpreted by the one or more AI/ML models. The system provides output that includes (i) the response to the prompt and (i) the generated interpretation statement.

Abstract: Methods, systems, and apparatus, including computer-readable media, for enhancing artificial intelligence chatbots with search functionality. In some implementations, a system stores a search index for data sets, where the search index describes data objects of the data sets and values for the data objects in the data sets. The system receives a user prompt to a chatbot and searches for data objects and values that are relevant to the user prompt, including using the search index to search for data objects and values of one or more data sets that the chatbot is configured to access. The system uses one or more results obtained using the search index to generate a chatbot response to the user prompt, including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model. The system provides the chatbot response as a response to the user prompt.

Abstract: A solenoid driver operable to drive a solenoid actuating a high-voltage power switch is disclosed. The solenoid driver includes a first group of semiconductor switches including a first semiconductor switch and a second semiconductor switch in series. This group is connected to a high-voltage supply line by a diode. The solenoid driver further includes a second group of semiconductor switches including a third semiconductor switch and a fourth semiconductor switch in series. This group is connected to the high-voltage supply line by a second diode. The solenoid driver further includes a common connection between the first group of semiconductor switches and the second group of semiconductor switches. A solenoid coil of the solenoid is connected between the first group of semiconductor switches and the second group of semiconductor switches at a junction between the first and second semiconductor switches and a junction between the third and fourth semiconductor switches.

Abstract: A system for determining and using a laboratory index for a laboratory is provided. The system includes a plurality of laboratory devices. The system also includes a plurality of sensors configured to obtain sensor data regarding operation of the plurality of laboratory devices or conditions in the laboratory. Additionally, the system includes a terminal including a screen, at least one processor, and at least one memory device. The memory device(s) include computer readable code configured, when executed, to cause the processor(s) to receive the sensor data, calculate the laboratory index based on the sensor data, and cause a graphical user interface to be presented on the screen with one or more fields comprising data related to the laboratory index.

Abstract: A solenoid driver operable to drive a solenoid actuating a high-voltage power switch is disclosed. The solenoid driver includes a first group of semiconductor switches including a first semiconductor switch and a second semiconductor switch in series. This group is connected to a high-voltage supply line by a diode. The solenoid driver further includes a second group of semiconductor switches including a third semiconductor switch and a fourth semiconductor switch in series. This group is connected to the high-voltage supply line by a second diode. The solenoid driver further includes a common connection between the first group of semiconductor switches and the second group of semiconductor switches. A solenoid coil of the solenoid is connected between the first group of semiconductor switches and the second group of semiconductor switches at a junction between the first and second semiconductor switches and a junction between the third and fourth semiconductor switches.

Abstract: A power supply system is operable to harvest power at low and high line currents. A current transformer is arranged to couple to a power transmission line. A current sensor which may be a Rogowski coil is arranged to couple to the power transmission line. Branches of power supply circuitry are connected to a plurality of secondary windings of the current transformer. A control circuit selects one of the branches of power supply circuitry, depending on sensed magnitude of line current, to provide electrical power to an output capacitor. Sufficient stored energy is also provided for performing a backup of operating parameters when the line current reduces to zero.

Abstract: A computer-implemented method for computing or modeling the risk of a cyber security breach to an asset begins by gathering coverage information from network sensors, endpoint agents, and decoys related to the asset, as well as gathering importance information related to the asset, alerts and anomalies from an enterprise and vulnerability information related to the asset. From this, a threat-score is computed for the asset. Connections or coupling information is gathered between users and assets, users and data, and assets and data, which is fused to generate a 3-dimensional vector representation of coverage, importance, and threat-score of the assets, users and data. From this 3-dimensional vector, an asset risk score is computed to provide the asset risk score.

Abstract: The disclosed invention provides a system on a cloud-hosted containers or containerized environment for performing complex modeling and analytics on big data that allows the analytics performed in it are reproducible at any time despite changes to the cloud ecosystem. The cloud-hosted, future-proofed containers allows previously completed analytics, data, research, publications, websites, etc., to be future proofed by detecting pending or proposed changes to the cloud ecosystem and updating projects automatically to be reproducible in the future ecosystem.

Abstract: A power supply system is operable to harvest power at low and high line currents. A current transformer is arranged to couple to a power transmission line. A current sensor which may be a Rogowski coil is arranged to couple to the power transmission line. Branches of power supply circuitry are connected to a plurality of secondary windings of the current transformer. A control circuit selects one of the branches of power supply circuitry, depending on sensed magnitude of line current, to provide electrical power to an output capacitor. Sufficient stored energy is also provided for performing a backup of operating parameters when the line current reduces to zero.

Abstract: A computer-implemented method for computing or modeling the risk of a cyber security breach to an asset begins by gathering coverage information from network sensors, endpoint agents, and decoys related to the asset, as well as gathering importance information related to the asset, alerts and anomalies from an enterprise and vulnerability information related to the asset. From this, a threat-score is computed for the asset. Connections or coupling information is gathered between users and assets, users and data, and assets and data, which is fused to generate a 3-dimensional vector representation of coverage, importance, and threat-score of the assets, users and data. From this 3-dimensional vector, an asset risk score is computed to provide the asset risk score.

Abstract: An apparatus and method are provided for measuring the physical strength and ability of a solid sample, to resist breakdown into fines after repeated cycles of hydration and regeneration of temperatures in excess of 100° C. The test samples are evaluated using an accelerated degradation apparatus that subjects the sample to a predetermined number of timed cycles of wetting/drying under heat and vacuum, and the weight-percent of any fines produced by the degradation of the sample are measured and recorded after a prescribed number of cycles. Specific values are used for predicting potential useful service life, in years of samples from different commercial manufacturers of the same class of product; the resulting data can be used by manufacturers for more effective quality control of production batches.

Abstract: An apparatus and method are provided for measuring the physical strength and ability of a solid sample, to resist breakdown into fines after repeated cycles of hydration and regeneration of temperatures in excess of 100° C. The test samples are evaluated using an accelerated degradation apparatus that subjects the sample to a predetermined number of timed cycles of wetting/drying under heat and vacuum, and the weight-percent of any fines produced by the degradation of the sample are measured and recorded after a prescribed number of cycles. Specific values are used for predicting potential useful service life, in years of samples from different commercial manufacturers of the same class of product; the resulting data can be used by manufacturers for more effective quality control of production batches.

Abstract: An apparatus and method are provided for measuring the physical strength and ability of a solid sample, to resist breakdown into fines after repeated cycles of hydration and regeneration of temperatures in excess of 100° C. The test samples are evaluated using an accelerated degradation apparatus that subjects the sample to a predetermined number of timed cycles of wetting/drying under heat and vacuum, and the weight-percent of any fines produced by the degradation of the sample are measured and recorded after a prescribed number of cycles. Specific values are used for predicting potential useful service life, in years of samples from different commercial manufacturers of the same class of product; the resulting data can be used by manufacturers for more effective quality control of production batches.