Abstract: Implementations relate to reducing latency in generating and/or rendering natural language (NL) output generated using a large language model (LLM). Processor(s) of a system can: receive NL based input associated with a client device, and generate the NL based output utilizing the LLM. The NL based output can be a stream of NL based output in that it includes a plurality of segments, and is generated on a segment-by-segment basis. In some implementations, a first segment of the stream of NL based output is selected for inclusion in the stream of NL based output as a second segment (and any subsequent segment) is being generated to reduce latency in evaluating the NL based output as a whole prior to rendering thereof. In some versions of those implementations, the first segment is rendered as the second segment (and any subsequent segment) is being generated to further reduce latency in rendering thereof.

Abstract: A system for enabling testing a target data pipeline within a graphical user interface (GUI) is disclosed. The system is programmed to present a GUI. The GUI shows a data pipeline including data transforms that are related based on data dependencies as a graph. The GUI then accept user inputs to identify a target pipeline from the data pipeline and set up a test for the target pipeline. The user inputs include interacting with the graph and providing test inputs and expected outputs for the target data pipeline, including specifying in each expected output for a test output one or more assertions related to the test output. The GUI further accepts user inputs to execute the test and review test results. The GUI facilitates specifying rich assertions, determining the source of a test failure, and updating the target data pipeline or the test based on the test results.

Abstract: Systems, methods, and computer-readable media for constraint-based itinerary generation in a ride-sharing service are disclosed. Drivers in the ride-sharing service may execute itineraries that include legs, where each leg is defined by a start point and a stop point. The itineraries may be generated in real time in response to ride requests, traffic conditions, and the like. A number of itinerary variations may be generated. Ride requests may include ride tags upon which a ride constraint may be defined. Vehicles may be compared to the ride constraint to determine whether the vehicle satisfies the ride constraint. Vehicles that do not satisfy the ride constraint may be removed from consideration when generating the itineraries, thereby constraining the search space in determining an optimal itinerary.

Abstract: Systems, methods, and computer-readable media for constraint-based itinerary generation in a ride-sharing service are disclosed. Drivers in the ride-sharing service may execute itineraries that include legs, where each leg is defined by a start point and a stop point. The itineraries may be generated in real time in response to ride requests, traffic conditions, and the like. A number of itinerary variations may be generated. Ride requests may include ride tags upon which a ride constraint may be defined. Vehicles may be compared to the ride constraint to determine whether the vehicle satisfies the ride constraint. Vehicles that do not satisfy the ride constraint may be removed from consideration when generating the itineraries, thereby constraining the search space in determining an optimal itinerary.

Abstract: Implementations relate to dialog management of a large language model (LLM) utilized in generating natural language (NL) output during an ongoing dialog. Processor(s) of a system can: receive NL based input as part of the ongoing dialog, generate NL based output utilizing the LLM, and cause the NL based output to be rendered. Further, the processor(s) can receive subsequent NL based input as part of the ongoing dialog. In some implementations, the processor(s) can determine whether to modify a corresponding dialog context in generating subsequent NL based output, and modify the corresponding dialog context accordingly. For example, the processor(s) can restrict the corresponding dialog context, or supplant the corresponding dialog context with a corresponding curated dialog context. In additional or alternative implementations, the processor(s) can modify a corresponding NL based output threshold utilized in generating the subsequent NL based response to ensure the resulting NL based output is desirable.

Abstract: Implementations relate to dialog management of a large language model (LLM) utilized in generating natural language (NL) output during an ongoing dialog. Processor(s) of a system can: receive NL based input as part of the ongoing dialog, generate NL based output utilizing the LLM, and cause the NL based output to be rendered. Further, the processor(s) can receive subsequent NL based input as part of the ongoing dialog. In some implementations, the processor(s) can determine whether to modify a corresponding dialog context in generating subsequent NL based output, and modify the corresponding dialog context accordingly. For example, the processor(s) can restrict the corresponding dialog context, or supplant the corresponding dialog context with a corresponding curated dialog context. In additional or alternative implementations, the processor(s) can modify a corresponding NL based output threshold utilized in generating the subsequent NL based response to ensure the resulting NL based output is desirable.

Abstract: A system may use a large language model (“LLM”) to generate a data pipeline. The system can receive a natural language query and a selection of a plurality of data sets for generating a data pipeline and generate a prompt comprising at least: the natural language query, indications of the plurality of data sets, an indication of a format of a first computer language, and an indication of available data transformations. The system can transmit the prompt to an LLM and receive, from the LLM, a response to the prompt in the format of the first computer language. The system can parse the response in the first computer language to identify at least an indication of one or more recommended data transformations. The system can generate, based on the indication of the one or more recommended data transformations, the data pipeline using a second computer language.

Abstract: Disclosed herein are system, method, and computer program product embodiments for a customer records management translation extension. A computer system receives customer data comprising a first name, last name, an email address, and a phone number from a front-end interface of an agent workstation. Based on the customer data, the computer system obtains one or more customer objects from a customer object database, wherein each of the customer object comprises a customer identifier. The computer system selects the customer object that best matches the customer data and obtains a customer lead identifier from the customer object database that corresponds to the customer identifier of the selected customer object. Based on the customer lead identifier, the computer system obtains a lead object from a lead object database and generates a link to the lead object. Finally, the computer system transmits the link to the front-end interface of the agent workstation.

Abstract: Systems and methods for dynamically scheduling breaks for drivers in a ride-sharing service are disclosed. Driver breaks may be scheduled dynamically in the context of a ride-sharing service in which rides may be requested ad hoc and drivers are rerouted accordingly. An allocation system may optimize a drive itinerary to service passengers requesting rides and breaks for drivers. A break request comprising break parameters may be received. The allocation system may attempt an insertion of the break request into the drive itinerary. The drive itinerary may then be validated to determine if all rides can be serviced with the break request entered into the itinerary. If the drive itinerary is not validated, the drive itinerary is modified until the break request is successfully inserted into the drive itinerary. The drive itinerary and driver breaks may be continuously modified and optimized in response to real time events and conditions.

Abstract: Implementations relate to reducing latency in generating and/or rendering natural language (NL) output generated using a large language model (LLM). Processor(s) of a system can: receive NL based input associated with a client device, and generate the NL based output utilizing the LLM. The NL based output can be a stream of NL based output in that it includes a plurality of segments, and is generated on a segment-by-segment basis. In some implementations, a first segment of the stream of NL based output is selected for inclusion in the stream of NL based output as a second segment (and any subsequent segment) is being generated to reduce latency in evaluating the NL based output as a whole prior to rendering thereof. In some versions of those implementations, the first segment is rendered as the second segment (and any subsequent segment) is being generated to further reduce latency in rendering thereof.

Abstract: Implementations relate to dialog management of a large language model (LLM) utilized in generating natural language (NL) output during an ongoing dialog. Processor(s) of a system can: receive NL based input as part of the ongoing dialog, generate NL based output utilizing the LLM, and cause the NL based output to be rendered. Further, the processor(s) can receive subsequent NL based input as part of the ongoing dialog. In some implementations, the processor(s) can determine whether to modify a corresponding dialog context in generating subsequent NL based output, and modify the corresponding dialog context accordingly. For example, the processor(s) can restrict the corresponding dialog context, or supplant the corresponding dialog context with a corresponding curated dialog context. In additional or alternative implementations, the processor(s) can modify a corresponding NL based output threshold utilized in generating the subsequent NL based response to ensure the resulting NL based output is desirable.

Abstract: Systems and methods for dynamically scheduling breaks for drivers in a ride-sharing service are disclosed. Driver breaks may be scheduled dynamically in the context of a ride-sharing service in which rides may be requested ad hoc and drivers are rerouted accordingly. An allocation system may optimize a drive itinerary to service passengers requesting rides and breaks for drivers. A break request comprising break parameters may be received. The allocation system may attempt an insertion of the break request into the drive itinerary. The drive itinerary may then be validated to determine if all rides can be serviced with the break request entered into the itinerary. If the drive itinerary is not validated, the drive itinerary is modified until the break request is successfully inserted into the drive itinerary. The drive itinerary and driver breaks may be continuously modified and optimized in response to real time events and conditions.

Abstract: Implementations relate to processing, utilizing a large language model (“LLM”), input that is based on sensor data, from sensor(s) of a client device, to generate LLM output—and causing output, that is based on the generated LLM output, to be rendered by an interactive chatbot. The input that is based on sensor data and that is processed by the LLM in generating the LLM output can be, or can include, non-acoustic input based on non-acoustic sensor data. For example, an instance of LLM output can be generated based on processing of non-acoustic input using the LLM and without any processing of acoustic input (that is based on acoustic sensor data) using the LLM. As another example, an instance of LLM output can be generated based on processing, using the LLM, both non-acoustic input that is based on non-acoustic data and acoustic input that is based on acoustic sensor data.

Abstract: Systems and methods for dynamically scheduling breaks for drivers in a ride-sharing service are disclosed. Driver breaks may be scheduled dynamically in the context of a ride-sharing service in which rides may be requested ad hoc and drivers are rerouted accordingly. An allocation system may optimize a drive itinerary to service passengers requesting rides and breaks for drivers. A break request comprising break parameters may be received. The allocation system may attempt an insertion of the break request into the drive itinerary. The drive itinerary may then be validated to determine if all rides can be serviced with the break request entered into the itinerary. If the drive itinerary is not validated, the drive itinerary is modified until the break request is successfully inserted into the drive itinerary. The drive itinerary and driver breaks may be continuously modified and optimized in response to real time events and conditions.

Abstract: Systems and methods for dynamically scheduling breaks for drivers in a ride-sharing service are disclosed. Driver breaks may be scheduled dynamically in the context of a ride-sharing service in which rides may be requested ad hoc and drivers are rerouted accordingly. An allocation system may optimize a drive itinerary to service passengers requesting rides and breaks for drivers. A break request comprising break parameters may be received. The allocation system may attempt an insertion of the break request into the drive itinerary. The drive itinerary may then be validated to determine if all rides can be serviced with the break request entered into the itinerary. If the drive itinerary is not validated, the drive itinerary is modified until the break request is successfully inserted into the drive itinerary. The drive itinerary and driver breaks may be continuously modified and optimized in response to real time events and conditions.

Abstract: Embodiments relate to systems and methods for electronically booking ride share trips. The systems and methods can involve a data storage device storing ride sharing records with itineraries including a plurality of legs. The systems and methods can involve at least one processor configured to receive a trip booking request for a passenger, the trip booking request defining passenger constraints including a desired pickup time or drop off time.

Abstract: Embodiments relate to systems and methods for electronically booking ride share trips. The systems and methods can involve a data storage device storing ride sharing records with itineraries including a plurality of legs. The systems and methods can involve at least one processor configured to receive a trip booking request for a passenger, the trip booking request defining passenger constraints including a desired pickup time or drop off time.

Abstract: Embodiments relate to systems and methods for electronically booking ride share trips. The systems and methods can involve a data storage device storing ride sharing records with itineraries including a plurality of legs. The systems and methods can involve at least one processor configured to receive a trip booking request for a passenger, the trip booking request defining passenger constraints including a desired pickup time or drop off time. The at least one processor is configured to generate trip booking options from available ride sharing itineraries, each trip booking option including a leg that satisfies the passenger constraints of the trip booking request. The at least one processor is configured to compute objective values for the trip booking options and remove at least one trip booking option based on a comparison of its objective value and temporal proximity to at least one other trip booking option.

Abstract: A metal pallet (1) having: a top deck (5), a bottom deck (10) and at least two elongate bearers (15) securing the decks (5, 10) together. Each bearer (15) having a first portion (16) and a second portion (17), each portion (16, 17) extends separately between the decks (5, 10) and has a top web (20) and a bottom web (25) connected to a central web (30) by inclined portions (35).

Abstract: Information analysing apparatus is described for clustering information elements in items of information into groups of related information elements. The apparatus has an expected probability calculator (11a), a model parameter updater (11b) and an end point determiner (19) for iteratively calculating expected probabilities using first, second and third model parameters representing probability distributions for the groups, for the elements and for the items, updating the model parameters in accordance with the calculated expected probabilities and count data representing the number of occurrences of elements in each item of information until a likelihood calculated by the end point determiner meets a given criterion.