Thoughtspot, Inc.

Manikanta Balakavi

Rakesh Kothari

Ravi Tandon

Aditya Viswanathan

Amit Prakash

Ashish Shubham

Amitabh Singhal

Archit Bansal

Ajeet Singh

Ben Limonchik

Pavan Ram Piratla

Alonzo Canada

Maneesh Apte

Sandeep Kumar

Naresh Kumar

Tushar Mahale

Siva Singaram

Jasmeet Singh Jaggi

Rahul Paliwal

Performing, by a low-latency data access and analysis system, automatic grammar switching includes, in response to obtaining data indicating a request to switch from using a first defined grammar to using a second defined grammar, wherein the request includes data representing a first resolved-request generated for a first input string using the first defined grammar, generating, using the second defined grammar, a second resolved-request for the first input string, automatically generating a data-query in accordance with the second resolved-request, and outputting output data including results data obtained by executing the data-query.

Lossless switching between search grammars

Providing a search interface for a database includes receiving string data entered via a user interface. A sequence of tokens representative of the string data is determined. Determining the sequence of tokens includes applying natural language processing to the string data. A first database query is generated in accordance with the sequence of tokens. Respective text representations for tokens in the sequence of tokens are presented via the user interface. Feedback data related to the sequence of tokens is received via the user interface. A token of the sequence of tokens is modified based on the feedback data to obtain a modified sequence of tokens. A second database query is generated based on the modified sequence of tokens. Results data are obtained from the database responsive to execution of the second database query by the database. Data based on the results data are output for presentation in the user interface.

Natural language question answering systems

Systems and methods for conversational user experiences and conversational database analysis disclosed herein improve the efficiency and accessibility of low-latency database analytics. The method may include obtaining data expressing a usage intent with respect to the low-latency database analysis system, wherein the data expressing the usage intent includes a current request string expressed in a natural language, a current context associated with the current request string, and a previously generated context associated with a previously generated resolved-request, identifying, from the current request string, a conversational phrase corresponding to a conversational phrase pattern from a defined set of conversational phrase patterns, generating a resolved-request based on the identified conversational phrase, including the resolved-request in the current context, obtaining results data responsive to the resolved-request from a distributed in-memory database, generating a response including the results data and the current context, and outputting the response.

Conversational database analysis

Intent-resolution using a phrase index may include obtaining data expressing a usage intent, the data expressing the usage intent including an unresolved data portion, identifying a phrase fragment based on the data expressing the usage intent and a defined phrase pattern, the phrase fragment including the unresolved data portion, identifying, by a processor, an indexed phrase as a candidate phrase by searching a phrase index based on the phrase fragment, wherein the candidate phrase at least partially matches the phrase fragment in accordance with the defined phrase pattern, and outputting the candidate phrase for presentation to a user as a candidate for resolving the unresolved portion.

Phrase indexing

A method and system may be implemented for automatically analyzing data in a database. A method for use in a low-latency database analysis system may include generating a schema. The schema may be based on a portion of an external database. The method may include storing the schema in an in-memory database. The method may include receiving a data-query. The method may include generating a resolved-request. The resolved-request may be based on the data-query and the stored schema. The stored schema may be used for executing the query on the external database. The method may include receiving results data responsive to the data-query from the external database. The method may include outputting the results data for display on a user interface.

Low-latency database analysis using external data sources

Lossless switching between search grammars is described herein. A method may include generating a first resolved-request using a relational search grammar in response to receiving a request for data, where the first resolved-request includes an ordered sequence of tokens, and in response to receiving a request for data indicating the first resolved-request and indicating a request to use a natural language search grammar, generating a second resolved-request in accordance with the natural language search grammar by identifying tokens and token binding data associated with the relational search grammar resolved-request as query refinements, generating the second resolved-request consistent with the first resolved-request by tokenizing the request for data associated with the natural language search grammar in accordance with the natural language search grammar using the query refinements, and outputting search results obtained using the request for data associated with the natural language search grammar using the natural language search grammar.

Systems and methods for natural language question answering are described. For example, methods may include determining a set of candidate database queries, including respective sequences of tokens of a database syntax, based on a string; determining a first score for a first candidate database query from the set of candidate database queries, wherein the first score is based on a match between one or more words of the string and a token of the respective sequence of tokens of the first candidate database query; determining a second score for the first candidate database query, wherein the second score is based on natural language syntax data determined for words of the string; selecting, based on the first score and the second score, the first candidate database query from the set of candidate database queries; and invoking a search of the database using the first candidate database query to obtain search results.

Intent-resolution using a phrase index may include obtaining data expressing a usage intent, the data indicating an unresolved data portion, identifying a phrase fragment based on the data expressing the usage intent and a phrase pattern, the phrase fragment including the unresolved data portion, identifying candidate tokens, identifying candidate phrases by traversing a phrase index based on the phrase fragment, wherein identifying the candidate phrases includes, in response to a determination that the phrase index includes an indexed phrase at least partially matching the phrase fragment in accordance with the phrase pattern, the indexed phrase is identified as one of the candidate phrases, identifying candidate resolved-requests, weighting and sorting the candidate tokens, the candidate phrases, and the candidate resolved-request, to obtain sorted candidate resolutions, and outputting one or more of the sorted candidate resolutions for presentation to a user as respective candidates for resolving the unresolved data portion.

Growing community of inventors

Mountain View, CA, United States of America

Manikanta Balakavi