O9 Solutions, Inc.

Siddarth Wardhan

Rajeev Karri

Amit Agarwal

Smera George

Vikram Kulkarni

Koustuv Chatterjee

Devaraya Prabhu

Systems and techniques for protocol buffer trie packing and streaming updates are described herein. Data entities are identified in a received update query. An index value is assigned to each unique data entity to generate an index of unique data entities. A frequency of occurrence value is determined for each unique data entity. The index of unique data entities is sorted by data entity type in descending order by the frequency of occurrence value of each unique data entity. A trie is generated with a root node assigned as a first unique data entity from the index of unique data entities that has a frequency of occurrence value with the largest numerical value. An update payload is created for the trie by conversion of the trie into a protocol buffer format through serialization of the trie into a binary string.

Protocol buffer trie packing and streaming updates

Systems and techniques for a computational unified graph hierarchy model are disclosed herein. A set of source data may be received that may include entity data and relationship data. An entity may be identified in the entity data. A hierarchy may be determined for the entity. An entity graph network may be generated. A non-hierarchical link between the entity and a related entity may be determined. The entity graph network may be updated to include the non-hierarchical link. A set of measures may be generated for a relational link of the entity. A dependency may be configured between the set of measures for the relational link and a second set of measures of a second relational link. A change may be identified to a value of a measure and a dependent entity node measure value may be updated based on a computational effect of the change to the value.

Computational unified graph hierarchy model

Systems and techniques for protocol buffer trie packing and streaming updates are described herein. Data entities are identified in a received update query. An index value is assigned to each unique data entity to generate an index of unique data entities. A frequency of occurrence value is determined for each unique data. entity. The index of unique data entities is sorted by data entity type in descending order by the frequency of occurrence value of each unique data entity. A trie is generated with a root node assigned as a first unique data entity from the index of unique data entities that has a frequency of occurrence value with the largest numerical value. An update payload is created for the trie by conversion of the trie into a protocol buffer format through serialization of the trie into a binary string.

A proposed modification to a record of a base data structure is identified, the records of the base data structure sorted by primary key. A type of modification of the proposed modification is identified. A record is added to a differential data structure of the type, the differential data structure record describing the proposed modification. A record is added to a delta data structure sorted by the primary key, the delta data structure record including the primary key value of the record, the type of the proposed modification, and a pointer to the record added to the differential data structure. Data can be fetched using the delta data structure to apply modifications to a set of records requested in the fetch and generate a modified set of records to be returned in a response to the request.

Growing community of inventors

Bengaluru, India

Siddarth Wardhan