Low-latency differential access controls in time-series prediction system

A technology for predicting systems and predicting actions, applied in transmission systems, file management systems, instruments, etc., can solve problems such as infeasibility of real-time applications

Pending Publication Date: 2021-05-18
GOOGLE LLC
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, having leaf servers communicate with an external authorization system introduces unacceptable latency into the process, especially when thousands of leaf servers need to serve thousands of requests per second
For example, if there are 1000 leaf servers that

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Low-latency differential access controls in time-series prediction system
  • Low-latency differential access controls in time-series prediction system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] Embodiment 1 is a method, comprising:

[0086] A query specifying a token corresponding to a search parameter is received from a requester by the root server of the prediction system, which is a request to the prediction system to calculate the user actions that are most likely to co-occur with the search parameter in documents, for each document includes data representing actions performed by a single corresponding user during a particular time period;

[0087] Obtain one or more permission action types of the requestor from the authorization server through the root server;

[0088] Obtain, via the root server, a plurality of predicted actions each co-occurring with the search parameter in at least one document, including:

[0089] through the root server, providing tokens to each of the plurality of leaf servers,

[0090] by each leaf server, searching the documents assigned to the leaf server with the search parameters corresponding to the tokens to determine one o...

Embodiment 2

[0094] Embodiment 2 is the method of embodiment 1, wherein obtaining, by the root server, a plurality of predicted actions each co-occurring with the search parameter in at least one document is at least in part related to obtaining from the authorization server one or more granted action types for the requestor executed concurrently.

Embodiment 3

[0095] Embodiment 3 is the method of any one of embodiments 1 to 2, wherein obtaining the requestor's one or more permission action types from the authorization server via the root server includes:

[0096] maintain a mapping between requestor identifiers and granted action types, by the authorization server; and

[0097] One or more grant action types are obtained by using the requester's requester identifier as input to the map.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing low-latency differential access controls in a distributed prediction system. One of the methods includes obtaining, by a root server from an authorization server, one or more permitted action types for a requester. A plurality of predicted actions that each co-occur in at least one document with a search parameter are obtained. Any actions having an action type that is not one of the one or more permitted action types for the requester is filtered from the plurality of predicted actions. One or more predicted actions having one of the permitted action types is provided to the requester.

Description

Background technique [0001] This specification relates to large-scale low-latency distributed computer systems, and more particularly to using distributed computer systems to search large data sets to generate real-time predictions of time-dependent user actions. [0002] A time-series forecasting system, or simply a forecasting system, is a distributed computer system that predicts user actions based on large-scale aggregation of time-series data. This allows real-time discovery of time-dependent actions and ranking them by likelihood. Such predictive systems can be used in a wide variety of practical applications. An example application is query suggestion. For example, given previous queries typed by a user of a search engine, a predictive system can predict the next query that user would like to type by discovering and ranking a large number of previous queries typed by other users related to the time of the previous query. For example, if a user types in the first quer...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/332G06F16/9032
CPCG06F16/3322G06F16/90324G06F16/93H04L63/10
Inventor 埃马努埃尔·塔罗帕
Owner GOOGLE LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products