System and method for fast evaluation of standing queries in conjunctive normal form

Patent metadata

Field	Value
Publication number	US-10423883-B2
Application number	US-201514821245-A
Country	US
Kind code	B2
Filing date	Aug 7, 2015
Priority date	Mar 8, 2012
Publication date	Sep 24, 2019
Grant date	Sep 24, 2019

Abstract

Methods and systems are provided for evaluating standing queries against updated contact entries configured as a stream of facts. The method includes resolving the standing queries into an array of rules, each rule having a first and a second condition; sorting one of the facts into a first property and a second property; comparing the first property of the fact to the first condition of each rule in the array of rules to produce a first subset of matching rules; comparing the second property of the fact to the second condition of each rule in the first subset of rules to produce a second subset of matching rules; and reporting at least one of the second subset of rules to an author of the matching rule. The method further includes populating a first hash with indicia of the first subset, and populating a second hash with the second subset.

First claim

What is claimed is:

1. A computer-implemented method of evaluating computer database queries, the method comprising:
resolving by a data processor the queries of business contact entries in a database into a set of rules, each rule comprising conditions;
sorting by the data processor, for each rule, the conditions into a logical order;
identifying by the data processor a fact having a plurality of properties sorted in the logical order, wherein the identifying includes selecting the fact from the database of the business contact entries that represent user data of the business contact entries;
evaluating by the data processor the fact against each rule, wherein the evaluating comprises comparing the fact to each rule using hash tables, and further comprises using a second property associated with the fact as a key into a hash table to return a second set of rules; and
identifying by the data processor a subset of the set of rules which match the fact.

2. The method of claim 1 , wherein the database queries are standing queries in conjunctive normal form.

3. The method of claim 1 , wherein the logical order is lexicographical.

4. The method of claim 1 , wherein the resolving comprises reducing at least one clause in a query from a disjunction of literals to a single literal.

5. The method of claim 1 , wherein the fact comprises N properties and each rule comprises up to N conditions, where N is an integer.

6. The method of claim 1 , wherein the conditions and the properties include at least two of: city; last name; first name; country; company; zip code; and title.

7. The method of claim 1 , wherein a first property is used as a key into a first hash table to return a first set of rules.

8. The method of claim 1 , wherein the evaluating comprises creating a high level hash table representing first evaluation results.

9. The method of claim 8 , wherein the evaluating comprises creating at least one secondary hash table representing second evaluation results.

10. A computer-implemented method of evaluating computer database queries, the method comprising:
resolving by a data processor the queries of business contact entries in a database into rules, each rule comprising conditions;
sorting by the data processor, for each rule, the conditions into a logical order;
identifying by the data processor a fact having a plurality of properties sorted in the logical order, wherein the identifying includes selecting the fact from the database of the business contact entries that represent user data of the business contact entries, wherein the evaluating comprises comparing the fact to each rule using hash tables;
evaluating by the data processor the fact against each rule;
identifying by the data processor a subset of the rules which match the fact; and
reporting by the data processor the identified subset.

11. The method of claim 10 , wherein the database queries are standing queries in conjunctive normal form.

12. The method of claim 10 , wherein the reporting comprises notifying an author of one of the rules in the subset.

13. The method of claim 10 , wherein the reporting comprises posting at least one of the rules of the subset on a website accessible by an author of the posted rule.

14. A computer-implemented method of evaluating computer database queries in conjunctive normal form against a fact having properties sorted in a logical order, the queries comprising a plurality of conditions sorted into a logical order, the method comprising:
comparing by a data processor a first property of the fact to queries of business contact entries in a database in a first level table;
returning by the data processor a second level table of queries, based on the comparing;
comparing by the data processor a second property of the fact to queries of the business contact entries in the database in both the first level table and the second level table;
identifying by the data processor a subset of the queries that match the fact; and
reporting by the data processor the subset.

Assignees

• Salesforce Com Inc

Inventors

• Fuchs Matthew

Classifications

• G06Q10/00 Primary

  Administration; Management · CPC title

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• G06N5/046 Primary

  Forward inferencing; Production systems · CPC title

• G06N5/04

  Inference or reasoning models · CPC title