Referral Object Processing for Annotated ML Corpora

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current database systems, such as those used in customer relationship management (CRM), fail to identify and incorporate external objects referenced by documents during search queries, limiting the relevance and accuracy of search results.

Innovation Solution

A neural network model is employed to process reference identifiers within documents, extracting information from external objects and adding textual annotations to the document corpus, enabling the search engine to consider these external references for enhanced user experience.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If search systems only search the text and content of the document, then the search system is simple to implement, but the search results lack relevance and accuracy regarding external referenced content

Engineering Contradiction:
Improvesearch result accuracyVSAvoidsearch system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary extraction of external object information and generates textual annotations before the search query is executed. The neural network model pre-processes documents by identifying reference identifiers, extracting external object data, and creating annotations that are stored with the document corpus, making external information readily available during search without adding complexity to the search execution phase

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces textual annotations as an intermediary layer between the document and the search system. These annotations contain extracted external object information and serve as a bridge, allowing the search system to access external referenced content without directly processing complex external objects during the search operation

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If external object information is incorporated into search results, then the comprehensiveness of search results is improved, but the processing time and number of iterations increase

Engineering Contradiction:
Improveinformation completenessVSAvoidsearch iteration time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system extracts external object information and generates textual annotations in advance, before the search query is submitted. This pre-processing approach ensures that when a search is executed, the external information is already integrated into the document corpus annotations, eliminating the need for additional processing iterations during the search phase

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11403457B2Processing referral objects to add to annotated corpora of a machine learning engine
Publication Date: 2022.08.02 SALESFORCE INC
  • US11403457B2 patent drawing
  • US11403457B2 patent drawing
  • US11403457B2 patent drawing

AI summary

A system is provided for referral object processing for textual annotations. The system comprises a memory storing machine executable code and one or more processors coupled to the memory and configurable to execute the machine executable code to cause the one or more processors to parse a document to identify a reference identifier to an external object, the external object associated with information not contained in the document, retrieve the external object using the reference identifier, extract the information associated with the external object based on at least one data pattern detected in the external object, convert the extracted information into textual annotations associated with the reference identifier in the document, and enter the textual annotations to a corpus of content for the document so that the extracted information is associated with the reference in the document for the system.