Generative Language Model for Database Campaign Brief Generation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing database systems face challenges in efficiently generating and executing campaigns based on the large amount of unstructured customer relations management data, which is time-consuming and lacks effective solutions for improving campaign decisions.

Innovation Solution

The implementation of a machine learning subsystem within an on-demand database system that processes data to determine campaign recommendations, generates campaign briefs, and refines them based on user input and experimental data, utilizing a generative language model to create campaign assets and messages.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual processes are used to analyze customer data and develop campaigns, then decision-making control is maintained, but the process is time-consuming and inefficient

Engineering Contradiction:

Improvecampaign development speedVSAvoidtime for manual data analysis

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

A machine learning subsystem acts as an intermediary between the database system and users, automatically analyzing customer data and generating campaign recommendations. This intermediary handles the time-consuming analysis work while presenting refined options to users for final decision-making.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

Manual mechanical processes of data analysis and campaign development are replaced with automated machine learning algorithms. The system substitutes human analysts with computational models that can process large datasets much faster and identify patterns that would be difficult for humans to detect.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If more manual decisions are required for campaign creation, then control and customization are improved, but the complexity and time consumption increase

Engineering Contradiction:

Improveease of campaign creationVSAvoidcomplexity of campaign decision process

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The machine learning subsystem performs self-service by automatically analyzing customer data, identifying campaign opportunities, and generating recommended campaigns without requiring extensive manual intervention. Users simply review and select from pre-generated options rather than creating campaigns from scratch.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary actions by pre-analyzing customer data and pre-generating multiple campaign options before user interaction. This preliminary work reduces the complexity of the user's decision-making process, as they only need to evaluate pre-prepared recommendations rather than conduct their own analysis.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If conventional techniques are used for campaign creation, then simplicity is maintained, but solutions for improving campaign decisions are limited

Engineering Contradiction:

Improveability to improve campaign decisionsVSAvoidunstructured data utilization

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system changes parameters by transforming unstructured customer data into structured insights through machine learning analysis. It alters the state of raw data by applying computational models that extract meaningful patterns, enabling better campaign decisions based on previously unusable information.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The machine learning subsystem serves as an intermediary that bridges the gap between unstructured customer data and actionable campaign insights. It processes and transforms raw unstructured data into structured recommendations, making the information useful for campaign development without requiring manual interpretation.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20250086403A1Machine learning generation and refinement of group messaging in a database system via generative language modeling

Publication Date: 2025.03.13 SALESFORCE INC

AI summary

A computing services environment may include a database system, a generative language model interface, a communication interface, and a messaging interface. The database system may store database records reflecting interactions between tenants of the computer services environment and individuals interacting with the tenants, and may determine an input description of a communication campaign between a tenant of the plurality of tenants and a corresponding segment of the individuals. The generative language model interface may determine a textual description of one or more elements of the communication campaign by completing a campaign brief generation prompt via a generative language model. The communication interface may transmit to a client machine authenticated to a database system account linked to the tenant an instruction to generate a graphical user interface at the client machine. The messaging interface may transmit messages based on the input description and the refinement.