Situational Analysis for E-commerce User Personalization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

E-commerce platforms face challenges in understanding and personalizing user experiences due to the anonymity of internet users, as traditional marketing techniques based on customer targeting and differentiation are not applicable, and existing data processing methods provide only a partial understanding of users, relying on limited behavioral data.

Innovation Solution

A data processing method that analyzes 'situations' of users connected to a platform, using triggers to identify situational indices and generate situational signatures, allowing for prediction and personalization without relying on physical or logical models, and employing situational analysis processors to adapt and focus on essential data, enabling more comprehensive user understanding and personalized content delivery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional marketing techniques based on customer targeting and differentiation are used, then customer personalization can be achieved, but the anonymity of internet users prevents effective application of these techniques

Engineering Contradiction:
Improvecustomer personalizationVSAvoiduser anonymity
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent introduces 'situational indices' as an intermediary that mediates between user anonymity and personalization needs. Instead of directly identifying users through personal information, the system observes and analyzes situational data (behavioral patterns, context, interactions) that indirectly reveal user characteristics and preferences, enabling personalization without compromising anonymity

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional mechanical identification methods (collecting personal information, user profiles) with a situational analysis system that infers user characteristics through observation of behavioral patterns and contextual data, substituting direct identification with indirect inference based on situational context

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If behavioral data collection methods are used to identify users, then partial understanding of users can be achieved, but only a small amount of information can be deduced

Engineering Contradiction:
Improveuser understandingVSAvoidinformation quantity
Core Design Contradiction:
Loss of informationVSQuantity of substance

Solution Approach 1:

The patent segments user understanding into multiple situational indices (contextual factors, behavioral patterns, interaction characteristics) rather than relying on a single unified user profile. This segmentation allows the system to capture and analyze diverse aspects of user behavior independently, extracting more information from the same data sources

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent adds dimensional depth to user understanding by introducing situational context as an additional dimension. Instead of analyzing user data in a single dimension (traditional behavioral metrics), the system incorporates contextual dimensions (time, location, device, situation type) that multiply the information extractable from the same behavioral data

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Measurement precision

If situational analysis processors are implemented to analyze complete situations, then deeper user understanding and prediction capabilities are achieved, but system complexity increases

Engineering Contradiction:
Improveuser understanding depthVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the complex situational analysis task into distinct components: situational indices identification, situation pattern recognition, and prediction modeling. This segmentation allows each component to be developed and optimized independently, managing system complexity while achieving deep user understanding through coordinated analysis of multiple situational dimensions

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP2880557B1Method of processing data regarding connection of a platform of an internet site
Publication Date: 2022.05.04 NETWAVE
  • EP2880557B1 patent drawingFigure 1
  • EP2880557B1 patent drawingFigure 2
  • EP2880557B1 patent drawingFigure 3

AI summary

The present invention relates to a method of processing data regarding connection to a platform (2) of an internet site by a server (1) comprising at least one data processing unit and data storage means, the method being characterized in that it comprises steps of: (a) identification of a situation of a user connected to said platform (2) via an item of equipment (3) from among a list of reference situations, each reference situation being associated with at least one strategy, each strategy comprising one or more situational engines chosen from among a library of situational engines, each situational engine being able to implement a given processing on a situation of a user so as to obtain a message having a hoped-for effect on the situation; (b) for at least one of the strategies associated with said identified situation, implementation by the data processing means of the server (1) of the situational engines of said strategy on said situation so as to obtain at least one stack of messages; (c) dispatching to the item of equipment (3) of said user and/or of the platform (2) of a subset of messages of said at least one stack of messages.