Client Device Content Re-ranking via Session Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional techniques fail to provide a satisfactory user experience for mobile devices with weak network connections, as users may run out of new content and have to manually request updates, leading to a poor online system experience and potential loss of user base.

Innovation Solution

A client device re-ranks content items based on session-specific information, such as viewing frequency and speed, to provide a more up-to-date order, even when the online system lacks real-time access to this information due to unreliable network connections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If content items are ranked by the online system and downloaded to the mobile device, then the user has access to new content items, but if the network connection is weak or unreliable, the user may run out of new content and cannot receive updates in a timely manner

Engineering Contradiction:

Improvequantity of new content itemsVSAvoidreliability of network connection

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The system performs preliminary ranking of content items on the online system before download, creating a pre-ordered set that can be downloaded in advance. This allows content to be prepared and staged for download before the user actually needs it, reducing the impact of unreliable network connections during peak usage times.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamic re-ranking of content items based on user interactions and session-specific information after download. The ordered set is not static but dynamically adjusted as the user views and interacts with content, ensuring that the most relevant items remain accessible even when network updates are delayed or fail.

Inventive Principle:

Principle #15Dynamics

2Measurement precision

If the online system ranks content items based on available information, then the ranking is optimized for general user preferences, but it lacks real-time session-specific information from the client device

Engineering Contradiction:

Improveprecision of rankingVSAvoidloss of session-specific information

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent segments the ranking process into two parts: initial ranking by the online system based on general user preferences and profile data, and subsequent local re-ranking by the client device based on session-specific information. This segmentation allows each system to utilize the information most available to it, combining global and local context for optimized ranking.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The ordered set of content items acts as an intermediary between the online system and the user interface. It carries ranking information from the online system and allows local modification based on session data, serving as a buffer that reconciles the information gap between server-side and client-side ranking capabilities.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If users manually request new content items, then they can receive updates, but it requires user intervention and waiting time, degrading user experience

Engineering Contradiction:

Improvecontent update frequencyVSAvoidease of content access

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The system implements automatic content delivery mechanisms where the client device can autonomously request and receive new content items based on predefined triggers or schedules, without requiring manual user intervention. The ordered set is automatically replenished from the online system, making the content update process self-service and transparent to the user.

Inventive Principle:

Principle #25Self-service

4Adaptability or versatility

If the client device re-ranks content items based on session information, then the ordering is more up-to-date and relevant, but it requires additional processing and storage capacity on the device

Engineering Contradiction:

Improveadaptability of content orderingVSAvoidcomplexity of ranking mechanism

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The client device performs partial re-ranking of the ordered set based on session-specific information, focusing computational resources on adjusting the ranking of items most likely to be viewed based on current user behavior patterns. This partial action approach provides adaptive ranking benefits while limiting the computational overhead compared to complete re-ranking of all content items.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS10204166B2Ranking content items based on session information

Publication Date: 2019.02.12 META PLATFORMS INC

AI summary

An online system provides a continuous feed of content items to a client device. The online system maintains an ordered set of ranked content items for sending to the client device. The online system receives requests from the client device for content items and selects a subset from an ordered set of ranked content items in response to each request. The number of content items in the subset may be based on factors such as the network connection strength of the client device. The client device re-ranks content items received from the online system based on information received during a given session. The session information may indicate the types of content items viewed during the given session, or the speed at which the user is viewing content items during the given session.