Item Selection Apparatus Balancing User Preference and Sales Policy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing recommendation technologies tend to be biased towards seller's sales policies, leading to unattractive and potentially overwhelming recommendations for users, resulting in decreased user acceptance and distrust.
Innovation Solution
An item selecting apparatus and method that calculates user characteristic values based on preference degrees and recommended item conditions, allowing for a balanced selection of items that align with both user taste and seller sales policy, while avoiding excessive bias towards the sales policy, by using a favorite item set, rate calculation sections, and user characteristic value calculations to determine optimal item sets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all recommended goods are accorded with the sales policy of the seller, then the seller's sales policy is fulfilled, but the user feels high-pressure selling and distrust, reducing acceptance
Solution Approach 1:
The patent changes the parameter of recommendation composition by controlling the ratio of policy-accommodating items to user-preferred items. The recommendation control section adjusts this ratio dynamically based on user characteristics, transforming the recommendation system from purely policy-driven to a balanced approach that maintains policy fulfillment while improving user acceptance through parameter optimization.
Solution Approach 2:
The system dynamically adjusts the composition of recommended items based on user characteristics and behavior patterns. The recommendation control section modifies the ratio of policy-compliant items versus user-preferred items in real-time, making the recommendation system adaptive rather than static, thereby resolving the contradiction between policy fulfillment and user acceptance.
2Reliability
If recommendation information is biased toward particular goods and fields according to sales policy, then seller's sales policy is supported, but the recommendation becomes unattractive to users
Solution Approach 1:
The patent applies local quality by differentiating the treatment of different item types in recommendations. Policy-accommodating items and user-preferred items are mixed in specific ratios rather than uniformly applying one type. This localized differentiation in recommendation composition maintains sales policy alignment while enhancing attractiveness through diverse item selection.
Solution Approach 2:
The recommendation system creates a composite structure by combining policy-accommodating items and user-preferred items in controlled ratios. This composite recommendation set integrates both sales policy requirements and user attractiveness, similar to how composite materials combine different properties to achieve optimal performance.
3Reliability
If the rate of items satisfying recommended item conditions is increased in the result item set, then sales policy fulfillment is improved, but user distrust increases due to perceived aggressive peddling
Solution Approach 1:
The system applies partial action by not fully prioritizing policy-compliant items but rather incorporating them in controlled ratios alongside user-preferred items. This partial inclusion of policy items avoids the excessive action of overwhelming users with policy-driven recommendations, thereby reducing distrust while still fulfilling sales objectives.
Solution Approach 2:
The recommendation control section acts as an intermediary between sales policy requirements and user preferences. It mediates the conflict by balancing policy-compliant items with user-preferred items in optimized ratios, preventing the direct transmission of aggressive sales pressure to users while still achieving policy fulfillment.
Data Source
AI summary
A favorite item set making section makes a favorite item set. A first rate calculating section calculates, with respect to a first set of items, a first rate of the number of items satisfying recommended item conditions to the number of all items. A user characteristic value calculating section calculates a user characteristic value by using the first rate. An item selecting section selects, from items in the favorite item set, a plurality of items including items satisfying the recommended item conditions to make a result item set. When the user characteristic value satisfies prescribed conditions, the rate of the number of items in the result item set which satisfy the recommended item conditions to the number of all items in the result item set is greater than the first rate and smaller than 1 except for a case where the first rate is 1.