Intelligent Terminal Target Identification Using Segmented Time Windows

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Intelligent terminals face a challenge in balancing the timeliness and detail of target recognition, as they often need to sacrifice timeliness for detailed identification results, which is not conducive to human-machine interaction experiences.

Innovation Solution

A target identification method that uses information acquired within a predetermined time period as judgment information, prioritizing attribute types for identification, and continuously acquiring information if the initial result is not the most detailed, allowing for timely and progressively more detailed identification outputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the intelligent terminal acquires and analyzes more information to improve identification detail, then the detail degree of identification result is improved, but the time consumption increases and timeliness deteriorates

Engineering Contradiction:
Improvedetail degree of identification resultVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The identification process is segmented into multiple time periods (first predetermined time period, second predetermined time period, etc.). In each segment, the terminal acquires information within that specific time window and performs identification. This segmentation allows the system to provide identification results at different detail levels at different time points, rather than requiring all information to be collected before any identification can occur.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The terminal performs preliminary identification actions using information acquired within each predetermined time period before all information is fully collected. By outputting identification results progressively as information becomes available, the system provides timely preliminary results while continuing to gather more information for potentially more detailed future identification.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If the intelligent terminal outputs identification result within a limited time, then timeliness is improved, but the detail degree of identification result deteriorates

Engineering Contradiction:
Improvetimeliness of identification outputVSAvoiddetail degree of identification result
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The terminal performs periodic identification actions at predetermined time intervals. Instead of a single identification attempt, the system repeatedly acquires information and performs identification at regular time periods, allowing it to balance timely output with progressive improvement in identification detail as more information becomes available over time.

Inventive Principle:
Principle #19Periodic action

3Measurement precision

If the intelligent terminal continuously acquires information to improve identification detail, then the detail degree is improved, but the operation complexity increases

Engineering Contradiction:
Improvedetail degree of identification resultVSAvoidoperation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The terminal dynamically adjusts its information acquisition and identification process based on the attribute types and their priorities. The system flexibly determines whether to continue acquiring information in subsequent time periods based on whether the current identification result achieves the highest priority attribute type, allowing adaptive complexity management rather than rigid continuous acquisition.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS11036990B2Target identification method and apparatus, and intelligent terminal
Publication Date: 2021.06.15 CHONGQING XINGJIE SHUXING TECHNOLOGY PARTNERSHIP ENTERPRISE (LLP)
  • US11036990B2 patent drawing
  • US11036990B2 patent drawing
  • US11036990B2 patent drawing

AI summary

A target identification method includes: using information of a to-be-detected target acquired within a predetermined time period as judgment information; acquiring an identification result of the to-be-detected target at a current time and outputting the identification result; judging whether the attribute type corresponding to the identification result is an attribute type having the highest priority; and if the attribute type corresponding to the identification result is not the attribute type having the highest priority, using information of the to-be-detected target acquired within a next predetermined time period as the judgment information, and returning to the step of acquiring an identification result of the to-be-detected target at a current time and outputting the identification result.