Server Caching Extracted Text for Real-Time Image Translation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing translation tools face challenges in translating character strings from images in real-time due to the time-consuming character recognition process, making real-time translation difficult.

Innovation Solution

A server system that caches extracted character information after initial recognition, allowing for rapid retrieval and translation without re-acquiring and re-processing images, using image ID information and specified parameters to associate and store recognized character strings for efficient output.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If character recognition processing is performed on images to translate character strings, then translation accuracy is improved, but processing time increases making real-time translation difficult

Engineering Contradiction:
Improvetranslation accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs character recognition processing in advance and stores the recognized character strings in a database. When a translation request is received, the system retrieves pre-recognized character strings from the database using image ID information, bypassing the time-consuming character recognition step and enabling real-time translation while maintaining accuracy.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If character recognition is performed every time an image translation is requested, then translation quality is maintained, but system productivity decreases

Engineering Contradiction:
Improvetranslation qualityVSAvoidsystem throughput
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system creates copies of recognized character strings and stores them in a database associated with image ID information. Subsequent translation requests utilize these stored copies rather than performing new character recognition, thereby maintaining translation quality while significantly increasing system throughput and reducing processing time.

Inventive Principle:
Principle #26Copying

3Measurement precision

If complete image processing is performed for each translation request, then translation accuracy is ensured, but resource consumption increases

Engineering Contradiction:
Improvetranslation accuracyVSAvoidprocessing resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs the computationally intensive character recognition processing in advance and stores results in a database. When translation requests are received, the system only performs lightweight database retrieval operations using image ID information, thereby ensuring translation accuracy while dramatically reducing energy consumption and resource usage for each request.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2704014B1Server, server control method, program and recording medium
Publication Date: 2019.03.27 RAKUTEN GROUP INC
  • EP2704014B1 patent drawingFigure 1
  • EP2704014B1 patent drawingFigure 2
  • EP2704014B1 patent drawingFigure 3

AI summary

A request receiver (101) receives a request in which image ID information and a parameter for image processing are specified, from a terminal. An image processor (102) acquires an image based on the ID information that was specified in the received request, and by using the parameter that was specified in the received request to apply the image processing on the acquired image, outputs extracted information that was extracted from inside the image. A response transmitter (103) transmits a response in which the extracted information that was outputted by the image processor (102) is specified, to the terminal. When the extracted information that is associated with the ID information and the parameter that were specified in the received request is cached, the image processor (102), instead of acquiring the image and applying the image processing, obtains the cached extracted information, and outputs the obtained extracted information.