WO2025233667 - MULTIMODAL EXPLAINABLE JUSTIFICATION FOR FACT-CHECKING FIELD
National phase entry is expected:
Publication Number
WO/2025/233667
Publication Date
13.11.2025
International Application No.
PCT/IB2024/056848
International Filing Date
15.07.2024
Title **
[English]
MULTIMODAL EXPLAINABLE JUSTIFICATION FOR FACT-CHECKING FIELD
[French]
JUSTIFICATION EXPLICABLE MULTIMODALE DANS LE DOMAINE DE LA VÉRIFICATION DES FAITS
Applicants **
NEC LABORATORIES EUROPE GMBH
Inventors
HUNG, Chia-Chien
GONG, Na
Priority Data
63/645,181
10.05.2024
US
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| Number of Office Actions | * |
| * | |
International Searching Authority |
EPO
* |
| Recordal of a Change of the Applicant's Name/Address |
Change of Applicant's Name and Address
* |
| Type of Assignment |
The Standard Agent's Assignment
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Patent Delivery |
Send the Letters Patent by Courier
* |
| Translation |
|
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing, Examination, Granting | 2124 | |
| EPO | Filing, Examination, Granting | 8477 | |
| Japan | Filing, Examination, Granting | 2174 | |
| South Korea | Filing, Examination, Granting | 2050 | |
| USA | Filing, Examination, Granting | 4740 |
Total:
19,565
Contact Us
Abstract[English]
A computer-implemented method for multimodal fact-checking includes receiving, from an agent system, new textual data indicating a textual claim. The method further includes segmenting the evidences that are in the different modalities and/or the different data formats into trackable multi-modal unit-based pairs and transforming image-based multi-modal evidences that are in the image data formats into the non-image formats. The method also includes inputting the textual claim, the trackable multi-modal unit-based pairs, and output from a generative artificial intelligence (AI) model into a multimodal explanation generator to generate final multimodal explanation information. The method has applications including, but not limited to, use cases in machine learning and medicine / healthcare, e.g., generating final multimodal explanation information indicating the veracity of whether a patient has a medical condition and a subset of evidences that support the veracity of whether the patient has the medical condition, which can help optimize decision making.[French]
Un procédé mis en œuvre par ordinateur pour une vérification des faits multimodale consiste à recevoir, en provenance d'un système agent, de nouvelles données textuelles indiquant une affirmation textuelle. Le procédé consiste en outre à segmenter des éléments de preuve issus de différentes modalités et/ou de différents formats de données en paires unitaires multimodales traçables et à transformer des preuves multimodales basées sur des images, initialement en formats de données image, en formats non visuels. Le procédé consiste également à introduire l'affirmation textuelle, les paires unitaires multimodales traçables, ainsi que la sortie d’un modèle d’intelligence artificielle (IA) générative dans un générateur d'explication multimodale pour générer des informations explicatives multimodales finales. Le procédé trouve des applications notamment, mais de manière non limitative, dans les domaines de l’apprentissage automatique et de la médecine/santé, par exemple pour générer des informations explicatives multimodales finales indiquant la véracité du diagnostic d’une pathologie chez un patient, ainsi qu’un sous-ensemble d’éléments de preuve étayant cette véracité, ce qui peut contribuer à optimiser la prise de décision.