1. WO2026174390 - METHODS AND SYSTEMS FOR PREDICTING SEQUENTIAL ACTIONS USING DEEP GENERATIVE MODELS

Publication Number WO/2026/174390

Publication Date 27.08.2026

International Application No. PCT/CA2026/050259

International Filing Date 19.02.2026

IPC

G06N 20/00 2019.1

G	PHYSICS
06	COMPUTING; CALCULATING OR COUNTING
N	COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
20	Machine learning

G06N 3/04 2023.1

G	PHYSICS
06	COMPUTING; CALCULATING OR COUNTING
N	COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
3	Computing arrangements based on biological models
02	Neural networks
04	Architecture, e.g. interconnection topology

G06N 3/08 2023.1

G	PHYSICS
06	COMPUTING; CALCULATING OR COUNTING
N	COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
3	Computing arrangements based on biological models
02	Neural networks
08	Learning methods

G06N 20/00 2019.1

G	PHYSICS
06	COMPUTING; CALCULATING OR COUNTING
N	COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
20	Machine learning

G06N 3/04 2023.1

G	PHYSICS
06	COMPUTING; CALCULATING OR COUNTING
N	COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
3	Computing arrangements based on biological models
02	Neural networks
04	Architecture, e.g. interconnection topology

G06N 3/08 2023.1

G	PHYSICS
06	COMPUTING; CALCULATING OR COUNTING
N	COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
3	Computing arrangements based on biological models
02	Neural networks
08	Learning methods

View less classifications

Applicants

• SHOPIFY INC. [CA]/[CA]

Inventors

• ARNOLD, Andrew
• PARAKHIN, Mikhail

Agents

• SMART & BIGGAR LP
• WONG, Christine
• JEZIORSKI, Katherine

Priority Data

19/056,937

19.02.2025

US

Publication Language English (en)

Filing Language English (en)

Designated States

View all

AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CV, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IQ, IR, IS, IT, JM, JO, JP, KE, KG, KH, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, MG, MK, MN, MU, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UY, UZ, VC, VN, WS, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, CV, GH, GM, KE, LR, LS, MU, MW, MZ, NA, RW, SC, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Organization (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, ME, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)

Hide all

Title

(EN) METHODS AND SYSTEMS FOR PREDICTING SEQUENTIAL ACTIONS USING DEEP GENERATIVE MODELS

(FR) PROCÉDÉS ET SYSTÈMES DE PRÉDICTION D'ACTIONS SÉQUENTIELLES À L'AIDE DE MODÈLES GÉNÉRATIFS PROFONDS

Abstract

(EN) Methods and systems for implementing an action prediction framework associated with a user are described. An action prediction model generates a plurality of synthetic action sequences and corresponding synthetic end states for the user, based on a sequence of historical actions and corresponding historical end states. A plurality of pathways are projected through the plurality of synthetic action sequences, for assisting the user in arriving at a desired end state. During a training phase, a machine learning model is trained to learn a plurality of implicit features related to user behavior, for generating the synthetic action sequences and pathways. During an inference phase, the action prediction framework identifies waypoints associated with recommended user or system actions for assisting the user in reaching the end state more efficiently. The disclosed methods and systems may enable robust and efficient sequential action prediction while minimizing resource consumption associated with computationally expensive foundation models.

(FR) L'invention concerne des procédés et des systèmes pour mettre en œuvre un cadre de prédiction d’actions associé à un utilisateur. Un modèle de prédiction d’actions génère une pluralité de séquences synthétiques d’actions et des états finals synthétiques correspondants pour l'utilisateur, sur la base d'une séquence historique d’actions et d'états finals historiques correspondants. Une pluralité de voies est projetée par l'intermédiaire de la pluralité de séquences synthétiques d’actions, pour aider l'utilisateur à arriver à un état final souhaité. Pendant une phase d'apprentissage, un modèle d'apprentissage automatique est entraîné pour apprendre une pluralité de caractéristiques implicites liées au comportement de l'utilisateur, pour générer les séquences synthétiques d’actions et les voies. Pendant une phase d'inférence, le cadre de prédiction d’actions identifie des points de cheminement associés à des actions recommandées de l'utilisateur ou du système pour aider l'utilisateur à atteindre l'état final de manière plus efficiente. Les procédés et les systèmes de l'invention peuvent permettre une prédiction d’actions séquentielles robuste et efficiente tout en réduisant au minimum la consommation de ressources associée à des modèles de fondation coûteux en termes de calcul.

Related patent documents

US20260244936

Latest bibliographic data on file with the International Bureau

The publication of an international application under the Patent Cooperation Treaty in PATENTSCOPE (which constitutes an element of the Gazette) does not imply the expression of any opinion whatsoever on the part of the International Bureau of WIPO concerning the legal status of any country, territory, city or area or of its authorities, or concerning the delimitation of its frontiers or boundaries.