# US 12,182,216 B2 · Machine learning model and encoder to predict online user journeys > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,182,216 B2 - Document ID: US12182216B2 - Status: Granted - Kind: B2 - Application number: 18/345,802 - Filed: 2023-06-30 - Published: 2023-11-02 - Granted: 2024-12-31 - Earliest claimed: 2021-03-26 - Assignees: Zeta Global Corp. - Applicants: Zeta Global Corp. - Inventors: Danny Portman; Zachary D. Jones - Web page: https://patentgrep.com/patent/US12182216B2 ## CPC - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 11/3438: {monitoring of user actions (tracking the activity of the user H04L67/535)} - G06F 16/958: Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/09: Supervised learning - G06Q 30/0201: Market modelling; Market analysis; Collecting market data - G06Q 30/0241: Advertisements - G06Q 30/0282: Rating or review of business operators or products - G06Q 30/0631: {Recommending goods or services} - G06F 11/008: {Reliability or availability analysis} - G06F 2201/86: Event-based monitoring - G06N 3/084: Backpropagation, e.g. using gradient descent - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract The subject technology identifies a series of journey event types in an online user journey, the event types including an impression event, an email event, a click event, and a website visit, and assigns an encoder to each event type. Using an assigned encoder, the technology encodes each event type to generate an encoded vector for each event type. The encoded vector is representative of at least a portion of the online user journey relating to that event type. The technology generates an encoded vector for each event type to create a set of encoded vectors, the set of encoded vectors including one or more of an impression event encoded vector, an email event encoded vector, a click event encoded vector, and a website visit encoded vector. The technology aggregates the set of encoded vectors to generate an output of the online user journey encoder, the output including a composite encoded user journey vector for modeling, transmits the output of the online user journey encoder to a user journey training model for training of the model and, using a trained model, generates an occurrence probability for at least one further event in the online user journey. ## Claims ### Claim 1 A system for predicting online user activity comprising: one or more processors; and a memory storing instructions which, when executed by at least one processor in the one or more processors, cause the at least one processor to: identify multiple journey event types in a sample of multiple online user journeys; assign an encoder to each event type; use an assigned encoder, encoding each instance of a particular event type in the sample to generate an encoded vector for the particular event type, the encoded vector being representative of at least a portion of one or more of the multiple online user journeys that relates to the particular event type; generate an encoded vector for each event type to create a set of encoded vectors; aggregate the set of encoded vectors to generate an output of the online user journey encoder, the output including a composite encoded user journey vector for modeling; transmit the output of the online user journey encoder to a user journey training model for training of a user journey model; and use a trained model, generating an occurrence probability for at least one further event in an online user journey. ### Claim 2 (depends on 1) The system of claim 1, wherein the user journey model includes a long short-term memory (LSTM). ### Claim 3 (depends on 1) The system of claim 1, wherein the at least one further event includes a conversion event. ### Claim 4 (depends on 3) The system of claim 3, wherein the processor is further configured to determine how the occurrence probability of the conversion event is affected by differing content items associated with one or more of the multiple journey event types. ### Claim 5 (depends on 3) The system of claim 3, wherein the processor is further configured to optimize an occurrence probability of the conversion event using differing content items associated with one or more of the multiple journey event types. ### Claim 6 (depends on 1) The system of claim 1, wherein the processor is further configured to augment the composite encoded user journey vector based on one or more of a media type, a timing, a media channels, an image, and a text or email content. ### Claim 7 (depends on 1) The system of claim 1, wherein the processor is further configured to map each instance of one or more of the multiple event types to a unique user id. ### Claim 8 A method of predicting online user activity, the method comprising: identifying multiple journey event types in a sample of multiple online user journeys; assigning an encoder to each event type; using an assigned encoder, encoding each instance of a particular event type in the sample to generate an encoded vector for the particular event type, the encoded vector being representative of at least a portion of one or more of the multiple online user journeys that relates to the particular event type; generating an encoded vector for each event type to create a set of encoded vectors; aggregating the set of encoded vectors to generate an output of an online user journey encoder, the output including a composite encoded user journey vector for modeling; transmitting the output of the online user journey encoder to a user journey training model for training of a user journey model; and using a trained model, generating an occurrence probability for at least one further event in an online user journey. ### Claim 9 (depends on 8) The method of claim 8, wherein the user journey model includes a long short-term memory (LSTM). ### Claim 10 (depends on 8) The method of claim 8, wherein the at least one further event includes a conversion event. ### Claim 11 (depends on 10) The method of claim 10, further comprising determining how the occurrence probability of the conversion event is affected by differing content items associated with one or more of the multiple journey event types. ### Claim 12 (depends on 10) The method of claim 10, further comprising optimizing an occurrence probability of the conversion event using differing content items associated with one or more of the multiple journey event types. ### Claim 13 (depends on 8) The method of claim 8, further comprising augmenting the composite encoded user journey vector based on one or more of a media type, a timing, a media channels, an image, and a text or email content. ### Claim 14 (depends on 8) The method of claim 8, further comprising mapping each instance of one or more of the multiple event types to a unique user id. ### Claim 15 A non-transitory machine-readable medium comprising instructions which, when read by a machine, cause the machine to perform operations in a method of predicting online user activity, the operations comprising: identifying a multiple journey event types in a sample of multiple online user journeys; assigning an encoder to each event type; using an assigned encoder, encoding each instance of a particular event type in the sample to generate an encoded vector for the particular event type, the encoded vector being representative of at least a portion of one or more of the multiple online user journeys that relates to the particular event type; generating an encoded vector for each event type to create a set of encoded vectors; aggregating the set of encoded vectors to generate an output of an online user journey encoder, the output including a composite encoded user journey vector for modeling; transmitting the output of the online user journey encoder to a user journey training model for training of a user journey model; and using a trained model, generating an occurrence probability for at least one further event in the online user journey. ### Claim 16 (depends on 15) The medium of claim 15, wherein the user journey training model includes a long short-term memory (LSTM). ### Claim 17 (depends on 15) The medium of claim 15, wherein the at least one further event includes a conversion event. ### Claim 18 (depends on 17) The medium of claim 17, wherein the operations further comprise determining how the occurrence probability of the conversion event is affected by differing content items associated with one or more of the multiple journey event types. ### Claim 19 (depends on 17) The medium of claim 17, wherein the operations further comprise optimizing an occurrence probability of the conversion event using differing content items associated with one or more of the multiple journey event types. ### Claim 20 (depends on 15) The medium of claim 15, wherein the operations further comprise augmenting the composite encoded user journey vector based on one or more of a media type, a timing, a media channels, an image, and a text or email content.