Multi-modal model training method and apparatus, image recognition method and apparatus, and electronic device
US-2024331370-A1 · Oct 3, 2024 · US
US12548002B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12548002-B2 |
| Application number | US-202318324062-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 25, 2023 |
| Priority date | May 25, 2023 |
| Publication date | Feb 10, 2026 |
| Grant date | Feb 10, 2026 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Disclosed embodiments may include a system for providing automated bill splitting. The system may receive speech data. The system may identify, from the speech data and using natural language processing, one or more users. The system may determine, from the speech data and using natural language processing, orders of the one or more users. The system may determine, from the speech data and using natural language processing, rules for the orders of the one or more users. The system may process one or more payments for the orders based on the rules and one or more credentials associated with the one or more users.
Opening claim text (preview).
What is claimed is: 1 . A bill splitting system comprising: one or more processors; memory in communication with the one or more processors and storing instructions that are configured to cause the bill splitting system to: receive speech data; identify, from the speech data and using natural language processing, one or more users; dynamically and in real-time, determine, from the speech data and using natural language processing, orders of the one or more users by, for each item ordered, identifying which of the one or more users ordered the item and establishing a record of items that have been ordered by each of the one or more users; determine, from the speech data and using natural language processing, rules for the orders of the one or more users; generate a graphical user interface (GUI) for display by a user device comprising a list of items allocated to a first user of the one or more users, wherein the list of items is dynamically modified in real-time based on the determination of the orders of the one or more users and the rules for the orders of the one or more users; and process one or more payments for the orders based on the rules and one or more credentials associated with the one or more users. 2 . The bill splitting system of claim 1 , wherein the memory stores further instructions that are configured to cause the bill splitting system to: receive video data. 3 . The bill splitting system of claim 2 , wherein the video data comprises images of faces of the one or more users, and wherein the memory stores further instructions that are configured to cause the bill splitting system to: process the video data to track speech of the one or more users; and verify, using the video data and facial recognition, an identity of the one or more users. 4 . The bill splitting system of claim 3 , wherein the one or more users are identified by a trained machine learning model using speech embeddings and image analysis from the video data. 5 . The bill splitting system of claim 2 , wherein the memory stores further instructions that are configured to cause the bill splitting system to: verify, using the video data, the rules. 6 . The bill splitting system of claim 2 , wherein the memory stores further instructions that are configured to cause the bill splitting system to: verify, using the video data, the orders of the one or more users. 7 . The bill splitting system of claim 1 , further comprising: a microphone, for receiving the speech data; and a camera, for receiving video data. 8 . The bill splitting system of claim 7 , wherein the bill splitting system is operated on a smartphone of one or more users, a mobile device of a waiter, a pay-at-the-table device, or combinations thereof. 9 . A bill splitting system comprising: one or more processors; memory in communication with the one or more processors and storing instructions that are configured to cause the bill splitting system to: receive speech data; receive video data; identify, from the speech data and the video data, using a first machine learning model and speech embeddings, one or more users; dynamically and in real-time, determine, from the speech data and the video data, orders of the one or more users by, for each item ordered, identifying which of the one or more users ordered the item and establishing a record of items that have been ordered by each of the one or more users; determine, from the speech data and the video data, rules for the orders of the one or more users; generate an interactive graphical user interface (GUI) for display by a user device comprising a list of items allocated to a first user of the one or more users, wherein the list of items is dynamically modified in real-time based on the determination of the orders of the one or more users and the rules for the orders of the one or more users; and charge a balance to one or more associated account of the one or more users based on the rules. 10 . The bill splitting system of claim 9 , wherein identifying the one or more users further comprises associating a name with a voice using natural language processing. 11 . The bill splitting system of claim 9 , wherein determining the rules uses a second machine learning model. 12 . The bill splitting system of claim 9 , wherein the memory stores further instructions that are configured to cause the bill splitting system to: send, to the associated account, a receipt. 13 . The bill splitting system of claim 9 , wherein the memory stores further instructions that are configured to cause the bill splitting system to: send, to a mobile device associated with the associated account, a request for verification of the balance; and receive, from the mobile device, verification of the balance. 14 . The bill splitting system of claim 13 , wherein the request for verification of the balance further comprises the interactive GUI, wherein the interactive GUI shows the orders of the one or more users, the rules, and a total. 15 . The bill splitting system of claim 14 , wherein the interactive graphical user interface comprises one or more interactive elements that allow a user to modify one or more of the orders of the one or more users, the rules, and the total. 16 . A bill splitting system comprising: one or more processors; memory in communication with the one or more processors and storing instructions that are configured to cause the bill splitting system to: receive speech data; receive video data; identify, from the speech data and the video data, using a first machine learning model and speech embeddings, one or more users; dynamically and in real-time, determine, from the speech data and the video data, orders of the one or more users by, for each item ordered, identifying which of the one or more users ordered the item and establishing a record of items that have been ordered by each of the one or more users; determine, from the speech data and the video data, rules for the orders of the one or more users; generate a graphical user interface (GUI) for display by a user device comprising a list of items allocated to a first user of the one or more users, wherein the list of items is dynamically modified in real-time based on the determination of the orders of the one or more users and the rules for the orders of the one or more users; determine, from the rules, that long-term storage is required; responsive to determining that the long-term storage is required: store a reminder for a first user based on the rules, the speech data, and voice data; receive event data; determine that the event data corresponds to the reminder; and responsive to determining that the event data corresponds to the reminder: transmit, to the first user, the reminder. 17 . The bill splitting system of claim 16 , wherein the event data comprises a same merchant as a prior event, a same merchant type as the prior event, a same other users as the prior event, or combinations thereof. 18 . The bill splitting system of claim 1 , wherein the memory stores further instructions that are configured to cause the bill splitting system to: access a menu; and for each item ordered, associate the item with a menu item and a corresponding price listed in the menu for the item. 19 . The bill splitting system of claim 1 , wherein determining rules for the orders of the one or more users comprising: determining a first rule; subsequent to determining the first rule, determining a second rul
Electronic credentials · CPC title
Speaker identification or verification techniques · CPC title
Billing or invoicing · CPC title
Establishing or using transaction specific rules · CPC title
Classification, e.g. identification · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.