# US 10,454,869 B2 · Computerized system and method for controlling electronic messages and their responses after delivery

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,454,869 B2
- Document ID: US10454869B2
- Status: Granted
- Kind: B2
- Application number: 15/805,369
- Filed: 2017-11-07
- Published: 2019-05-09
- Granted: 2019-10-22
- Earliest claimed: 2017-11-07
- Assignees: Oath Inc.
- Applicants: Oath Inc.
- Inventors: Natalia Silberstein; Irena Grabovitch-Zuyev; Iftah Gamzu; Noa Avigdor-Elgrabli; Yoelle Maarek; Liane Lewin-Eytan
- Web page: https://patentgrep.com/patent/US10454869B2

## CPC

- G06F 40/216: using statistical methods
- G06F 16/951: Indexing; Web crawling techniques
- G06F 40/30: Semantic analysis
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- G06Q 10/109: Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q 10/40: Business processes related to social networking or social networking services
- H04L 51/18: Commands or executable codes
- H04W 4/12: Messaging; Mailboxes; Announcements
- G06N 3/08: Learning methods
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- H04L 51/42: Mailbox-related aspects, e.g. synchronisation of mailboxes
- H04W 88/184: {Messaging devices, e.g. message centre}
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

Disclosed are systems and methods for improving interactions with and between computers in content searching, hosting and/or providing systems supported by or configured with devices, servers and/or platforms. The disclosed systems and methods for efficiently monitoring and following up on delivered messages for which a user expects and/or requires a reply. The disclosed functionality provides a fully automated, personalized, easy and efficient way to identify and manage outgoing mail messages that require reply by marking outbound messages as RSVP messages, which are those messages determined to require a reply. Such functionality is based on the ability of the disclosed framework to distinguish between a “satisfactory response” (i.e., a response that includes the required information) and a response that is not.

## Claims

### Claim 1

A method comprising:
receiving, at a computing device, input provided by a sender, said input comprising information related to composition of a message addressed to a recipient on a message platform;
analyzing, via the computing device, said input, and based on said analysis, extracting attributes related to the composed message, said attributes comprising features of the message, features of the sender and features of the recipient;
generating, via the computing device, a feature vector M for said composed message based on said identified attributes, said vector M comprising nodes related to said message features, sender features and recipient features;
determining, via the computing device, a target date for said composed message, said target date being a time a reply to said composed message is expected to be received after sending of said composed message;
applying, via the computing device, said target date to said composed message, said application causing said composed message to be tagged as an RSVP message, such that said vector M has a bit added indicating whether a reply has been received, said bit initially set to “0” indicating no reply has yet been received;
sending, via the computing device, said RSVP message to said recipient;
receiving, via the computing device, a response message from said recipient in an inbox of said sender, said response message being sent by the recipient as a reply to said RSVP message;
analyzing, via the computing device, said response message, and based on said analysis, extracting attributes of the response message, said analysis further comprising generating a feature vector R based on the attributes of the response message, said response message attributes comprising message features of the response message, features of the recipient and features of the sender;
determining, via the computing device executing a machine learning (ML) classifier, whether said response message is a satisfactory response to said RSVP message based on said vector M and vector R, said determination further comprising:
marking, via the computing device, said RSVP message bit as “1”, thereby indicating to said message platform that said response message is received and is satisfactory, when the classifier classifies the response as satisfactory, and
generating, via the computing device, a follow-up message to said recipient indicating that the response was not satisfactory, when the classifier classifiers the response as a not satisfactory;
updating, via the computing device, said inbox of said sender based on said RSVP message tagging, said updating comprising populating a RSVP folder with said RSVP message; and
upon said response message being determined satisfactory, removing, via the computing device, said RSVP message from said RSVP folder.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
periodically monitoring, based on said target date, said inbox of the sender for said response message to said RSVP message from said recipient, said periodic monitoring occurring during a time period between a time the RSVP message was sent and a time prior to said target date;
determining, based on said monitoring, that said response message has not been received; and
generating and sending a follow-up message to said recipient, said follow-up message comprising information at least referencing said RSVP message and providing an indicating that a response to said RSVP message is outstanding.

### Claim 3 (depends on 1)

The method of claim 1, wherein said context of the RSVP message provides an indication as to a type of content included in said RSVP message, and an indication as to a type message content within a response message that addresses said context.

### Claim 4 (depends on 2)

The method of claim 2, wherein said context is represented as a node on said vector M.

### Claim 5 (depends on 1)

The method of claim 1, wherein said attributes further comprise sender-recipient features related to a relationship between the sender and recipient, wherein said vector M further comprises at least one node related to said sender-recipient features.

### Claim 6 (depends on 5)

The method of claim 5, wherein said sender-recipient features comprise information related to past message activity between the sender and recipient on said message platform.

### Claim 7 (depends on 1)

The method of claim 1, wherein:
said message features comprise content and metadata extracted from a body of the message,
said sender features comprise information extracted from the inbox of the sender indicating past messaging behavior by the sender, and
said recipient features comprise information extracted from said message platform indicating messaging activity by the recipient on said message platform.

### Claim 8 (depends on 1)

The method of claim 1, wherein said analysis of the input is performed by the computing device executing natural language processing (NLP) software on the input of the composed message.

### Claim 9 (depends on 3)

The method of claim 3, wherein said determination of the context and the target date are performed by the computing device executing natural language processing (NLP) software on the input of the composed message.

### Claim 10 (depends on 1)

The method of claim 1, wherein said composed message is addressed to a plurality of recipients.

### Claim 11 (depends on 10)

The method of claim 10, wherein said RSVP message is assigned a bit for each recipient, and is only determined to be completely responded to when each bit for each recipient is set at “1”.

### Claim 12 (depends on 1)

The method of claim 1, further comprising:
determining, via the computing device executing the ML classifier, whether the composed message is an RSVP message, wherein said applying said target date is performed based on said determination.

### Claim 13

A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a processor associated with a computing device, performs a method comprising:
receiving, at the computing device, input provided by a sender, said input comprising information related to composition of a message addressed to a recipient on a message platform;
analyzing, via the computing device, said input, and based on said analysis, extracting attributes related to the composed message, said attributes comprising features of the message, features of the sender and features of the recipient;
generating, via the computing device, a feature vector M for said composed message based on said identified attributes, said vector M comprising nodes related to said message features, sender features and recipient features;
determining, via the computing device, a target date for said composed message, said target date being a time a reply to said composed message is expected to be received after sending of said composed message;
applying, via the computing device, said target date to said composed message, said application causing said composed message to be tagged as an RSVP message, such that said vector M has a bit added indicating whether a reply has been received, said bit initially set to “0” indicating no reply has yet been received;
sending, via the computing device, said RSVP message to said recipient;
receiving, via the computing device, a response message from said recipient in an inbox of said sender, said response message being sent by the recipient as a reply to said RSVP message;
analyzing, via the computing device, said response message, and based on said analysis, extracting attributes of the response message, said analysis further comprising generating a feature vector R based on the attributes of the response message, said response message attributes comprising message features of the response message, features of the recipient and features of the sender;
determining, via the computing device executing a machine learning (ML) classifier, whether said response message is a satisfactory response to said RSVP message based on said vector M and vector R, said determination further comprising:
marking, via the computing device, said RSVP message bit as “1”, thereby indicating to said message platform that said response message is received and is satisfactory when the classifier classifies the response message as satisfactory, and
generating, via the computing device, a follow-up message to said recipient indicating that the response was not satisfactory when the classifier classifies the response message as a non-satisfactory;
updating, via the computing device, said inbox of said sender based on said RSVP message tagging, said updating comprising populating a RSVP folder with said RSVP message; and
upon said response message being determined satisfactory, removing, via the computing device, said RSVP message from said RSVP folder.

### Claim 14 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, further comprising:
periodically monitoring, based on said target date, said inbox of the sender for said response message to said RSVP message from said recipient, said periodic monitoring occurring during a time period between a time the RSVP message was sent and a time prior to said target date;
determining, based on said monitoring, that said response message has not been received; and
generating and sending a follow-up message to said recipient, said follow-up message comprising information at least referencing said RSVP message and providing an indicating that a response to said RSVP message is outstanding.

### Claim 15 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein said context of the RSVP message provides an indication as to a type of content included in said RSVP message, and an indication as to a type message content within a response message that addresses said context, wherein said context is represented as a node on said vector M.

### Claim 16 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein said attributes further comprise sender-recipient features related to a relationship between the sender and recipient, wherein said vector M further comprises at least one node related to said sender-recipient features, wherein said sender-recipient features comprise information related to past message activity between the sender and recipient on said message platform.

### Claim 17 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein:
said message features comprise content and metadata extracted from a body of the message,
said sender features comprise information extracted from the inbox of the sender indicating past messaging behavior by the sender, and
said recipient features comprise information extracted from said message platform indicating messaging activity by the recipient on said message platform.

### Claim 18

A computing device comprising:
a processor; and
a non-transitory computer-readable storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
logic executed by the processor for receiving, at the computing device, input provided by a sender, said input comprising information related to composition of a message addressed to a recipient on a message platform;
logic executed by the processor for analyzing, via the computing device, said input, and based on said analysis, extracting attributes related to the composed message, said attributes comprising features of the message, features of the sender and features of the recipient;
logic executed by the processor for generating, via the computing device, a feature vector M for said composed message based on said identified attributes, said vector M comprising nodes related to said message features, sender features and recipient features;
logic executed by the processor for determining, via the computing device, a target date for said composed message, said target date being a time a reply to said composed message is expected to be received after sending of said composed message;
logic executed by the processor for applying, via the computing device, said target date to said composed message, said application causing said composed message to be tagged as an RSVP message, such that said vector M has a bit added indicating whether a reply has been received, said bit initially set to “0” indicating no reply has yet been received;
logic executed by the processor for sending, via the computing device, said RSVP message to said recipient;
logic executed by the processor for receiving, via the computing device, a response message from said recipient in an inbox of said sender, said response message being sent by the recipient as a reply to said RSVP message;
logic executed by the processor for analyzing, via the computing device, said response message, and based on said analysis, extracting attributes of the response message, said analysis further comprising generating a feature vector R based on the attributes of the response message, said response message attributes comprising message features of the response message, features of the recipient and features of the sender;
logic executed by the processor for determining, via the computing device executing a machine learning (ML) classifier, whether said response message is a satisfactory response to said RSVP message based on said vector M and vector R, said determination further comprising:
logic executed by the processor for marking, via the computing device, said RSVP message bit as “1”, thereby indicating to said message platform that said response message is received and is satisfactory when the classifier indicates that the response message is satisfactory, and
logic executed by the processor for generating, via the computing device, a follow-up message to said recipient indicating that the response was not satisfactory when the classifier indicates that the response message is not satisfactory;
logic executed by the processor for updating, via the computing device, said inbox of said sender based on said RSVP message tagging, said updating comprising populating a RSVP folder with said RSVP message; and
logic executed by the processor for removing, via the computing device, upon said response message being determined satisfactory, said RSVP message from said RSVP folder.