# US 2021/0342038 A1 · Message application improvement for recalling one to many private conversations

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

- Number: US 2021/0342038 A1
- Document ID: US20210342038A1
- Status: Published application
- Kind: A1
- Application number: 16/866,380
- Filed: 2020-05-04
- Published: 2021-11-04
- Earliest claimed: 2020-05-04
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Adam Leon; Monique Yin; David Golland; Felix Giguere Villegas
- Web page: https://patentgrep.com/patent/US20210342038A1

## CPC

- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G06F 16/90335: {Query processing}
- G06N 20/00: Machine learning
- H04L 51/214: using selective forwarding
- H04L 51/52: for supporting social networking services
- H04M 1/7243: with interactive means for internal management of messages
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

Techniques for improving an interactive user interface of a messaging application by dynamically identifying a configurable number of top-ranked targets for a new message from a plurality of possible targets for the new message are disclosed. An interaction with the messaging application is detected. The interaction is determined to be indicative of an intent to identify a target for the new message from the plurality of possible targets for the new message. The identifying of the targets is performed by applying a matching algorithm to the one or more keywords. The matching algorithm blends a ranking of individual connections associated with the member with a ranking of group conversations associated with the member. Responsive to the detection of the interaction, a listing of identifiers associated with the targets is caused to be presented in a search results portion of the user interface.

## Claims

### Claim 1

A system comprising:
one or more computer processors;
one or more computer memories;
a set of instructions incorporated into the one or more computer memories, the set of instructions configuring the one or more computer processors to perform operations, the operations comprising:
detecting an interaction with a messaging application, the interaction being usable for identifying a target for a new message from a plurality of possible targets for the new message, the interaction including a specification of one or more keywords associated with the target in a search portion of a user interface, the plurality of possible targets including individual connections and group conversations associated with a member of a social networking system;
applying a matching algorithm to the one or more keywords, the matching algorithm blending a ranking of the individual connections associated with the member with a ranking of the group conversations associated with the member; and
responsive to the detection of the interaction, causing a listing of identifiers associated with the targets to be presented in a search results portion of the user interface, each of the identifiers being selectable to cause a field to be presented in the user interface for entering the new message.

### Claim 2 (depends on 1)

The system of claim 1, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to personalized engagement by the member with the group conversations, the features including one or more of conversation impressions by the member and messages sent to the conversations by the member.

### Claim 3 (depends on 1)

The system of claim 1, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to relationships between the member and participants of the conversations, the features including one or more of numbers of the participants in the group conversations, proportions of the participants who are connections of the member to participants who are not connections of the member.

### Claim 4 (depends on 1)

The system of claim 1, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to general activity associated with the group conversations, the features including one or more of a total count of messages sent by participants in the group conversations and ages of the group conversations.

### Claim 5 (depends on 1)

The system of claim 1, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to a context of the interaction, the features including one or more of fields to which the keywords are matched and classifications of activities of the member with respect to the group conversations.

### Claim 6 (depends on 2)

The system of claim 2, wherein the machine-learned model is generated based on a plurality of training data sources, the training data sources including one or more of a database of conversation views, a database of previous messages sent, and a database of connection strengths.

### Claim 7 (depends on 2)

The system of claim 2, wherein the machine-learned model is selected from a plurality of machine-learned models based on one or more metrics, the one or more metrics including time to click, click-through rate, or distribution of click position.

### Claim 8 (depends on 5)

The system of claim 5, wherein the fields include one or more of a field pertaining to a participant name and a field pertaining to a group conversation name.

### Claim 9 (depends on 5)

The system of claim 5, wherein the interaction invokes a typeahead (TYAH) functionality in which each keystroke in the search portion triggers an update of the search results portion.

### Claim 10 (depends on 9)

The system of claim 9, wherein the TYAH functionality is implementing with low latency based on accessing of an online key-value data store to identify search results for including in the updating of the search results portion.

### Claim 11

A method comprising:
detecting an interaction with a messaging application, the interaction being usable for identifying a target for a new message from a plurality of possible targets for the new message, the interaction including a specification of one or more keywords associated with the target in a search portion of a user interface, the plurality of possible targets including individual connections and group conversations associated with a member of a social networking system;
applying a matching algorithm to the one or more keywords, the matching algorithm blending a ranking of the individual connections associated with the member with a ranking of the group conversations associated with the member; and
responsive to the detection of the interaction, causing a listing of identifiers associated with the targets to be presented in a search results portion of the user interface, each of the identifiers being selectable to cause a field to be presented in the user interface for entering the new message.

### Claim 12 (depends on 11)

The method of claim 11, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to personalized engagement by the member with the group conversations, the features including one or more of conversation impressions by the member and messages sent to the conversations by the member.

### Claim 13 (depends on 11)

The method of claim 11, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to relationships between the member and participants of the conversations, the features including one or more of numbers of the participants in the group conversations, proportions of the participants who are connections of the member to participants who are not connections of the member.

### Claim 14 (depends on 11)

The method of claim 11, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to general activity associated with the group conversations, the features including one or more of a total count of messages sent by participants in the group conversations and ages of the group conversations.

### Claim 15 (depends on 11)

The method of claim 11, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to a context of the interaction, the features including one or more of fields to which the keywords are matched and classifications of activities of the member with respect to the group conversations.

### Claim 16

A non-transitory machine-readable storage medium embodying a set of instructions that, when executed by one or more processors, causes the one or more processors to perform operations for dynamically identifying targets for a new message from a plurality of possible targets for the new message, the operations comprising:
detecting an interaction with a messaging application, the interaction being usable for identifying a target for a new message from a plurality of possible targets for the new message, the interaction including a specification of one or more keywords associated with the target in a search portion of a user interface, the plurality of possible targets including individual connections and group conversations associated with a member of a social networking system;
applying a matching algorithm to the one or more keywords, the matching algorithm blending a ranking of the individual connections associated with the member with a ranking of the group conversations associated with the member; and
responsive to the detection of the interaction, causing a listing of identifiers associated with the targets to be presented in a search results portion of the user interface, each of the identifiers being selectable to cause a field to be presented in the user interface for entering the new message.

### Claim 17 (depends on 16)

The non-transitory machine-readable storage medium of claim 16, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to personalized engagement by the member with the group conversations, the features including one or more of conversation impressions by the member and messages sent to the conversations by the member.

### Claim 18 (depends on 16)

The non-transitory machine-readable storage medium of claim 16, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to relationships between the member and participants of the conversations, the features including one or more of numbers of the participants in the group conversations, proportions of the participants who are connections of the member to participants who are not connections of the member.

### Claim 19 (depends on 16)

The non-transitory machine-readable storage medium of claim 16, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to general activity associated with the group conversations, the features including one or more of a total count of messages sent by participants in the group conversations and ages of the group conversations.

### Claim 20 (depends on 16)

The non-transitory machine-readable storage medium of claim 16, wherein the applying of the matching algorithm includes applying a machine-learned model to the group conversations, the machine-learned model using features pertaining to a context of the interaction, the features including one or more of fields to which the keywords are matched and classifications of activities of the member with respect to the group conversations.
