# US 2021/0243143 A1 · Suggested responses based on message stickers

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

- Number: US 2021/0243143 A1
- Document ID: US20210243143A1
- Status: Published application
- Kind: A1
- Application number: 17/224,949
- Filed: 2021-04-07
- Published: 2021-08-05
- Earliest claimed: 2016-09-20
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Hung PHAM
- Web page: https://patentgrep.com/patent/US20210243143A1

## CPC

- H04L 51/046: Interoperability with other network applications or services
- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G06F 40/274: Converting codes to words; Guess-ahead of partial word inputs
- G06F 40/56: Natural language generation
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04L 51/08: Annexed information, e.g. attachments
- H04W 4/14: Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
- G06F 40/30: Semantic analysis
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

Implementations relate to automatic suggested responses based on message stickers provided in a messaging application. In some implementations, a computer-implemented method to provide message suggestions in a messaging application includes detecting a first message sent by a first user device to a second user device over a communication network, programmatically analyzing the first message to determine a semantic concept associated with the first message, identifying one or more message stickers based at least in part on the semantic concept, and transmitting instructions to cause the one or more message stickers to be displayed in a user interface displayed on the second user device.

## Claims

### Claim 1

A computer-implemented method to provide message suggestions in a messaging application, the method comprising:
detecting a first message sent from a first user device to a second user device over a communication network;
programmatically analyzing the first message to determine a semantic concept associated with the first message;
determining multiple suggested text responses to the first message based on the semantic concept;
comparing each of the multiple suggested text responses to respective descriptors associated with a plurality of message stickers;
selecting at least one descriptor of the respective descriptors that matches at least a portion of at least one suggested text response of the multiple suggested text responses; and
transmitting instructions to cause the at least one selected descriptor to be displayed in a user interface on the second user device as a suggested response to the first message.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the at least one selected descriptor is a word included in the at least one suggested text response.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the at least one suggested text response includes at least two words, and wherein the at least one selected descriptor includes a first selected descriptor that matches a first word of the at least two words and a second selected descriptor that matches a second word of the at least two words.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the plurality of message stickers are in a predefined set of available message stickers stored locally on the second user device.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising transmitting instructions to cause one or more message stickers that have the at least one descriptor to be displayed as one or more additional suggested responses in the user interface displayed on the second user device.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein determining the multiple suggested text responses includes receiving the multiple suggested text responses from a server device, wherein the server device determines the multiple suggested text responses based on a mapping of the semantic concept to a library of suggested text responses stored on the server device.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the first message includes a received message sticker, wherein programmatically analyzing the first message to determine the semantic concept associated with the first message includes using sticker identification information received with the received message sticker to retrieve an associated descriptor that is associated with the received message sticker from sticker data storage, and wherein the associated descriptor is included in the semantic concept.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, further comprising:
receiving selection of the suggested response based on user input to the second user device; and
in response to receiving the selection, transmitting the selected suggested response to the first user device over the communication network via the messaging application.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein comparing each of the multiple suggested text responses to the respective descriptors includes at least one of:
checking for letter matches between words of the respective descriptors and the multiple suggested text responses; or
checking for semantic similarity between the respective descriptors and the multiple suggested text responses.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the plurality of message stickers includes at least one of images, animated images, or videos.

### Claim 11

A system to provide message suggestions in a messaging application comprising:
at least one processor; and
memory coupled to the at least one processor and storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
detecting a first message sent from a first user device to a second user device over a communication network;
programmatically analyzing the first message to determine a semantic concept associated with the first message;
determining multiple suggested text responses to the first message based on the semantic concept;
comparing each of the multiple suggested text responses to respective descriptors associated with a plurality of message stickers;
selecting at least one descriptor of the respective descriptors that matches at least a portion of at least one suggested text response of the multiple suggested text responses; and
transmitting instructions to cause the at least one selected descriptor to be displayed in a user interface on the second user device as a suggested response to the first message.

### Claim 12 (depends on 11)

The system of claim 11, wherein the at least one selected descriptor is a word included in the at least one suggested text response.

### Claim 13 (depends on 11)

The system of claim 11, wherein the at least one suggested text response includes at least two words, and wherein the at least one selected descriptor includes a first selected descriptor that matches a first word of the at least two words and a second selected descriptor that matches a second word of the at least two words.

### Claim 14 (depends on 11)

The system of claim 11, wherein the plurality of message stickers are in a predefined set of available message stickers stored locally on the second user device.

### Claim 15 (depends on 11)

The system of claim 11, wherein the operation of determining the multiple suggested text responses includes receiving the multiple suggested text responses from a server device, wherein the server device determines the multiple suggested text responses based on a mapping of the semantic concept to a library of suggested text responses stored on the server device.

### Claim 16 (depends on 11)

The system of claim 11, wherein the first message includes a received message sticker, wherein the operation of programmatically analyzing the first message to determine the semantic concept associated with the first message includes using sticker identification information received with the received message sticker to retrieve an associated descriptor that is associated with the received message sticker from sticker data storage, and wherein the associated descriptor is included in the semantic concept.

### Claim 17 (depends on 11)

The system of claim 11, wherein the at least one processor performs further operations of:
receiving selection of the suggested response based on user input to the second user device; and
in response to receiving the selection, transmitting the selected suggested response to the first user device over the communication network via the messaging application.

### Claim 18 (depends on 11)

The system of claim 11, wherein the operation of comparing each of the multiple suggested text responses to the respective descriptors includes at least one of:
checking for letter matches between words of the respective descriptors and the multiple suggested text responses; or
checking for semantic similarity between the respective descriptors and the multiple suggested text responses.

### Claim 19 (depends on 11)

The system of claim 11, wherein the plurality of message stickers includes at least one of images, animated images, or videos.

### Claim 20

A non-transitory computer usable medium including computer program instructions that, when executed on a computer, cause the computer to perform operations comprising:
detecting a first message sent from a first user device to a second user device over a communication network;
programmatically analyzing the first message to determine a semantic concept associated with the first message;
determining multiple suggested text responses to the first message based on the semantic concept;
comparing each of the multiple suggested text responses to respective descriptors associated with a plurality of message stickers;
selecting at least one descriptor of the respective descriptors that matches at least a portion of at least one suggested text response of the multiple suggested text responses; and
transmitting instructions to cause the at least one selected descriptor to be displayed in a user interface on the second user device as a suggested response to the first message.
