# US 2025/0097175 A1 · Smart sticker selection for a messaging system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0097175 A1 - Document ID: US20250097175A1 - Status: Published application - Kind: A1 - Application number: 18/968,003 - Filed: 2024-12-04 - Published: 2025-03-20 - Earliest claimed: 2022-04-01 - Assignees: Snap Inc. - Applicants: Snap Inc. - Inventors: Jiayu He - Web page: https://patentgrep.com/patent/US20250097175A1 ## CPC - H04L 51/04: Real-time or near real-time messaging, e.g. instant messaging [IM] - G06F 40/205: Parsing - G06F 40/247: Thesauruses; Synonyms - G06F 40/30: Semantic analysis - H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages - H04L 51/10: Multimedia information - H04L 51/52: for supporting social networking services - G06N 3/0464: Convolutional networks [CNN, ConvNet] - H04L 51/18: Commands or executable codes - H04L 51/216: Handling conversation history, e.g. grouping of messages in sessions or threads - 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) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A text string provided by a second client device of a second user is received by a first client device of a first user. The text string is parsed into one or more text portions. A score is assigned to each of the one or more text portions based on a specified criterion. One or more relevant tags of a plurality of tags are determined based on the one or more text portions. One or more media overlays are selected based on the one or more relevant tags and the assigned score for each of the one or more text portions. The text string with a reply interface for sending a reply message to the second client device is displayed. ## Claims ### Claim 1 A method, the method comprising: identifying a text string in an interaction client that enables a communication message sent from a first user of a first device to a plurality of second devices, the plurality of second devices including a second user of a second device; identifying a root word in the text string based on one or more relevant tags; identifying one or more associated children words in the text string associated with the identified root word; generating a first score for the identified root word; generating a second set of scores for the one or more identified children words; selecting a media overlay of a plurality of media overlays based on the first score and the second set of scores; and recommending the selected media overlay for display within the interaction client. ### Claim 2 (depends on 1) The method of claim 1, wherein the communication message includes a broadcast message that initiates a broadcast of the message to the plurality of the second devices. ### Claim 3 (depends on 1) The method of claim 1, wherein the selected media overlay includes an emoji. ### Claim 4 (depends on 1) The method of claim 1, further comprising parsing the text string into one or more text portions, wherein identifying the root word comprises identifying the root word in at least one of the text portions. ### Claim 5 (depends on 4) The method of claim 4, further comprising: determining a relevancy score for each of the plurality of media overlays that includes the selected media overlay based on the individual one or more relevant tags and the generated first and second scores for each of the one or more parsed text portions; and ordering the selected media overlay with other media overlays within the interaction client based on the determined relevancy score of each of the plurality of media overlays. ### Claim 6 (depends on 4) The method of claim 4, wherein determining the one or more relevant tags based on the one or more parsed text portions comprises iteratively scanning through each text portion of the text string. ### Claim 7 (depends on 4) The method of claim 4, wherein the one or more parsed text portions comprise one or more words; and the method further comprises determining one or both of a synonym and an antonym of at least one of the one or more words, wherein determining the one or more relevant tags comprises determining the one or more relevant tags based on one or both of the synonym and the antonym. ### Claim 8 (depends on 4) The method of claim 4, further comprising determining the one or more relevant tags based on at least one of the parsed text portions. ### Claim 9 (depends on 1) The method of claim 1, wherein the second set of scores is generated based on an association with the identified root word. ### Claim 10 (depends on 1) The method of claim 1, wherein the media overlay is further selected based on the one or more relevant tags. ### Claim 11 (depends on 1) The method of claim 1, wherein the recommendation is for display of the selected media overlay adjacent to the text string within the interaction client. ### Claim 12 (depends on 1) The method of claim 1, wherein the recommendation enables the first device to send a reply message that includes the selected media overlay to the second device. ### Claim 13 (depends on 1) The method of claim 1, wherein the first score for the identified root word and the second set of scores for the identified children words each correspond to an emotion of individual words, the emotion reflecting a mood of the second user, the selected media overlay being selected based on the first score and the second set of scores corresponding to individual emotions. ### Claim 14 (depends on 1) The method of claim 1, wherein the method further comprises: selecting a set of media overlays includes by identifying a plurality of media overlays selected based on the first score and the second scores corresponding to individual emotions, the plurality of media overlays including the selected media overlay, and randomly selecting the set of media overlays from the plurality of media overlays, wherein selecting the media overlay of the plurality of media overlays comprises selecting the media overlay of the set of media overlays. ### Claim 15 (depends on 14) The method of claim 14, wherein at least one of the first score for the identified root word or the second set of scores for the identified children words correspond to an amount of the emotion of the second user, the selected media overlay being selected based on the amount of the emotion. ### Claim 16 (depends on 1) The method of claim 1, wherein the selected media overlay corresponds to a predefined overlay for displaying in a predefined order, wherein the method further includes ranking media overlays that includes the selected media overlay based on a number of relevant tags associated with each media overlay of the media overlays. ### Claim 17 (depends on 1) The method of claim 1, further comprising: receiving, via the interaction client, user selection of the selected media overlay among other media overlays; and providing, by the first device, for transmission of the selected media overlay to the second device. ### Claim 18 (depends on 1) The method of claim 1, wherein the text string comprises words and at least one emoji. ### Claim 19 A computing apparatus, comprising: at least one processor; and a memory storing instructions that, when executed by the at least one processor, configure the computing apparatus to perform one or more operations comprising: identifying a text string in an interaction client that enables a communication message sent from a first user of a first device to a plurality of second devices, the plurality of second devices including a second user of a second device; identifying a root word in the text string based on one or more relevant tags; identifying one or more associated children words in the text string associated with the identified root word; generating a first score for the identified root word; generating a second set of scores for the one or more identified children words; selecting a media overlay of a plurality of media overlays based on the first score and the second set of scores; and recommending the selected media overlay for display within the interaction client. ### Claim 20 A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to perform one or more operations comprising: identifying a text string in an interaction client that enables a communication message sent from a first user of a first device to a plurality of second devices, the plurality of second devices including a second user of a second device; identifying a root word in the text string based on one or more relevant tags; identifying one or more associated children words in the text string associated with the identified root word; generating a first score for the identified root word; generating a second set of scores for the one or more identified children words; selecting a media overlay of a plurality of media overlays based on the first score and the second set of scores; and recommending the selected media overlay for display within the interaction client.