# US 11,310,184 B1 · Communication response analyzer > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,310,184 B1 - Document ID: US11310184B1 - Status: Granted - Kind: B1 - Application number: 17/039,066 - Filed: 2020-09-30 - Published: 2022-03-31 - Granted: 2022-04-19 - Earliest claimed: 2020-09-30 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Christian Wilhelm Kurt Byza; Jeffrey William Pasternack; Haowen Ning; Pujita Mathur; Yizhou Pan; Ngoc M. Vu; Akshaya Subbaraya Bhat; Arya Ghatak Choudhury; Jia Liu; Neil Cruz Pomerleau; Howard Mario Narvaez; Kelly K. Hosokawa; Ryan A. Espiritu - Web page: https://patentgrep.com/patent/US11310184B1 ## CPC - H04L 51/18: Commands or executable codes - G06F 3/0481: based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance - 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 40/30: Semantic analysis - G06N 3/0499: Feedforward networks - G06N 3/09: Supervised learning - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages - G06N 3/08: Learning methods - 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 Methods are presented for classifying responses to communications. One method includes presenting, in a first user interface (UI), a message from a sender to a recipient requesting a response. The first UI includes response options of a first classification, a second classification, and an entry field for entering a free text message. Another operation is for receiving a recipient response with a selection of: (a) the first or the second button and (b) the free text message entered in the text entry field. The method further includes generating a featurized recipient response based on the free text message and the selection. An acceptance machine-learning (ML) model calculates a classification value of the recipient response from a set of possible classification values based on the featurized recipient response. The method further includes presenting, in a second UI for the sender, an indicator for the message and the calculated classification value. ## Claims ### Claim 1 A computer-implemented method comprising: causing presentation in a first user interface (UI) of a message from a sender to a recipient, the message requesting a response from the recipient, the first UI including response options comprising: a first button to select a first classification; a second button to select a second classification; and a text entry field for entering a free text message; receiving a recipient response that includes a selection of: (a) either the first button or the second button and (b) the free text message entered in the text entry field; generating a featurized recipient response vector based on the free text message and the selection; calculating, by an acceptance machine-learning (ML) model, a classification value of the recipient response from a plurality of classification values based on the featurized recipient response vector; and presenting, in a second UI for the sender, an indicator for the message and the calculated classification value, wherein the presentation in the second UI is based on the calculated classification value. ### Claim 2 (depends on 1) The method as recited in claim 1, wherein the acceptance ML model is generated by an ML program based on training data that includes one or more of: (a) information about recipient responses to requests including text responses and button selections, and (b) classification values of the responses to the requests. ### Claim 3 (depends on 2) The method as recited in claim 2, further comprising: generating training data based on the recipient responses to requests, the generating the training data comprising: presenting in a third UI a message requesting a response from the recipient; enabling the recipient to select one of the first classification or the second classification; and adding in the training data information about the message requesting the response and the selection by the recipient. ### Claim 4 (depends on 2) The method as recited in claim 2, wherein the acceptance ML model is based on features comprising: the requests to the recipients; the responses to the requests; the text embeddings of the responses to the requests; and the classification value of the responses to the requests. ### Claim 5 (depends on 4) The method as recited in claim 4, wherein the features further comprise one or more of: user profile information; information associated with the requests; and information about a company associated with the request. ### Claim 6 (depends on 1) The method as recited in claim 1, wherein generating the featurized recipient response vector comprises: utilizing a natural language processor to generate the featurized recipient response vector based on a semantic meaning of the free text message. ### Claim 7 (depends on 1) The method as recited in claim 1, wherein the first classification is to accept the request and the second classification is to reject the request. ### Claim 8 (depends on 7) The method as recited in claim 7, wherein presenting in the second UI further comprises: providing, in the second UI, a first folder for accepted requests and a second folder for rejected requests. ### Claim 9 (depends on 1) The method as recited in claim 1, wherein the message is a request from a recruiter for an employment opportunity. ### Claim 10 (depends on 1) The method as recited in claim 1, wherein the message is one of an offer of a product for sale, an offer of a service for sale, or a survey. ### Claim 11 A system comprising: a memory comprising instructions; and one or more computer processors, wherein the instructions, when executed by the one or more computer processors, cause the system to perform operations comprising: causing presentation in a first user interface (UI) of a message from a sender to a recipient, the message requesting a response from the recipient, the first UI including response options comprising: a first button to select a first classification; a second button to select a second classification; and a text entry field for entering a free text message; receiving a recipient response that includes a selection of: (a) either the first button or the second button and the free text message entered in the text entry field; generating a featurized recipient response vector based on the free text message and the selection; calculating, by an acceptance machine-learning (ML) model, a classification value of the recipient response from a plurality of classification values based on the featurized recipient response vector; and presenting, in a second UI for the sender, an indicator for the message and the calculated classification value, wherein the presentation in the second UI is based on the calculated classification value. ### Claim 12 (depends on 11) The system as recited in claim 11, wherein the acceptance ML model is generated by an ML program based on training data that includes one or more of: (a) information about recipient responses to requests including text responses and button selections, and (b) classification values of the responses to the requests. ### Claim 13 (depends on 12) The system as recited in claim 12, wherein the instructions further cause the one or more computer processors to perform operations comprising: generating training data based on the recipient responses to requests, the generating the training data comprising: presenting in a third UI a message requesting a response from the recipient; enabling the recipient to select one of the first classification or the second classification; and adding in the training data information about the message requesting the response and the selection by the recipient. ### Claim 14 (depends on 12) The system as recited in claim 12, wherein the acceptance ML model is based on features comprising: the requests to the recipients; the responses to the requests; the text embeddings of the responses to the requests; and the classification value of the responses to the requests. ### Claim 15 (depends on 14) The system as recited in claim 14, wherein the features further comprise one or more of; user profile information; information associated with the requests; and information about a company associated with the request. ### Claim 16 (depends on 11) The system as recited in claim 11, wherein generating the featurized recipient response vector comprises: utilizing a natural language processor to generate the featurized recipient response vector based on a semantic meaning of the free text message. ### Claim 17 (depends on 11) The system as recited in claim 11, wherein the first classification is to accept the request and the second classification is to reject the request. ### Claim 18 (depends on 11) The system as recited in claim 11, wherein presenting in the second UI further comprises: providing, in the second UI, a first folder for accepted requests and a second folder for rejected requests. ### Claim 19 A non-transitory machine-readable storage medium including instructions that, when executed by a machine, cause the machine to perform operations comprising: causing presentation in a first user interface (UI) of a message from a sender to a recipient, the message requesting a response from the recipient, the first UI including response options comprising: a first button to select a first classification; a second button to select a second classification; and a text entry field for entering a free text message; receiving a recipient response that includes a selection of: (a) either the first button or the second button and (b) the free text message entered in the text entry field; generating a featurized recipient response vector based on the free text message and the selection; calculating, by an acceptance machine-learning (ML) model, a classification value of the recipient response from a plurality of classification values based on the featurized recipient response vector; and presenting, in a second UI for the sender, an indicator for the message and the calculated classification value, wherein the presentation in the second UI is based on the calculated classification value. ### Claim 20 (depends on 19) The non-transitory machine-readable storage medium as recited in claim 19, wherein the ML model is generated by an ML program based on training data that includes one or more of: (a) information about recipient responses to requests including text responses and button selections, and (b) classification values of the responses to the requests.