# US 12,111,885 B2 · Image dispositioning using machine learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,111,885 B2 - Document ID: US12111885B2 - Status: Granted - Kind: B2 - Application number: 17/359,959 - Filed: 2021-06-28 - Published: 2022-12-29 - Granted: 2024-10-08 - Earliest claimed: 2021-06-28 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Mayoore Selvarasa Jaiswal; Anne Elizabeth Gattiker; Matthew Comer; Mary D. Swift; Ambal Balakrishnan; Florian Pinel - Web page: https://patentgrep.com/patent/US12111885B2 ## CPC - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06V 10/82: using neural networks - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting - G06V 10/803: {of input or preprocessed data} - G06V 20/30: in albums, collections or shared content, e.g. social network photos or video - G06V 20/35: {Categorising the entire scene, e.g. birthday party or wedding scene} - G06N 5/045: Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Provided is a method, computer program product, and system for predicting image sharing decisions using machine learning. A processor may receive a set of annotated images and an associated text input from each user of a plurality of users. The processor may train, using the set of annotated images and the associated text input from each user, a neural network model to output an image sharing decision that is specific to a user. ## Claims ### Claim 1 A computer-implemented method comprising: receiving an annotated set of images and an associated text input from each user of a plurality of users, wherein the associated text input from each user comprises a set of questions and answers related to image sharing preferences, and the associated text input is separate from annotations associated with the annotated set of images; and training, using the annotated set of images and the associated text input from each user of the plurality of users, a neural network model to output an image sharing decision for an unannotated image that is specific to a user. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising: receiving a first image and a text input from a first user; applying the neural network model to the first image and the first text input; and providing a first image sharing decision for the first image to the first user. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the associated text input is encoded before being input to the neural network model. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the neural network model is a two-stream neural network that comprises components of both a convolutional neural network and a recurrent neural network. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein each image in the set of annotated images received from each user is annotated with the respective user's image sharing preferences for the image. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein a training sample used to train the neural network model comprises an image annotated with a respective user's sharing preference for the image and a text input associated with the respective user. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the image sharing decision provided to the user indicates a confidence in the image sharing decision. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein the neural network model is a 4-channel convolutional neural network. ### Claim 9 (depends on 8) The computer-implemented method of claim 8, wherein a first input to 3 of the input channels is an image and a second input to the 4th channel is a text input. ### Claim 10 A system comprising: a processor; and a computer-readable storage medium communicatively coupled to the processor and storing program instructions which, when executed by the processor, cause the processor to perform a method comprising: receiving an annotated set of images and an associated text input from each user of a plurality of users, wherein the associated text input from each user comprises a set of questions and answers related to image sharing preferences, and the associated text input is separate from annotations associated with the annotated set of images; and training, using the annotated set of images and the associated text input from each user of the plurality of users, a neural network model to output an image sharing decision for an unannotated image that is specific to a user. ### Claim 11 (depends on 10) The system of claim 10, wherein the method performed by the processor further comprises: receiving a first image and a text input from a first user; applying the neural network model to the first image and the first text input; and providing a first image sharing decision for the first image to the first user. ### Claim 12 (depends on 10) The system of claim 10, wherein the associated text input is encoded before being input to the neural network model. ### Claim 13 (depends on 10) The system of claim 10, wherein the neural network model is a two-stream neural network that comprises components of both a convolutional neural network and a recurrent neural network. ### Claim 14 A computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising: receiving an annotated set of images and an associated text input from each user of a plurality of users, wherein the associated text input from each user comprises a set of questions and answers related to image sharing preferences, and the associated text input is separate from annotations associated with the annotated set of images; and training, using the annotated set of images and the associated text input from each user of the plurality of users, a neural network model to output an image sharing decision for an unannotated image that is specific to a user. ### Claim 15 (depends on 14) The computer program product of claim 14, wherein the method performed by the processor further comprises: receiving a first image and a text input from a first user; applying the neural network model to the first image and the first text input; and providing a first image sharing decision for the first image to the first user. ### Claim 16 (depends on 14) The computer program product of claim 14, wherein the associated text input is encoded before being input to the neural network model. ### Claim 17 (depends on 14) The computer program product of claim 14, wherein the neural network model is a two-stream neural network that comprises components of both a convolutional neural network and a recurrent neural network. ### Claim 18 (depends on 1) The computer-implemented method of claim 1, wherein text words of each question of the set of questions and answers are encoded using a pre-trained word embedding and each answer is a numeric representation of a yes or no answer. ### Claim 19 (depends on 18) The computer-implemented method of claim 18, wherein a question-answer vector is formed from each encoded question and answer pair.