International Business Machines Corporation

Marisa Affonso Vasconcelos

Heloisa Caroline De Souza Pereira Candello

Carlos Henrique Cardonha

Claudio Santos Pinhanez

Andrea Britto Mattos Lima

Miguel Paredes Quinones

Vagner Figueredo De Santana

Ana Paula Appel

Alan Braz

Mauro Carlos Pichiliani

Ricardo Vieira Borges Franco

Marco Aurelio Stelmar Netto

Mu Qiao

Jaione Tirapu Azpiroz

Priscilla Barreira Avegliano

Paulo Rodrigo Cavalin

Rogerio Abreu De Paula

Yuya Jeremy Ong

Igor Cerqueira Oliveira

Nicholas Linck

Jorge Luis Guevara Diaz

Dario Augusto Borges Oliveira

Bernardo Nunes Goncalves

A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations that include analyzing interactions by a user within a network and generating a user profile for the user. The operations by the processor may further include identifying an attempt by the user to share a post via the network and prompting the user with a personalized alert to evaluate the post, wherein the personalized alert is generated based on the interactions, the user profile, and the properties of the post.

Personalized alert generation based on information dissemination

A computer-implemented method, a computer program product, and a computer system for misinformative content mitigation. A computer receives from a social network system a request for curated content, where the curated content is related to misinformative content that has been identified by the social network system. The computer sends to a system of a paid curated content producer a request for making the curated content public. In response to that the system of the paid curated content producer accepts the request for making the curated content public, the computer provides to the social network system a link to the curated content on the system of the paid curated content producer. On the social network system, the misinformative content is flagged and the link to the curated content is presented aside the misinformative content.

Mediating between social networks and payed curated content producers in misinformative content mitigation

A system for providing permissioned images in media transactions is described. The system processes images in an image set for a media transaction to identify the image owner and other persons depicted in the image and determines use permissions for the images. Various images in the image set are processed to remove or anonymize various persons in order to meet use conditions. The processed images are compiled and provided to an entity requesting the image set.

Media transactions consent management

A computer completes a data image analysis task. The computer receives a machine learning (ML) model trained for use with image data content characterized by first context. The computer receives an evaluation image dataset having evaluation image data content characterized by a second context. The computer receives a request to complete an image data analysis task for the evaluation image dataset using the ML model. The computer compares the contexts to determine whether the contexts are similar and whether the evaluation image dataset is compatible with the ML model. If the evaluation dataset is incompatible with the ML model, the computer uses the generative model to generate a ML model compatible synthetic image dataset based on the evaluation dataset. The computer applies the ML model to the synthetic image dataset to provide an answer for the data image analysis task; the computer delivers the answer to a user interface.

Artificial intelligence generated synthetic image data for use with machine language models

In an approach to training a chatbot for remote troubleshooting, one or more computer processors receive a request for help with an issue from a user via a chatbot. One or more computer processors extract information associated with the issue from the request. One or more computer processors determine a script is not available to resolve the issue. One or more computer processors request an agent to resolve the issue. One or more computer processors monitor one or more actions performed by the agent to resolve the issue. Based on the one or more actions, one or more computer processors generate a script, wherein the script includes a sequence of commands corresponding to the one or more actions. One or more computer processors store the script.

Training chatbots for remote troubleshooting

A method and system of mitigating bias in a decision-making system are provided. A presence of bias is identified in one or more machine learning models. For each of the machine learning models, a presence of bias in an output of the model is determined. One or more options to mitigate a system bias during a processing stage, based on the identified presence of bias for each of the one or more models, are determined. One or more options to mitigate the system bias during a post-processing stage, based on the identified presence of bias in each output of the models, are determined. A combination of options is provided, including (i) a processing option for the processing stage, and (ii) a post-processing option for the post-processing stage, wherein the combination of options accommodates a threshold bias limit to the system bias and a total bias mitigation cost threshold.

Audit machine learning models against bias

Aspects discussed herein include a computer-implemented method comprising receiving a support request from a user, and during a current support session responsive to the support request, performing textual analysis of one or more inputs provided by the user during one or both of: (i) the current support session and (ii) one or more previous support sessions. The method further comprises applying one or more features determined by the textual analysis to a model to classify the user into a first class of a predefined plurality of classes that describe a pace of conversation during the current support session. The method further comprises, based on the classification of the user, assigning the support request to be fulfilled by a first operator of a predefined plurality of support operators.

Support request assignment using pace of conversation

A computer system includes a processor configured to execute a conversational agent generator function. The conversational agent generator function is configured to receive a plurality of model input queries. Each model input query includes an intent and a corresponding answer to the intent. A database stores a corpus including sets of textual responses indicative of a common meaning. Each textual response in a given set of textual responses indicates a common meaning constructed in a different style indicative of a corresponding tone of communication. The processor is further configured to execute a rephrasing function configured determine the answer of one of the plurality of model input queries, and convert the answer of one of the plurality of model input queries into a plurality of different rephrased answers from the corpus stored in the database. The processor further outputs the plurality of different rephrased answers to the conversational agent generator function.

Adapting conversational agent communications to different stylistic models

Techniques relate to adapting communications. A computer system receives initial content and event constraints related to a to-be-delivered communication and extracts information for recipients designated to receive the to-be-delivered communication. The computer system determines content utility values for topics of the initial content for each of the recipients, the content utility values for each of the topics being based on the information for each of the recipients. The computer system determines total content utility values for each of the topics in the initial content and selects elements of the to-be-delivered communication from a database based at least in part on the total content utility values for the topics and the event constraints.

Adapting communications according to audience profile from social media

A wait time control method, system, and computer program product, includes extracting wait times for treatment at emergency facilities and routing times to the emergency facilities based on an emergency request and assigning a patient to an emergency facility by calculating a minimal treatment time for the patient comprising a minimum combined time of a wait time at the emergency facility and a routing time to the emergency facility from a location of the emergency request.

System, method and computer program product for dispatching of medical emergencies and wait time control

Systems and methods are described for supply chain vulnerability forecasting using external event data is described. The method may include identifying historic data from each entity of a plurality of entities connected in a supply chain, aggregating temporal-based information relating to the entities and to relations among the entities into one or more time periods based on the historic data, training a cognitive prediction model using the aggregated temporal-based information, generating a vulnerability score for each entity, generating a recommendation for at least one entity if the vulnerability score for the at least one entity is above a preset threshold, retraining the cognitive prediction model using changed data of the at least one entity, and adjusting the vulnerability score based on the retraining.

Supply chain forecasting system

Techniques for image analysis and configuration modification are provided. A first context of a camera device is determined, where the first context includes a current location of the camera device. A plurality of prior images is identified based on the first context, where each of the plurality of prior images was captured within a predefined distance from the current location of the camera device. Further, a respective popularity score is generated for each of the plurality of prior images, based on one or more social media networks. Finally, a first set of configuration parameters is generated for the camera device, based at least in part on (i) a degree of difference between the first context and a second context associated with a first prior image of the plurality of prior images, and (ii) a first popularity score of the first prior image.

Generating image capture configurations and compositions

A conversational agent capability assessment method, system, and computer program product, includes assessing a performance, a personality and a cognitive trait of a conversational agent based on natural written language by a second conversational agent by combining an analysis of a plurality of metrics that each compare a metric from the conversational agent with a metric from the second conversational agent and producing a report detailing the performance, the personality, and the cognitive trait of the conversational agent.

System, method and computer program product for assessing the capabilities of a conversation agent via black box testing

A processor-implemented method for providing merchants business advice, the method including: providing a merchant with a dashboard, the dashboard including information related to the merchant's business and a communication link to the merchant's financial institution; receiving a request from the merchant via the dashboard, the request being for a service provided by the merchant's financial institution; processing the request from the merchant by using data about the merchant's business; and providing a response to the request for viewing at the dashboard by the merchant.

Human steering dashboard to analyze 360-degree market view for merchants based on financial transactions

A conversational agent capability assessment method, system, and computer program product, includes obtaining data to create at least one scenario for testing a conversational agent, performing a set of tests using a scenario of the at least one scenario created to assess a capability of the conversational agent, and comparing a result of the capability from the set of tests with an expected result of the scenario.

Growing community of inventors

São Paulo, Brazil

Marisa Affonso Vasconcelos