International Business Machines Corporation

Juniper Networks, Inc.

O9 Solutions, Inc.

Wells Fargo Bank, N.a.

Amazon Technologies, Inc.

Oracle International Corporation

Yahoo! Inc.

Amit Agarwal

Peyush Gupta

Srivathsa Sarangapani

Abhishek Kumar

Uma Maheswara R Chandolu

Dipanjan Deb

Naveen Gururaja Yeri

Koustuv Chatterjee

Faraz Ahmad

Kulbhushan Pachauri

B Anthony Joseph

Chakradhar Gottemukkala

Umesh Arasu

Sean M O'Neill

Raghav Ranganathan

Siddarth Wardhan

Rajeev Karri

Joshua B Sandbulte

Chetan L Gaonkar

Shailaja Mallya

Xiaohan Qin

Pedro V Torres

Jun Qian

Xinya Wang

Krishna Leela Poola

Sapna Jayaram Rai

Rajesh Goli

Iman Zadeh

Mayank Kumari

Oleg Kiselev

Xiao Ma

Arihant Sethia

Julia A Kosheleva-Coates

Techniques are described for generating a set of emotion factor values using one or more machine learning models for customer communications. For example, a computing system includes one or more processors in communication with a memory. The one or more processors are configured to receive communication data of a current communication associated with a customer, apply the communication data to an emotion-based indexer as input wherein the emotion-based indexer includes a set of machine-learning models for a set of emotion factors, generate as output from the emotion-based indexer a set of emotion factor values for the current communication wherein each emotion factor value indicates the measure of a particular emotion factor in the current communication, apply the set of emotion factor values to an emotion classification model, and classify the current communication into an emotion state based on the set of emotion factor values.

Emotion analysis using deep learning model

A computing device may access visually rich documents comprising an image and metadata. A graph, based on the image or metadata, can be generated for a visually rich document. The graph's nodes can correspond to words from the visually rich document. Features for nodes can be determined by the device. The device may generate model labeled graphs by assigning a pseudo-label to nodes using a pretrained model. The device may generate a plurality of graph labeled graphs by assigning a pseudo-label to nodes by matching a first node from a first graph to at least a second node from a second graph. The device may generate a plurality of updated graphs by cross referencing labels from the model labeled graphs and the graph labeled graphs. Until a change in labels is below a threshold, a model can be trained to perform key-value extraction using the updated graphs.

Pseudo labelling for key-value extraction from documents

Techniques are described for personalizing customer interactions using one or more machine learning models for customer communications. For example, a computing system includes a memory and one or more processors in communication with the memory. The one or more processors are configured to: retrieve, from a database in memory, one or more sets of emotion factor values for communication data associated with a customer over time; classify, using an emotion propensity model running on the one or more processors, the customer into an emotional profile according to the customer's typical emotional response during customer communications based on the one or more sets of emotion factor values for the communication data associated with the customer over time; and determine a probability that the customer will respond positively to a particular type of customer engagement based on the emotional profile for the customer.

Predicting customer interaction using deep learning model

An unstructured data input is accessed that includes an electronic communication. Content of the unstructured data is parsed to determine one or more terms in the unstructured data input. It is determined that one or more particular elements defined in a structured business data model correspond to the terms. Tags are assigned to the unstructured data based on the terms corresponding to the one or more particular elements, where the tags define an association between the unstructured data and the structured data model.

Unstructured data processing in plan modeling

Techniques are described for determining a likelihood that a customer communication is fraudulent using one or more machine learning models. For example, a computing system includes a memory and one or more processors in communication with the memory. The one or more processors are configured to: receive a set of emotion factor values for communication data of a current communication associated with a customer, wherein each emotion factor value indicates a measure of a particular emotion factor in the current communication; classify, using an emotion variance model running on the one or more processors, the current communication into an emotional fraud category based on the set of emotion factor values for the current communication associated with the customer; and determine a risk score for the current communication indicative of a probability that the current communication is fraudulent based on at least the emotional fraud category for the current communication.

Fraud detection using emotion-based deep learning model

A computing device may receive a set of user documents. Data may be extracted from the documents to generate a first graph data structure with one or more initial graphs containing key-value pairs. A model may be trained on the first graph data structure to classify the pairs. Until a set of evaluation metrics for the model exceeds a set of deployment thresholds: generating, a set of evaluation metrics may be generated for the model. The set of evaluation metrics may be compared to the set of deployment thresholds. In response to a determination that the set of evaluation metrics are below the set of deployment thresholds: one or more new graphs may be generated from the one or more initial graphs in the first graph data structure to produce a second graph data structure. The first and second graph can be used to train the model.

Techniques for graph data structure augmentation

Techniques are described for performing complaint prioritization using one or more machine learning models for customer communications. For example, a computing system includes a memory and one or more processors in communication with the memory. The one or more processors are configured to receive communication data indicative of a service inquiry from a user device, generate a set of emotion factor values that indicate a measure of particular emotions in the service inquiry, determine, using a machine learning model and based on the set of emotion factor values, an emotional priority score for the service inquiry, and determine a response priority order for the service inquiry based on at least the emotional priority score.

Complaint prioritization using deep learning model

Disclosed in some examples are methods, systems, and machine readable mediums which provide summaries of topics determined within a corpus of documents. These summaries may be used by customer service associates, analysts, or other users to quickly determine both topics discussed and contexts of those topics over a large corpus of text. For example, a corpus of documents may be related to customer complaints and the topics may be summarized to produce summaries such as 'credit report update due to stolen identity.' These summarizations may be used to efficiently spot trends and issues.

Dynamic topic definition generator

A return address of a caller of a software function within an access control component is determined, the caller comprising a software component seeking access to a protected resource protected by the access control component. From the return address, a filename of the caller is determined. Responsive to determining that the filename is included in a set of filenames of components allowed to access the protected resource, the caller is allowed to access the protected resource.

Secure data storage device access control and sharing

Systems and methods automatically generate a low input visualization of data updated in a workbook. One aspect describes a computer-implemented method comprising obtaining a request to update data in an application workbook for an application. The request comprises an indication of a type of update being requested and at least a subset of the data being updated. The method further comprises performing the update of the data in the application workbook and determining that the performed update of the data in the application workbook results in a change to a visualization of the data. The method also comprises generating an updated visualization based on the received request and the updated application workbook and generating a confirmation message that the updated visualization has been generated, wherein the updated visualization is generated automatically based on the update of the data.

Application development based on stored data

An interactive user interface is generated to illustrate a graphical view of a network of plan models. The network of plan models includes a plurality of plan models, each plan model including one or more measures and one or more dimensions. At least one user-entered text character is entered in a query field and the plan models are searched for names of measures and/or dimensions in the plan models that correspond to the user entry. The names are presented as search term suggestions in the search query field and at least one suggestion is selected and adopted as at least a portion of a search query. The network of plan models is searched to generate search results corresponding to the search query. The graphical view of the network of plan models can be revised based on the search results.

Plan model searching

A proposed modification to a record of a base data structure is identified, the records of the base data structure sorted by primary key. A type of modification of the proposed modification is identified. A record is added to a differential data structure of the type, the differential data structure record describing the proposed modification. A record is added to a delta data structure sorted by the primary key, the delta data structure record including the primary key value of the record, the type of the proposed modification, and a pointer to the record added to the differential data structure. Data can be fetched using the delta data structure to apply modifications to a set of records requested in the fetch and generate a modified set of records to be returned in a response to the request.

Regressable differential data structures

Growing community of inventors

Bengaluru, India

Amit Agarwal