Accenture Global Services Gmbh

Accenture Global Solutions Limited

Marko Krema

Rayid Ghani

Andrew E Fano

Chad Michael Cumby

Yan Liu

Katharina Probst

Sai P Kandallu

Chad M Cumby

Divna Djordjevic

Thomas A Hsu

Ian Hook

Jose Eduardo Arias Quiros

Rebeca Gomez Vez

A device may receive a document including text, images, and one or more embedded documents. The device may parse the document to identify a content segment in the document. The device may determine a context for the content segment, wherein the context includes at least one of an entity identified by the content segment, a semantic meaning of the content segment, or an object identified by the content segment. The device may classify the content segment using a content classification model and based on the context for the content segment. The device may selectively alter the content segment based at least in part on a set of alteration rules, to generate a modified document. The device may provide the modified document based on selectively altering the content segment.

Document content classification and alteration

A method and system for using individualized customer models when operating a retail establishment is provided. The individualized customer models may be generated using statistical analysis of transaction data for the customer, thereby generating sub-models and attributes tailored to customer. The individualized customer models may be used in any aspect of a retail establishment's operations, ranging from supply chain management issues, inventory control, promotion planning (such as selecting parameters for a promotion or simulating results of a promotion), to customer interaction (such as providing a shopping list or providing individualized promotions).

System for individualized customer interaction

A plurality of topics encompassed in a document are determined and, for each such topic, a sentiment for that topic is likewise determined. Thereafter, credibility of the document is determined based on the resulting plurality of sentiments. In one embodiment, credibility of at least one target document is established by first determining, for each of a plurality of portions of the at least one target document, at least one topic encompassed in the portion to provide a plurality of target topics. Likewise, sentiment scores are determined for each portion. Thereafter, for each prior topic of a plurality of prior topics, a topic-sentiment score is determined based on sentiment scores corresponding to those portions of the plurality of portions having a target topic corresponding to the prior topic. A credibility index is determined based on the resulting plurality of topic-sentiment scores.

Performing an action related to a measure of credibility of a document

A generative model is used to develop at least one topic model and at least one sentiment model for a body of text. The at least one topic model is displayed such that, in response, a user may provide user input indicating modifications to the at least one topic model. Based on the received user input, the generative model is used to provide at least one updated topic model and at least one updated sentiment model based on the user input. Thereafter, the at least one updated topic model may again be displayed in order to solicit further user input, which further input is then used to once again update the models. The at least one updated topic model and the at least one updated sentiment model may be employed to analyze target text in order to identify topics and associated sentiments therein.

User modification of generative model for determining topics and sentiments

Method and apparatus are provided for providing one or more sentiment classifiers from training data using supervised classification techniques based on features extracted from the training data. Training data includes a plurality of units such as, but not limited to, documents, paragraphs, sentences, and clauses. A feature extraction component extracts a plurality of features from the training data, and a feature value determination component determines a value for each extracted feature based on a frequency at which each feature occurs in the training data. On the other hand, a class labeling component labels each unit of the training data according to a plurality of sentiment classes to provide labeled training data. Thereafter, a sentiment classifier generation component provides a least one sentiment classifier based on the value of each extracted feature and the labeled training data using a supervised classification technique.

Sentiment classifiers based on feature extraction

Determination of document credibility

Promotion planning system

One or more classification algorithms are applied to at least one natural language document in order to extract both attributes and values of a given product. Supervised classification algorithms, semi-supervised classification algorithms, unsupervised classification algorithms or combinations of such classification algorithms may be employed for this purpose. The at least one natural language document may be obtained via a public communication network. Two or more attributes (or two or more values) thus identified may be merged to form one or more attribute phrases or value phrases. Once attributes and values have been extracted in this manner, association or linking operations may be performed to establish attribute-value pairs that are descriptive of the product. In a presently preferred embodiment, an (unsupervised) algorithm is used to generate seed attributes and values which can then support a supervised or semi-supervised classification algorithm.

Extraction of attributes and values from natural language documents

In a machine learning system in which a plurality of learned models, each corresponding to a unique domain, already exist, new domain input for training a new domain model may be provided. Statistical characteristics of features in the new domain input are first determined. The resulting new domain statistical characteristics are then compared with statistical characteristics of features in prior input previously provided for training at least some of the plurality of learned models. Thereafter, at least one learned model of the plurality of learned models is identified as the basis for the new domain model when the new domain input statistical characteristics compare favorably with the statistical characteristics of the features in the prior input corresponding to the at least one learned model.

Determination of a basis for a new domain model based on a plurality of learned models

Performance of statistical machine learning techniques, particularly classification techniques applied to the extraction of attributes and values concerning products, is improved by preprocessing a body of text to be analyzed to remove extraneous information. The body of text is split into a plurality of segments. In an embodiment, sentence identification criteria are applied to identify sentences as the plurality of segments. Thereafter, the plurality of segments are clustered to provide a plurality of clusters. One or more of the resulting clusters are then analyzed to identify segments having low relevance to their respective clusters. Such low relevance segments are then removed from their respective clusters and, consequently, from the body of text. As the resulting relevance-filtered body of text no longer includes portions of the body of text containing mostly extraneous information, the reliability of any subsequent statistical machine learning techniques may be improved.

Preprocessing of text

A body of text comprises a plurality of unknown attributes and a plurality of unknown values. A first classification sub-component labels a first portion of the plurality of unknown values as a first set of values, whereas a second classification sub-component labels a portion of the plurality of unknown attributes as a set of attributes and a second portion of the plurality of unknown values as a second set of values. Learning models implemented by the first and second classification subcomponents are updated based on the set of attributes and the first and second set of values. The first classification sub-component implements at least one supervised classification technique, whereas the second classification sub-component implements an unsupervised and/or semi-supervised classification technique. Active learning may be employed to provide at least one of a corrected attribute and/or corrected value that may be used to update the learning models.

Growing community of inventors

Evanston, IL, United States of America

Marko Krema