40991 results about "Machine learning" patented technology

Techniques for negotiation techniques for mobile personal trusted device financial transactions are provided. A user of a mobile personal trusted device sets user preferences that define the user's preferred parameters for conducting financial transactions. A merchant sets merchant preferences that define the merchant's preferred parameters for conducting financial transactions. When a financial transaction is initiated, a user preference and a merchant preferences are accessed. A negotiated preference is generated that accommodates both the user preference and the merchant preference. If the user preference and the merchant preference are not mutually exclusive, the negotiated preference attempts to satisfy both preferences. If the user preference and the merchant preference are mutually exclusive, the negotiated preference satisfies at least one of the two preferences based on which of the two preferences has a higher priority. The financial transaction is conducted based on the negotiated preference.

A triggering mechanism for generating task reminders based on contextual information associated with the tasks is provided. Contextual information may be extracted from a variety of sources and may be related to one or more tasks. Based on the contextual information, task reminders may be generated and may be presented in a manner that makes the task reminders more useful to an end user.

Diffusing evidence among candidate answers during question answering may identify a relationship between a first candidate answer and a second candidate answer, wherein the candidate answers are generated by a question-answering computer process, the candidate answers have associated supporting evidence, and the candidate answers have associated confidence scores. All or some of the evidence may be transferred from the first candidate answer to the second candidate answer based on the identified relationship. A new confidence score may be computed for the second candidate answer based on the transferred evidence.

Financial data including general ledger activity and underlying journal entries are examined to determine whether risks of material misstatement due to fraudulent financial reporting can be identified. The financial data is analyzed statistically and modeled over time, comparing actual data values with predicted data values to identify anomalies in the financial data. The anomalous financial data is then analyzed using clustering algorithms to identify common characteristics of the various transactions underlying the anomalies. The common characteristics are then compared with characteristics derived from data known to derive from fraudulent activity, and the common characteristics are reported, along with a weight or probability that the anomaly associated with the common characteristic is an identification of risks of material misstatement due to fraud. Large volumes of financial data are therefore efficiently processed to accurately identify risks of material misstatement due to fraud in connection with financial audits, or for actual detection of fraud in connection with forensic and investigative accounting activities. The analysis is enhanced by using flow analysis methods to select subsets of financial data to examine for anomalies. Flow analysis methods are also used to reveal useful business information found in money flow graphs of financial data.

Applying a bias when determining a suggested search query. Examples of biases that can be applied include, but are not limited to, temporal biases and monetization biases. Temporal biasing involves increasing a weight associated with a search query, based on a temporal attribute associated with the query. Search queries may also have associated with them a parameter such as frequency, count, etc. One of these parameters may serve as a weight. In order to determine suggested search queries, the temporal attribute is used to modify or bias the parameter (e.g., frequency parameter). Thus, the weight of the search query is modified to temporally bias the query. The suggested search queries are determined based on the biased parameter.

According to one embodiment, an apparatus comprises a detection engine and a classification engine. The detection engine is responsible for analyzing an object to determine if the object is malicious. The classification engine is configured to (i) receive results of the analysis of the object conducted by the detection engine and (ii) analyze, based at least in part on the results from the detection engine, whether the object is malicious in accordance with a predictive model. Responsive to the detection engine and the classification engine differing in determinations as to whether the object is malicious, information associated with at least a portion of the results of the analysis of the object by at least one of the detection engine and the classification engine is uploaded for determining whether an update of the predictive model is to occur. An update of the predictive model is subsequently received by the classification engine.