Abstract: The present disclosure describes a patent management system and method for remediating insufficiency of input data for a machine learning system. A plurality of data vectors using data from a plurality of data sources are extracted. A user input with respect to an input data context is received. An input vector based on the user input is generated and a set of matching data vectors are determined from the plurality of data vectors based on the input vector. Data vectors in the set of matching data vectors are determined to be thick data or thin data based on a comparison of a number of matching data vectors with a first pre-determined threshold, and/or a variance with a second pre-determined threshold. Further, the set of matching data vectors are expanded by modifying the input vector when the input data is determined to be insufficient based on a selection of a recommendation.

Abstract: The present disclosure describes a patent management system and method for remediating insufficiency of input data for a machine learning system. A plurality of data vectors using data from a plurality of data sources are extracted. A user input with respect to an input data context is received. An input vector based on the user input is generated and a set of matching data vectors are determined from the plurality of data vectors based on the input vector. Data vectors in the set of matching data vectors are determined to be thick data or thin data based on a comparison of a number of matching data vectors with a first pre-determined threshold, and/or a variance with a second pre-determined threshold. Further, the set of matching data vectors are expanded by modifying the input vector when the input data is determined to be insufficient based on a selection of a recommendation.

Abstract: A compliance testing system for generating a compliance prediction for a test target. Determinate factors and indeterminate factors associated with a current testing stage of the test target are identified. A test vector for each of the indeterminate factors is generated. A set of matching test vectors for each of the indeterminate factors is determined based on the test vector. The set of matching test vectors are determined using data extracted from at least one profile model. A cumulative factor value is determined for each of the indeterminate factors based on the set of matching test vectors. A first outcome is generated for each of the determinate factors. A second outcome is generated for each of the indeterminate factors, based on the cumulative factor value and the set of matching test vectors. A compliance prediction is generated for the test target based on the first outcome and the second outcome.

Abstract: The present disclosure receives input signals from different sources to fill gaps in a desired heat score signal. Received input signals are categorized to match to a desired category of the desired signal. The various signals are represented in vector format using category tags. There are different latencies for each input signal that are aligned in time with the desired signal. The match to the desired signal varies from the input signals so that each desired signal's contribution during the gap is weighted accordingly. A composite signal is formulated from the time-adjusted and weighted input signals to fill the gap in the desired signal. Over time, the weighting and time-adjustment for each input signal can be modified with a machine learning algorithm that takes the approximation during the gap and compares it later with the actual data once the gap is filled.

Abstract: The present disclosure describes a patent management system and method for remediating insufficiency of input data for a machine learning system. A plurality of data vectors using data are extracted from a plurality of data sources. A user input with respect to an input data context is received, the input data context correspond to a subset of the plurality of data elements. An input vector based on the user input is generated and a set of matching data vectors are determined from the plurality of data vectors based on the input vector. An insufficiency of the input data is determined based on a comparison of a number of matching data vectors with a first pre-determined threshold, and/or a variance with a second pre-determined threshold. Further, the set of matching data vectors are expanded by modifying the input vector when the input data is determined to be insufficient.

Abstract: A compliance testing system for generating a compliance prediction for a test target. Determinate factors and indeterminate factors associated with a current testing stage of the test target are identified. A test vector for each of the indeterminate factors is generated. A set of matching test vectors for each of the indeterminate factors is determined based on the test vector. The set of matching test vectors are determined using data extracted from at least one profile model. A cumulative factor value is determined for each of the indeterminate factors based on the set of matching test vectors. A first outcome is generated for each of the determinate factors. A second outcome is generated for each of the indeterminate factors, based on the cumulative factor value and the set of matching test vectors. A compliance prediction is generated for the test target based on the first outcome and the second outcome.

Abstract: The present disclosure describes a patent management system and method for remediating insufficiency of input data for a machine learning system. A plurality of data vectors using data are extracted from a plurality of data sources. A user input with respect to an input data context is received, the input data context correspond to a subset of the plurality of data elements. An input vector based on the user input is generated and a set of matching data vectors are determined from the plurality of data vectors based on the input vector. An insufficiency of the input data is determined based on a comparison of a number of matching data vectors with a first pre-determined threshold, and/or a variance with a second pre-determined threshold. Further, the set of matching data vectors are expanded by modifying the input vector when the input data is determined to be insufficient.

Abstract: The present disclosure uses input signals from different sources to fill gaps in the desired signal, for example a heat score signal. Different input signals are categorized so that they can be matched to a desired category of the desired signal. The various signals can be represented in vector format using category tags, for example. There are different latencies for each input signal that is aligned in time with the desired signal. Also, the match to the desired signal may vary from the input signals so that each desired signal's contribution during the gap is weighted accordingly. A composite signal is formulated from the time-adjusted and weighted input signals to fill the gap in the desired signal. Over time, the weighting and time-adjustment for each input signal can be modified with a learning algorithm that takes the approximation during the gap and compares it later with the actual data once the gap is filled in one embodiment.

Abstract: A method and system for determining of timing for vector following a branched processing model is disclosed. A data source is mined to determine event vectors from a large number of cases that follow a branched processing model. Current event vectors are compared to the mined event vectors with machine learning to predict future nodes for the current event vectors. Historical temporal spacing for the mined event vectors are used to predict temporal position for the current event vector in the future.

Abstract: A method and system for allocation of resources is disclosed. A data source is mined to determine event vectors from a large number of cases that follow a branched processing model. Current event vectors are compared to the mined event vectors with machine learning to predict future nodes for the current event vectors. Historical resource allocations for the mined event vectors are used to determine resource allocation for the current event vector over time. Current event vectors are combined to produce a resource allocation curve showing past and future resources allocated.

Abstract: A method and system for allocation of resources is disclosed. Authenticated and unauthenticated data sources are mined to determine event vectors from a large number of cases that follow a branched processing model. A current event vector is compared to the mined event vectors with machine learning to predict future nodes for the current event vector. Historical resource allocations for the mined event vectors are used to determine resource allocation for the current event vector over time.