Streamline your patent due diligence with deep analytics for patents, inventors, and attorneys

Compare patents by technology sector

Deep Analytics

Quickly evaluate patents of interest

► Want to see more? Join for free!

PatentQuant Patent Profile
Generated January 22, 2018

Pattern recognition using an observable operator model

Patent Number: 6,845,357

Patent Information

Data structures, systems, and methods are aspects of pattern recognition using observable operator models (OOMs). OOMs are more efficient than Hidden Markov Models (HMMs). A data structure for an OOM has characteristic events, an initial distribution vector, a probability transition matrix, an occurrence count matrix, and at least one observable operator. System applications include computer systems, cellular phones, wearable computers, home control systems, fire safety or security systems, PDAs, and flight systems. A method of pattern recognition comprises training OOMs, receiving unknown input, computing matching probabilities, selecting the maximum probability, and displaying the match. A method of speech recognition comprises sampling a first input stream, performing a spectral analysis, clustering, training OOMs, and recognizing speech using the OOMs.
Patent Number: 6,845,357
Issue Date: 2005-01-18

Primary Category

Biographical Information

Executive Summary


This patent was granted in ► Log In, which is ► Log In speed.

It has ► Log In claims, which is ► Log In than average for this category.

Its proximity to basic research is ► Log In than others in this category, and it displays ► Log In technology cycle time.

This patent received ► Log In citations from other patents, and references ► Log In other patents, as compared to other patents in this category.

Grant Time

► Log In


► Log In

► Want to see more? Join for free!

PatentStat Scores in Not categorized
These scores show the percentile ranks for each metric.
For example, a score of 90 means that 90% of similar patents had lower scores.

Patent Grant Time

This patent had ► Log In grant time compared to others in this category.

Patent grant time can be influenced by many factors. Activities within the USPTO that are beyond the control of patent attornies can influence grant time, but short grant times can also indicate well-written patents and dedicated efforts to respond rapidly to USPTO office actions with strong arguments. Shorter grant times are preferable, and the scores for this section are inverse measures — higher scores are better.

Patent Claims

This patent has ► Log In claims compared to others in this category.

The number of claims in a patent is correlated with its strength. Because greater claim counts increase the cost of a patent, more claims can indicate the importance an applicant assigns to a patent. Importantly, some may elect to file claims across multiple patents. A higher score in this metric indicates more claims, relative to others in this category.

Citations From Other Patents

This patent has received ► Log In citations from other patents, than others in this category.

Citations from other patents are an important measure of the significance of a patent. More citations indicate that other technologies build on a patent. Higher scores in this metric are better, and indicate more citations from other patents.

Citations to Other Patents

This patent referenced ► Log In citations to other patents, than others in this category.

A lower number of citations to other patents can be a sign of diminished patent strength. More citations indicate dependence on more other technologies. Higher scores in this category are better, and indicate fewer citations to other patents.

Research and Innovation Indicators
These are percentile ranks — they indicate the percentage of peers with lower scores.

Proximity to Basic Research

► Log In


Proximity to Basic Research

This patent has ► Log In proximity to basic research compared to others in this category.

Proximity to basic research is measured by comparing the number of citations to non-patent literature among a cohort of patents. Because most non-patent citations are primary research papers, a higher count indicates greater proximity to basic research.

► Want to see more? Join for free!


Patents cited by this patent

Patent Title
6,151,592 Recognition apparatus using neural network, and learning method therefor
6,151,574 Technique for adaptation of hidden markov models for speech recognition
6,052,662 Speech processing using maximum likelihood continuity mapping
5,983,186 Voice-activated interactive speech recognition device and method
5,860,062 Speech recognition apparatus and speech recognition method
5,857,169 Method and system for pattern recognition based on tree organized probability densities

Patents that cite this patent

Patent Title
9,240,184 Frame-level combination of deep neural network and gaussian mixture models
9,239,986 Assessing accuracy of trained predictive models
9,189,747 Predictive analytic modeling platform
9,172,918 Systems and methods for managing live video data
8,909,568 Predictive analytic modeling platform
8,878,931 Systems and methods for managing video data
8,768,692 Speech recognition method, speech recognition apparatus and computer program
8,706,659 Predictive analytic modeling platform
8,595,154 Dynamic predictive modeling platform
8,533,224 Assessing accuracy of trained predictive models
8,533,222 Updateable predictive analytical modeling
8,484,022 Adaptive auto-encoders
8,473,431 Predictive analytic modeling platform
8,438,122 Predictive analytic modeling platform
7,974,977 Spectral clustering using sequential matrix compression
7,881,537 Automated activity detection using supervised learning
7,760,908 Event packaged video sequence
7,606,425 Unsupervised learning of events in a video sequence

► Want to see more? Join for free!

Information presented on this site is collected from the USPTO and other sources. Errors may have been introduced in the original assembly or analysis of the data.
No warranties are expressed or implied.The content of this site is not a substitute for skilled legal, financial, or other guidance.
Copyright thinkBiotech LLC. All rights reserved.
Privacy policy.