Pattern recognition system
Abstract
Methods, apparatuses and systems directed to pattern learning, recognition, and metrology. In some particular implementations, the invention provides a flexible pattern recognition platform including pattern recognition engines that can be dynamically adjusted to implement specific pattern recognition configurations for individual pattern recognition applications. In certain implementations, the present invention provides for methods and systems suitable for analyzing and recognizing patterns in biological signals such as multi-electrode array waveform data. In other implementations, the present invention also provides for a partition configuration where knowledge elements can be grouped and pattern recognition operations can be individually configured and arranged to allow for multi-level pattern recognition schemes. In other implementations, the present invention provides methods and systems for dynamic learning of patterns in supervised and unsupervised manners.
Claims
exact text as granted — not AI-modified1 . (canceled)
2 . A system, comprising:
one or more memories; and one or more processors implementing logic configured to: identify a dithered pattern outside of a region of search in data; generate one or more dithered knowledge elements based on the dithered pattern; search, using a search process, for occurrences of a pattern of interest in the data by comparing input vectors derived from the data with one or more of:
one or more data vectors representing the pattern of interest,
the one or more dithered knowledge elements, or
one or more entities to be excluded from being found in the search process, the one or more entities identified using a graphical user interface (GUI);
record, for each occurrence of the pattern of interest found in the data, one or more of:
one or more measurements corresponding to one or more characteristics of the occurrence of the pattern of interest, or
a relationship between selected measurements;
record, for each occurrence of the pattern of interest found in the data, a point in the data corresponding to the occurrence of the pattern of interest or a range of the data corresponding to the occurrence of the pattern of interest; and generate search results, the search results identifying one or more of:
one or more occurrences of the pattern of interest found in the data and the corresponding one or more measurements, or
an indication that the pattern of interest was not found in a position where the pattern of interest was expected.
3 . The system of claim 2 , wherein an indication of the one or more entities is obtained from a user device capable of displaying the GUI.
4 . The system of claim 2 , wherein the one or more entities identified using the GUI includes one or more of:
an input vector, a waveform, a channel, or logic for defining one or more conditions to prevent a pattern from being identified.
5 . The system of claim 2 , wherein, for each occurrence of the pattern of interest found in the data, the search results include and/or provide access to the corresponding point in the data or the corresponding range of the data.
6 . The system of claim 2 , wherein, in response to user interaction with a representation of a particular occurrence of the pattern of interest found in the data, the logic is configured to cause display of the corresponding point in the data or the corresponding range of the data.
7 . The system of claim 2 , wherein, in response to user interaction with a representation of a particular occurrence of an excluded pattern of interest, the logic is configured to cause display of a corresponding point in data or a corresponding range of the data.
8 . The system of claim 2 , wherein the search results include one or more of: a reference to the corresponding point in the data, the corresponding range of the data, statistics associated with the one or more occurrences of the pattern of interest found in the data, statistics about one or more excluded patterns, or metadata characterizing one or more reasons for the exclusion.
9 . The system of claim 2 , wherein the logic is configured to record the one or more measurements for a particular occurrence of the pattern of interest found in the data with reference to at least one other occurrence of the pattern of interest.
10 . The system of claim 2 , wherein the GUI is configured to provide definition of logic for identifying one or more of: the pattern of interest, an exclusion pattern, or one or more associated channels.
11 . The system of claim 2 , wherein the data corresponds to a first data channel, and the logic is configured to trigger processing of information associated with a second data channel in response to identification of each occurrence of the pattern of interest found in the data.
12 . The system of claim 2 , wherein the GUI is configured to provide identification of metadata elements to be displayed for the pattern of interest.
13 . The system of claim 2 , wherein the logic is configured to determine one or more relationships between attributes of metadata elements associated with the pattern of interest.
14 . The system of claim 2 , wherein the logic is configured to search for the occurrences of the pattern of interest in the data by applying one or more weights or a mask to at least some of the input vectors and the one or more data vectors.
15 . The system of claim 2 , wherein:
the data corresponds to a first data channel, the logic is configured to search for occurrences of a different pattern of interest in a second data channel, and the logic is configured to combine one or more recognition results associated with the first data channel with one or more recognition results associated with the second channel to determine a combined result.
16 . The system of claim 15 , wherein the logic is configured to adjust one or more parameters associated with the comparing, the one or more parameters including one or more of: a start of a dithering window, an end of the dithering window, a description of the one or more entities to be excluded, or particular logic.
17 . The system of claim 2 , wherein the logic is configured to cause display of a particular knowledge element for a particular input vector in response to a result the of comparing.
18 . A computer-implemented method, comprising:
identifying a dithered pattern outside of a region of search in data; generating one or more dithered knowledge elements based on the dithered pattern; searching, using a search process, for occurrences of a pattern of interest in the data by comparing input vectors derived from the data with one or more of:
one or more data vectors representing the pattern of interest,
the one or more dithered knowledge elements, or
one or more entities to be excluded from being found in the search process, the one or more entities identified using a graphical user interface (GUI);
recording, for each occurrence of the pattern of interest found in the data, one or more of:
one or more measurements corresponding to one or more characteristics of the occurrence of the pattern of interest, or
a relationship between selected measurements;
recording, for each occurrence of the pattern of interest found in the data, a point in the data corresponding to the occurrence of the pattern of interest or a range of the data corresponding to the occurrence of the pattern of interest; and generating search results, the search results identifying one or more of:
one or more occurrences of the pattern of interest found in the data and the corresponding one or more measurements, or
an indication that the pattern of interest was not found in a position where the pattern of interest was expected.
19 . The method of claim 18 , wherein an indication of the one or more entities is obtained from a user device capable of displaying the GUI.
20 . The method of claim 18 , wherein the one or more entities identified using the GUI includes one or more of:
an input vector, a waveform, a channel, or logic for defining one or more conditions to prevent a pattern from being identified.
21 . The method of claim 18 , wherein, for each occurrence of the pattern of interest found in the data, the search results include and/or provide access to the corresponding point in the data or the corresponding range of the data.
22 . The method of claim 18 , wherein, in response to user interaction with a representation of a particular occurrence of the pattern of interest found in the data, the method further comprises causing display of the corresponding point in the data or the corresponding range of the data.
23 . The method of claim 18 , wherein, in response to user interaction with a representation of a particular occurrence of an excluded pattern of interest, the method further comprises causing display of a corresponding point in data or a corresponding range of the data.
24 . The method of claim 18 , wherein the search results include one or more of: a reference to the corresponding point in the data, the corresponding range of the data, statistics associated with the one or more occurrences of the pattern of interest found in the data, statistics about one or more excluded patterns, or metadata characterizing one or more reasons for the exclusion.
25 . The method of claim 18 , the method further comprising recording the one or more measurements for a particular occurrence of the pattern of interest found in the data with reference to at least one other occurrence of the pattern of interest.
26 . The method of claim 18 , wherein the GUI is configured to provide definition of logic for identifying one or more of: the pattern of interest, an exclusion pattern, or one or more associated channels.
27 . The method of claim 18 , wherein the data corresponds to a first data channel, and the method further comprises triggering processing of information associated with a second data channel in response to identification of each occurrence of the pattern of interest found in the data.
28 . The method of claim 18 , wherein the GUI is configured to provide identification of metadata elements to be displayed for the pattern of interest.
29 . The method of claim 18 , the method further comprising determining one or more relationships between attributes of metadata elements associated with the pattern of interest.
30 . The method of claim 18 , the method further comprising searching for the occurrences of the pattern of interest in the data by applying one or more weights or a mask to at least some of the input vectors and the one or more data vectors.
31 . The method of claim 18 , wherein:
the data corresponds to a first data channel, and the method further comprises:
searching for occurrences of a different pattern of interest in a second data channel; and
combining one or more recognition results associated with the first data channel with one or more recognition results associated with the second channel to determine a combined result.
32 . The method of claim 31 , the method further comprising adjusting one or more parameters associated with the comparing, the one or more parameters including one or more of: a start of a dithering window, an end of the dithering window, a description of the one or more entities to be excluded, or particular logic.
33 . The method of claim 18 , the method further comprising displaying a particular knowledge element for a particular input vector in response to a result the of comparing.
34 . A computer program product, comprising one or more non-transitory computer-readable media storing computer program instructions implementing logic configured such that, when executed by one or more computing devices, cause the one or more computing devices to:
identify a dithered pattern outside of a region of search in data; generate one or more dithered knowledge elements based on the dithered pattern; search, using a search process, for occurrences of a pattern of interest in the data by comparing input vectors derived from the data with one or more of:
one or more data vectors representing the pattern of interest,
the one or more dithered knowledge elements, or
one or more entities to be excluded from being found in the search process, the one or more entities identified using a graphical user interface (GUI);
record, for each occurrence of the pattern of interest found in the data, one or more of:
one or more measurements corresponding to one or more characteristics of the occurrence of the pattern of interest, or
a relationship between selected measurements;
record, for each occurrence of the pattern of interest found in the data, a point in the data corresponding to the occurrence of the pattern of interest or a range of the data corresponding to the occurrence of the pattern of interest; and generate search results, the search results identifying one or more of:
one or more occurrences of the pattern of interest found in the data and the corresponding one or more measurements, or
an indication that the pattern of interest was not found in a position where the pattern of interest was expected.
35 . The computer program product of claim 34 , wherein an indication of the one or more entities is obtained from a user device capable of displaying the GUI.
36 . The computer program product of claim 34 , wherein the one or more entities identified using the GUI includes one or more of:
an input vector, a waveform, a channel, or logic for defining one or more conditions to prevent a pattern from being identified.
37 . The computer program product of claim 34 , wherein, for each occurrence of the pattern of interest found in the data, the search results include and/or provide access to the corresponding point in the data or the corresponding range of the data.
38 . The computer program product of claim 34 , wherein, in response to user interaction with a representation of a particular occurrence of the pattern of interest found in the data, the logic is configured to cause displaying of the corresponding point in the data or the corresponding range of the data.
39 . The computer program product of claim 34 , wherein, in response to user interaction with a representation of a particular occurrence of an excluded pattern of interest, the logic is configured to cause displaying of a corresponding point in data or a corresponding range of the data.
40 . The computer program product of claim 34 , wherein the search results include one or more of: a reference to the corresponding point in the data, the corresponding range of the data, statistics associated with the one or more occurrences of the pattern of interest found in the data, statistics about one or more excluded patterns, or metadata characterizing one or more reasons for the exclusion.
41 . The computer program product of claim 34 , wherein the logic is configured to cause recording of the one or more measurements for a particular occurrence of the pattern of interest found in the data with reference to at least one other occurrence of the pattern of interest.
42 . The computer program product of claim 34 , wherein the GUI is configured to provide definition of logic for identifying one or more of: the pattern of interest, an exclusion pattern, or one or more associated channels.
43 . The computer program product of claim 34 , wherein the data corresponds to a first data channel, and the logic is configured to trigger processing of information associated with a second data channel in response to identification of each occurrence of the pattern of interest found in the data.
44 . The computer program product of claim 34 , wherein the GUI is configured to provide identification of metadata elements to be displayed for the pattern of interest.
45 . The computer program product of claim 34 , wherein the logic is configured to cause determining of one or more relationships between attributes of metadata elements associated with the pattern of interest.
46 . The computer program product of claim 34 , wherein the logic is configured to cause searching for the occurrences of the pattern of interest in the data by applying one or more weights or a mask to at least some of the input vectors and the one or more data vectors.
47 . The computer program product of claim 34 , wherein:
the data corresponds to a first data channel, the logic is configured to cause searching for occurrences of a different pattern of interest in a second data channel, and the logic is configured to cause combining of one or more recognition results associated with the first data channel with one or more recognition results associated with the second channel to determine a combined result.
48 . The computer program product of claim 47 , wherein the logic is configured to cause adjusting of one or more parameters associated with the comparing, the one or more parameters including one or more of: a start of a dithering window, an end of the dithering window, a description of the one or more entities to be excluded, or particular logic.
49 . The computer program product of claim 34 , wherein the logic is configured to cause displaying of a particular knowledge element for a particular input vector in response to a result the of comparing.Cited by (0)
No later patents cite this yet.
References (0)
No backward citations on record.