-
公开(公告)号：US20210133394A1
公开(公告)日：2021-05-06
申请号：US17148685
申请日：2021-01-14
Applicant: Verint Americas Inc.
Inventor： Timothy James Hewitt , Joseph Wayne Dumoulin
IPC: G06F40/211 , G06F40/253 , G06F40/284 , G06F40/232
Abstract: Experiential parsing (EP) is a technique for natural language parsing that falls into the category of dependency parsing. EP supports applications that derive meaning from chat language. An experiential language model parses chat data, and uses documented experiences with language without using automatic natural language processing (NLP) methods. A descriptive grammar is built at word level rather than a prescriptive grammar at phrase level. The experiential model is designed to understand that word “A” associates with word “B” by function “C”. The experiential model understands the relationship between words, independent of whether or not the overall phrase structure is grammatical. A high accuracy of producing the syntactic roles (such as main verb, direct object, etc.) is attained even when confronted with a variety of agrammatical inputs.
-
公开(公告)号：US11928634B2
公开(公告)日：2024-03-12
申请号：US17939632
申请日：2022-09-07
Applicant: Verint Americas Inc.
Inventor： Joseph Wayne Dumoulin , Cynthia Freeman , James DelloStritto
IPC: G06Q10/00 , G06F17/18 , G06Q10/0635 , G06Q30/018 , H04M15/00
CPC classification number: G06Q10/0635 , G06F17/18 , G06Q30/0185 , H04M15/00 , H04M15/47
Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.
-
公开(公告)号：US20220351099A1
公开(公告)日：2022-11-03
申请号：US17745422
申请日：2022-05-16
Applicant: Verint Americas Inc.
Inventor： Joseph Wayne Dumoulin , Cynthia Freeman , James DelloStritto
Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.
-
公开(公告)号：US11842311B2
公开(公告)日：2023-12-12
申请号：US17745400
申请日：2022-05-16
Applicant: Verint Americas Inc.
Inventor： Joseph Wayne Dumoulin , Cynthia Freeman , James DelloStritto
IPC: G06Q10/00 , G06Q10/0635 , G06F17/18 , G06Q30/018 , H04M15/00
CPC classification number: G06Q10/0635 , G06F17/18 , G06Q30/0185 , H04M15/00 , H04M15/47
Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.
-
Patent Agency Ranking
公开(公告)号：US20230004891A1
公开(公告)日：2023-01-05
申请号：US17939632
申请日：2022-09-07
Applicant: Verint Americas Inc.
Inventor： Joseph Wayne Dumoulin , Cynthia Freeman , James DelloStritto
Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.
-
公开(公告)号：US20220405660A1
公开(公告)日：2022-12-22
申请号：US17745400
申请日：2022-05-16
Applicant: Verint Americas Inc.
Inventor： Joseph Wayne Dumoulin , Cynthia Freeman , James DelloStritto
Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.
-
公开(公告)号：US11334832B2
公开(公告)日：2022-05-17
申请号：US16589511
申请日：2019-10-01
Applicant: Verint Americas Inc.
Inventor： Joseph Wayne Dumoulin , Cynthia Freeman , James DelloStritto
Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.
-
公开(公告)号：US11842312B2
公开(公告)日：2023-12-12
申请号：US17745422
申请日：2022-05-16
Applicant: Verint Americas Inc.
Inventor： Joseph Wayne Dumoulin , Cynthia Freeman , James DelloStritto
IPC: G06Q10/00 , G06Q10/0635 , G06F17/18 , G06Q30/018 , H04M15/00
CPC classification number: G06Q10/0635 , G06F17/18 , G06Q30/0185 , H04M15/00 , H04M15/47
Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.
-
公开(公告)号：US10984191B2
公开(公告)日：2021-04-20
申请号：US16145582
申请日：2018-09-28
Applicant: Verint Americas Inc.
Inventor： Timothy James Hewitt , Joseph Wayne Dumoulin
IPC: G06F40/232 , G06F40/211 , G06F40/253 , G06F40/284
Abstract: Experiential parsing (EP) is a technique for natural language parsing that falls into the category of dependency parsing. EP supports applications that derive meaning from chat language. An experiential language model parses chat data, and uses documented experiences with language without using automatic natural language processing (NLP) methods. A descriptive grammar is built at word level rather than a prescriptive grammar at phrase level. The experiential model is designed to understand that word “A” associates with word “B” by function “C”. The experiential model understands the relationship between words, independent of whether or not the overall phrase structure is grammatical. A high accuracy of producing the syntactic roles (such as main verb, direct object, etc.) is attained even when confronted with a variety of agrammatical inputs.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.012 seconds)
