专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20040236696A1 History information adding program, fraud determining program using history information, and fraud determining system using history information 审中-公开
标题翻译：历史信息添加程序，使用历史信息的欺诈判定程序，以及使用历史信息的欺诈判定系统
公开(公告)号：US20040236696A1
公开(公告)日：2004-11-25
申请号：US10747041
申请日：2003-12-30
申请人： INTELLIGENT WAVE, INC.
发明人： Osamu Aoki , Mikinori Seita
IPC分类号： G06F017/60
CPC分类号： G06Q40/02 , G06Q20/04 , G06Q20/24 , G06Q20/40 , G06Q20/4016 , G06Q20/403
摘要： A fraud determining system adds, to authorization data concerning a present use, history information, such as a difference in time of use or monetary value between the authorization data and authorization data concerning an immediately previous use. When a determination as to whether the present use involves a fraud is made on the basis of the authorization data concerning the present use, it is possible to determine whether or not the present use is irregular from the history information. The result of the determination is reflected in a score, and therefore, the score can be calculated with high reliability.
摘要翻译：欺诈判定系统对授权数据和与之前的使用相关的授权数据之间的历史信息（例如使用时间差异或货币价值）之间的历史信息进行授权。当根据关于本使用的授权数据确定当前使用是否涉及欺诈时，可以根据历史信息确定当前用途是不规则的。测定结果反映在分数中，因此可以高可靠性计算得分。

2. 发明授权

US11528202B2 Packet flow monitoring device, packet data extraction device, extraction data aggregation device, and program 有权
公开(公告)号：US11528202B2
公开(公告)日：2022-12-13
申请号：US17280974
申请日：2019-10-24
申请人： INTELLIGENT WAVE INC.
发明人： Tomofumi Koyama , Masahiro Kawaragi , Takuya Kurakake , Masaki Tsuji , Ryo Hasegawa , Keiichiro Katsuta , Naoya Suzuki
IPC分类号： H04L43/062 , H04L43/067 , H04L43/0882 , H04L43/0888 , H04L69/22 , H04L101/622
摘要： A packet flow monitoring device, a packet data extraction device, an extraction data aggregation device, and a program for efficiently and highly accurately monitoring a packet flow in a video or audio communication system constructed by an Ethernet (registered trademark) frame or IP packet network. This packet flow monitoring device includes: a packet data extraction device that replicates all passing packets that pass through one or a plurality of specific network switches on the network and extracts and aggregates some predetermined pieces of information in the replicated passing packets to form and output an extraction data report packet; and an extraction data aggregation device that receives the extraction data report packet, analyzes the extraction data report packet so as to aggregate the predetermined pieces of information in the replicated passing packets included in the extraction data report packet for each packet flow, and records the aggregated information as aggregation data.

3. 发明申请

US20210359923A1 PACKET FLOW MONITORING DEVICE, PACKET DATA EXTRACTION DEVICE, EXTRACTION DATA AGGREGATION DEVICE, AND PROGRAM 有权
公开(公告)号：US20210359923A1
公开(公告)日：2021-11-18
申请号：US17280974
申请日：2019-10-24
申请人： INTELLIGENT WAVE INC.
发明人： Tomofumi KOYAMA , Masahiro KAWARAGI , Takuya KURAKAKE , Masaki TSUJI , Ryo HASEGAWA , Keiichiro KATSUTA , Naoya SUZUKI
IPC分类号： H04L12/26 , H04L29/06 , H04L29/12
摘要： A packet flow monitoring device, a packet data extraction device, an extraction data aggregation device, and a program for efficiently and highly accurately monitoring a packet flow in a video or audio communication system constructed by an Ethernet (registered trademark) frame or IP packet network. This packet flow monitoring device includes: a packet data extraction device that replicates all passing packets that pass through one or a plurality of specific network switches on the network and extracts and aggregates some predetermined pieces of information in the replicated passing packets to form and output an extraction data report packet; and an extraction data aggregation device that receives the extraction data report packet, analyzes the extraction data report packet so as to aggregate the predetermined pieces of information in the replicated passing packets included in the extraction data report packet for each packet flow, and records the aggregated information as aggregation data.

4. 发明申请

US20040225628A1 Data merging program, data merging method, and scoring system using data merging program 有权
标题翻译：数据合并程序，数据合并方法和使用数据合并程序的评分系统
公开(公告)号：US20040225628A1
公开(公告)日：2004-11-11
申请号：US10747039
申请日：2003-12-30
申请人： INTELLIGENT WAVE, INC.
发明人： Osamu Aoki , Mikinori Seita
IPC分类号： G06F017/00 , G06N005/00 , G06F015/18 , G06G007/00 , G06E003/00 , G06E001/00 , G06F017/60
CPC分类号： G06Q20/4016 , G06Q20/10 , G06Q20/24 , Y10S707/99942
摘要： A data merging program causes a computer to perform a step of selecting a first cell as a starting point of merging; a step of comparing a first numerical value, which is recorded in the first cell, with a preset reference value; a step of, if the first numerical value is smaller than the reference value, calculating a total value of the first numerical value and a second numerical value recorded in a second cell adjacent to the first cell in the same column; a step of comparing the total value with the reference value and, if the total value is smaller than the reference value, setting a third cell into which the first and second cells are merged and recording the total value in the third cell; and a step of selecting the third cell as a new starting point of merging.
摘要翻译：数据合并程序使计算机执行选择第一个单元作为合并起点的步骤; 将记录在第一单元中的第一数值与预先设定的基准值进行比较的步骤; 如果第一数值小于参考值，则计算第一数值的总值和记录在与同一列中的第一单元相邻的第二单元中的第二数值的步骤; 将总值与参考值进行比较的步骤，如果总值小于参考值，则设置合并第一和第二单元的第三单元，并记录第三单元中的总值; 以及选择第三个单元格作为新的合并起始点的步骤。

5. 发明申请

US20040225520A1 Fraud score calculating program, method of calculating fraud score, and fraud score calculating system for credit cards 有权
标题翻译：欺诈分数计算程序，计算欺诈分数的方法，以及信用卡欺诈分数计算系统
公开(公告)号：US20040225520A1
公开(公告)日：2004-11-11
申请号：US10747042
申请日：2003-12-30
申请人： INTELLIGENT WAVE, INC.
发明人： Osamu Aoki , Mikinori Seita
IPC分类号： G06F017/60
CPC分类号： G06Q10/10 , G06Q20/10 , G06Q20/4016 , G06Q40/025
摘要： A fraud score calculating program primarily for use in determining the possibility of credit card fraud can calculate a score reflecting the reliability of a model created based on Bayesian theory. Various factors are extracted from authorization data, and cases are selected for various combinations of the factors. A fraud score is calculated for each case, and a result of score calculation is specified using at least one of the calculated scores. The result of score calculation may be an average of a plurality of the calculated scores. When each score reflects reliability, the result of score calculation may be the largest of the calculated scores.
摘要翻译：主要用于确定信用卡欺诈的可能性的欺诈分数计算程序可以计算反映基于贝叶斯理论创建的模型的可靠性的分数。从授权数据中提取各种因素，并对因素的各种组合选择情况。针对每种情况计算欺诈分数，并且使用计算得分中的至少一个来指定得分计算的结果。分数计算的结果可以是多个计算得分的平均值。当每个分数反映可靠性时，分数计算的结果可能是计算得分的最大值。

6. 发明申请

US20040225473A1 Fraud score calculating program, method of calculating fraud score, and fraud score calculating system for credit cards 审中-公开
标题翻译：欺诈分数计算程序，计算欺诈分数的方法，以及信用卡欺诈分数计算系统
公开(公告)号：US20040225473A1
公开(公告)日：2004-11-11
申请号：US10747098
申请日：2003-12-30
申请人： INTELLIGENT WAVE, INC.
发明人： Osamu Aoki , Mikinori Seita
IPC分类号： G06F015/00
CPC分类号： G07F7/08 , G06Q20/40 , G06Q20/4016 , G06Q20/4037 , G06Q40/00
摘要： A fraud score calculating program primarily for use in determining the possibility of credit card fraud can calculate a score reflecting the reliability of a model created based on Bayesian theory. A model which is stored in a fraud detection model database 120 obtains new authorization data and continues learning as the number of data samples increases. Calculation of the score is performed by a calculation logic provided in a scoring subsystem 110. The sample number data for a case corresponding to the authorization data are obtained from the model, and the probability of the occurrence of fraudulent use is calculated. The reliability of the model is also calculated on the basis of, for example, the number of the registered samples, and a fraud score is calculated using both the calculated probability of the occurrence of fraud and the calculated reliability of the model.
摘要翻译：主要用于确定信用卡欺诈的可能性的欺诈分数计算程序可以计算反映基于贝叶斯理论创建的模型的可靠性的分数。存储在欺诈检测模型数据库120中的模型获得新的授权数据，并随着数据样本的数量的增加而继续学习。通过评分子系统110中提供的计算逻辑来执行分数的计算。从模型获得与授权数据相对应的情况的样本数量数据，并且计算发生欺诈性使用的概率。还可以基于例如登记样本的数量来计算模型的可靠性，并且使用所计算的欺诈发生的概率和所计算的模型的可靠性两者来计算欺诈分数。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式