公开(公告)号：WO2022000039A1

公开(公告)日：2022-01-06

申请号：PCT/AU2021/050703

申请日：2021-06-30

Applicant: AUSTRALIA AND NEW ZEALAND BANKING GROUP LIMITED

Inventor： DU PREEZ, Warren

IPC: G06N20/20 ,  G06F17/18 ,  G06F16/906 ,  G06Q10/04 ,  G06N5/003 ,  G06N5/04

Abstract: A method for generating an artificial intelligence model for determining probability of rainfall, by applying a decision tree ensemble learning process on a dataset, the method comprising: receiving a first dataset comprising at least two variables; determining at least one split criteria for each variable within the first dataset; partitioning the first dataset based on each determined split criteria; calculating a measure of directionality for each partition of data; performing a constrained node selection process by selecting a candidate variable and split criteria, wherein the selection is made to keep a consistent directionality for the selected variable based on existing nodes; updating a directionality table at the end of a constrained node selection; reiterating the constrained node selection process for every node selection throughout the decision tree ensemble learning process until an ensemble model is generated; and processing a second dataset with the generated ensemble model to determine probability of rainfall; wherein the first dataset contains data received from one or more sensors, the received data including data pertaining to temperature.

公开(公告)号：WO2003032266A1

公开(公告)日：2003-04-17

申请号：PCT/AU2002/001322

申请日：2002-09-27

Applicant: AUSTRALIA AND NEW ZEALAND BANKING GROUP LIMITED ,  AUSDATA PTY LIMITED ,  DUNN, Charles ,  SQUIRES, Brian

Inventor： DUNN, Charles ,  SQUIRES, Brian

IPC: G07F19/00

CPC classification number: G06Q20/04 ,  G06Q20/042 ,  G06Q40/12 ,  G07F17/40 ,  G07F19/202

Abstract: This invention concerns a method for processing cheque and deposit vouchers by a financial institution (Proof of Deposit). The method involves an operator preparing vouchers for feeding into a machine reader. Capturing an image from the voucher. Correcting incorrectly read scan lines. Automatically notifying the operator when a transaction boundary is detected and suspending processing of vouchers until the transaction is manually balanced. Finalising processing of each voucher by printing captured and trace details on each voucher.

Abstract translation: 本发明涉及一种由金融机构（存款证明）处理支票和存款凭单的方法。 该方法涉及操作者准备用于馈送到机器读取器的凭证。 从凭证中获取图像。 纠正错误地读取扫描线。 检测到交易边界时自动通知操作员，并在交易手动平衡之前暂停凭证处理。 通过在每个凭证上打印捕获和跟踪细节来完成每个凭证的处理。

公开(公告)号：WO2004054208A1

公开(公告)日：2004-06-24

申请号：PCT/AU2003/000840

申请日：2003-07-01

Applicant: AUSTRALIA AND NEW ZEALAND BANKING GROUP LIMITED ,  VASUDEVA, Nambi ,  OR, Burnnet ,  SETHURAMAN, Raman

Inventor： VASUDEVA, Nambi ,  OR, Burnnet ,  SETHURAMAN, Raman

IPC: H04L009/30

CPC classification number: H04L9/0825 ,  H04L9/0894 ,  H04L9/30 ,  H04L2209/56

Abstract: A method of storing secret information on a secret information injection device includes generating a transport key and encrypting the secret information using the transport key. The transport key and the encrypted secret information are received at a data storage and processing device. The data storage and processing device is used to generate an encryption key pair which consists of a secret key and a public key. The encrypted secret information is transferred from the data storage and processing device to the secret information injection device. The transport key is encrypted using the secret key and is then transferred to the secret information injection device.

Abstract translation: 一种在秘密信息注入装置上存储秘密信息的方法包括：使用传输密钥生成传输密钥并加密秘密信息。 传输密钥和加密的秘密信息在数据存储和处理设备处被接收。 数据存储和处理装置用于生成由密钥和公共密钥组成的加密密钥对。 将加密的秘密信息从数据存储处理装置传送到秘密信息注入装置。 传输密钥使用秘密密钥加密，然后传送到秘密信息注入设备。

公开(公告)号：WO2008070898A9

公开(公告)日：2008-06-19

申请号：PCT/AU2007/001851

申请日：2007-11-30

Applicant: AUSTRALIA AND NEW ZEALAND BANKING GROUP LIMITED ,  FAGG, Jennifer

Inventor： FAGG, Jennifer

IPC: G06Q40/00

公开(公告)号：WO2021207797A8

公开(公告)日：2021-10-21

申请号：PCT/AU2021/050342

申请日：2021-04-16

Applicant: AUSTRALIA AND NEW ZEALAND BANKING GROUP LIMITED

Inventor： DU PREEZ, Warren

IPC: G06N20/00 ,  G06F17/18 ,  G06Q10/04 ,  G06F16/906 ,  G01W1/00 ,  G01W1/14 ,  G06F16/285 ,  G06N20/20 ,  G06N3/08 ,  G06N5/003 ,  G06N7/005

Abstract: Embodiments generally relate to a method for selecting hybrid variables. The method comprises sampling at least one interaction effect structure of at least one multivariable dataset, sampling at least one hybrid variable for each sampled interaction effect structure, calculating a lift value for each sampled hybrid variable, and comparing the lift value to a threshold lift criteria, labelling each sampled hybrid variable based on determining that the lift value of the sample hybrid variable exceeds the threshold lift criteria, training a machine learning model to predict the likelihood of a hybrid variable having a lift which exceeds the threshold lift criteria, applying the trained machine learning model to each hybrid variable within each sampled interaction effect structure to determine a value corresponding to the likelihood of each hybrid variable having a lift which exceeds the threshold lift criteria, and retaining only hybrid variables with a likelihood value that exceeds a decision criteria. The training of the machine learning model is performed using the labelled sampled hybrid variables.

公开(公告)号：WO2021207797A1

公开(公告)日：2021-10-21

申请号：PCT/AU2021/050342

申请日：2021-04-16

Applicant: AUSTRALIA AND NEW ZEALAND BANKING GROUP LIMITED

Inventor： DU PREEZ, Warren

IPC: G06N20/00 ,  G06F17/18 ,  G06Q10/04 ,  G06F16/906 ,  G01W1/00

Abstract: Embodiments generally relate to a method for selecting hybrid variables. The method comprises sampling at least one interaction effect structure of at least one multivariable dataset, sampling at least one hybrid variable for each sampled interaction effect structure, calculating a lift value for each sampled hybrid variable, and comparing the lift value to a threshold lift criteria, labelling each sampled hybrid variable based on determining that the lift value of the sample hybrid variable exceeds the threshold lift criteria, training a machine learning model to predict the likelihood of a hybrid variable having a lift which exceeds the threshold lift criteria, applying the trained machine learning model to each hybrid variable within each sampled interaction effect structure to determine a value corresponding to the likelihood of each hybrid variable having a lift which exceeds the threshold lift criteria, and retaining only hybrid variables with a likelihood value that exceeds a decision criteria. The training of the machine learning model is performed using the labelled sampled hybrid variables.

公开(公告)号：WO2007090241A1

公开(公告)日：2007-08-16

申请号：PCT/AU2007/000140

申请日：2007-02-09

Applicant: AUSTRALIA AND NEW ZEALAND BANKING GROUP LIMITED ,  PEARSE, Andrew ,  WELSH, Mike ,  O'TOOLE, Michael ,  DALEY, John ,  BOURKE, Peter ,  MORRIS, Richard

Inventor： PEARSE, Andrew ,  WELSH, Mike ,  O'TOOLE, Michael ,  DALEY, John ,  BOURKE, Peter ,  MORRIS, Richard

IPC: G06Q40/00 ,  G06Q90/00

CPC classification number: G06Q40/06

Abstract: An automated method of optimising a security value of an investor investment portfolio financed using a margin lending facility, the investment portfolio including a plurality of security holdings at least some of which comprise a diversified portion of the portfolio, the method including the following steps: A) determining a market value and composition of the portfolio based on a level of diversification in the portfolio, the composition of the portfolio including a diversified portion and a standard portion; B) applying a diversified LVR to the diversified portion of the portfolio and a standard loan to value ratio to the standard portion of the portfolio to calculate a maximum security value; and C) comparing the maximum security value calculated against a minimum security value required to secure the loan to determine whether the margin loan requires clearing.

Abstract translation: 一种自动化方法，用于优化使用保证金借贷设施资助的投资者投资组合的担保价值，所述投资组合包括多个证券持有量，其中至少一部分包括投资组合的多样化部分，该方法包括以下步骤：A ）根据投资组合多元化水平确定投资组合的市场价值和组成，投资组合的组合包括多元化部分和标准部分; B）将多元化LVR应用于投资组合的多元化部分，并将标准贷款与价值比率与投资组合的标准部分进行比较，以计算最大安全价值; 和C）比较计算的最大安全价值与确保贷款所需的最低安全价值，以确定保证金贷款是否需要清算。

公开(公告)号：WO2003090114A1

公开(公告)日：2003-10-30

申请号：PCT/AU2002/001285

申请日：2002-09-19

Applicant: AUSTRALIA AND NEW ZEALAND BANKING GROUP LIMITED ,  JONES, Russell ,  CHRYSTALL, Douglas ,  DELEKTA, Paul ,  BAXTER, Geoff ,  NAGY, Sandor

Inventor： JONES, Russell ,  CHRYSTALL, Douglas ,  DELEKTA, Paul ,  BAXTER, Geoff ,  NAGY, Sandor

IPC: G06F17/30

CPC classification number: G06F17/30575 ,  G06F17/30289

Abstract: A method for administering a distributed network (2) of managed database servers (4, 5) from a central database server (3), the method including the steps of: at predefined intervals, (a) receiving at the central database server (3) a heart beat signal identifying each managed database server (4, 5); (b) receiving notification at the central database server (3) of events resulting from execution of tasks by each managed database server (4, 5); (c) checking in the central database server (3) for new changes or tasks to be implemented by one or more of the managed database servers (4, 5); and (d) distributing the new changes or tasks from the central database server (3) to the one or more database servers (4, 5) for execution.

Abstract translation: 一种用于从中央数据库服务器（3）管理受管数据库服务器（4,5）的分布式网络（2）的方法，所述方法包括以下步骤：以预定间隔，（a）在中央数据库服务器（3）处接收 ）识别每个被管理的数据库服务器（4,5）的心跳信号; （b）在中央数据库服务器（3）处接收由每个受管数据库服务器（4,5）执行任务而产生的事件的通知; （c）在中央数据库服务器（3）中检查要由一个或多个被管理的数据库服务器（4,5）实现的新的改变或任务; 和（d）将新的更改或任务从中央数据库服务器（3）分发到一个或多个数据库服务器（4,5）以供执行。