阅读说明：本技术 具有可定制机器预测的可扩展软件工具 (Extensible software tool with customizable machine prediction ) 是由 雷明 C·波佩斯库 W·L·埃特基德 于 2019-10-14 设计创作，主要内容包括：提供了使用可扩展软件工具来执行可定制机器预测的系统和方法。可以接收包括经训练的机器学习模型的特征的规范,并且可以生成用于经训练的机器学习模型的接口。可以使用该接口来加载经训练的机器学习模型,该加载的机器学习模型包括被配置为接收数据作为输入并且生成预测数据作为输出的二进制文件。可以使用根据多维数据模型存储的观察数据来生成预测,其中观察数据的一部分被输入到已加载的机器学习模型以生成第一数据预测,并且观察数据的一部分被通用预报模型用于生成第二数据预测。可以在被配置为显示多维数据模型的交集的用户界面中显示第一数据预测和第二数据预测。(Systems and methods for performing customizable machine predictions using extensible software tools are provided. A specification including features of the trained machine learning model may be received and an interface for the trained machine learning model may be generated. The interface may be used to load a trained machine learning model that includes a binary file configured to receive data as input and generate predicted data as output. Predictions may be generated using observation data stored from a multidimensional data model, where a portion of the observation data is input to a loaded machine learning model to generate a first data prediction, and a portion of the observation data is used by a generic forecasting model to generate a second data prediction. The first data prediction and the second data prediction may be displayed in a user interface configured to display an intersection of the multidimensional data model.)

1. A method for performing customizable machine prediction using an extensible software tool, the method comprising:

receiving a specification including at least features of a trained machine learning model;

generating an interface for the trained machine learning model based on the received specification;

loading a trained machine learning model using the generated interface, the trained machine learning model comprising a binary file configured to receive data as input and generate prediction data as output;

generating predictions using observation data stored according to a multidimensional data model, wherein a portion of the observation data is input to a loaded trained machine learning model to generate a first data prediction, and a portion of the observation data is used by a generic forecasting model to generate a second data prediction; and

the first data prediction and the second data prediction are displayed in a user interface configured to display an intersection of the multidimensional data model.

2. The method of claim 1, wherein the first data prediction and the second data prediction comprise an intersection within the multidimensional data model.

3. The method of claim 2, wherein the generated interface comprises an Application Programming Interface (API) configured to load the trained machine learning model according to the received specification.

4. The method of claim 3, further comprising:

the loaded trained machine learning model is validated against the received specification.

5. The method of claim 3, further comprising:

a machine learning framework for the extensible data modeling system is defined, wherein the trained machine learning model is constructed based on the defined machine learning framework.

6. The method of claim 3, wherein the observation data comprises retail data, and the first data forecast and the second data forecast comprise demand forecasts for one or more retail items at a future point in time.

7. The method of claim 6, further comprising:

causing a quantity of the one or more retail items to be shipped to a retail location based on the first data forecast and the second data forecast.

8. The method of claim 3, wherein the generic predictive model comprises a linear regression model and the loaded trained machine learning model comprises a trained neural network or a trained support vector machine.

9. The method of claim 3, wherein the trained machine learning model is trained using observation data stored according to the multidimensional data model and confidential data that is not included in the observation data and is stored according to the multidimensional data model.

10. A non-transitory computer readable medium having stored thereon instructions that, when executed by a processor, cause the processor to perform customizable machine prediction using an extensible software tool, wherein the instructions, when executed, cause the processor to:

receiving a specification including at least features of a trained machine learning model;

generating an interface for the trained machine learning model based on the received specification;

loading a trained machine learning model using the generated interface, the trained machine learning model comprising a binary file configured to receive data as input and generate prediction data as output;

generating predictions using observation data stored according to a multidimensional data model, wherein a portion of the observation data is input to a loaded trained machine learning model to generate a first data prediction, and a portion of the observation data is used by a generic forecasting model to generate a second data prediction; and

the first data prediction and the second data prediction are displayed in a user interface configured to display an intersection of the multidimensional data model.

11. The non-transitory computer readable medium of claim 10, wherein the first data prediction and the second data prediction comprise an intersection within the multidimensional data model.

12. The non-transitory computer-readable medium of claim 11, wherein the generated interface comprises an Application Programming Interface (API) configured to load the trained machine learning model according to the received specification.

13. The non-transitory computer readable medium of claim 12, further comprising:

the loaded trained machine learning model is validated against the received specification.

14. The non-transitory computer readable medium of claim 12, wherein the observation data comprises retail data, and the first data forecast and the second data forecast comprise demand forecasts for one or more retail items at a future point in time.

15. The non-transitory computer readable medium of claim 14, further comprising:

causing a quantity of the one or more retail items to be shipped to a retail location based on the first data forecast and the second data forecast.

16. The non-transitory computer readable medium of claim 12, wherein the trained machine learning model is trained using observation data stored according to the multidimensional data model and confidential data that is not included in the observation data and is stored according to the multidimensional data model.

17. A system for performing customizable machine prediction using extensible software tools, the system comprising:

a processor; and

a memory storing instructions for execution by the processor, the instructions configuring the processor to:

receiving a specification including at least features of a trained machine learning model;

generating an interface for the trained machine learning model based on the received specification;

loading a trained machine learning model using the generated interface, the trained machine learning model comprising a binary file configured to receive data as input and generate prediction data as output;

generating predictions using observation data stored according to a multidimensional data model, wherein a portion of the observation data is input to a loaded trained machine learning model to generate a first data prediction, and a portion of the observation data is used by a generic forecasting model to generate a second data prediction; and

the first data prediction and the second data prediction are displayed in a user interface configured to display an intersection of the multidimensional data model.

18. The system of claim 17, wherein the first data prediction and the second data prediction comprise an intersection within the multidimensional data model.

19. The system of claim 18, wherein the generated interface comprises an Application Programming Interface (API) configured to load the trained machine learning model according to the received specification.

20. The system of claim 19, wherein the trained machine learning model is trained using observation data stored according to the multidimensional data model and confidential data that is not included in the observation data and is stored according to the multidimensional data model.

Technical Field

Embodiments of the present disclosure generally relate to extensible software tools with customizable machine prediction.

Background

Data planning (planning), analysis, and processing for entities and/or scenarios generates substantial benefits for organizations. For example, enhancements in planning and forecasting may improve supply and/or logistics efficiency and may better utilize resources. Implementing such data planning, analysis, and processing can be challenging, particularly when the entities include a large number of different departments and sub-departments with many dependencies between them. This situation requires complex data storage and modeling, retrieval, analysis, and display techniques to achieve the desired planning and forecasting results. In addition, planning, forecasting, and/or data prediction may be implemented using a variety of different algorithms or predictive models, adding additional complexity to the overall software system. Systems that efficiently and effectively implement various predictive models within such complex software systems may provide greater flexibility while maintaining robust planning and forecasting solutions.

Disclosure of Invention

Embodiments of the present disclosure are generally directed to systems and methods for performing customizable machine prediction using extensible software tools that substantially improve upon the prior art.

A specification including at least features of a trained machine learning model may be received. An interface for the trained machine learning model may be generated based on the received specification. The generated interface may be used to load a trained machine learning model that includes a binary file configured to receive data as input and generate prediction data as output. Predictions may be generated using observed data (observed data) stored according to a multidimensional data model, wherein a portion of the observed data is input into a loaded trained machine learning model to generate a first data prediction and a portion of the observed data is used by a generic forecasting model to generate a second data prediction. The first data prediction and the second data prediction may be displayed in a user interface configured to display an intersection (interaction) of the multidimensional data model.

Drawings

Further embodiments, details, advantages and modifications will become apparent from the following detailed description of preferred embodiments, when read in conjunction with the accompanying drawings.

FIG. 1 illustrates a system for performing customizable machine prediction using extensible software tools, according to an example embodiment.

FIG. 2 illustrates a block diagram of a computing device operably coupled to a system, according to an example embodiment.

3A-3B illustrate hierarchy dimensions (hierarchy dimensions) of a multidimensional data model in accordance with an example embodiment.

FIG. 4 illustrates a user interface for displaying customizable machine predictions using extensible software tools in a graphical user interface, according to an example embodiment.

FIG. 5 illustrates a user interface for displaying customizable machine predictions for intersections of multidimensional data in a graphical user interface, according to an example embodiment.

FIG. 6 illustrates a flow diagram for performing customizable machine prediction using extensible software tools, according to an example embodiment.

FIG. 7 illustrates a flow diagram for training and uploading a customizable machine learning module for use with an extensible software tool to perform machine prediction, according to an example embodiment.

Fig. 8 illustrates an integrated supplier, inventory, and logistics system including improved planning and supply actions as disclosed herein, according to an example embodiment.

Features and advantages of the embodiments are set forth in the description that follows, or are obvious from the description, or may be learned through practice of the disclosure.