Height data and analysis management platform

Abstract

An advanced data management platform, method, and system that enable several users to remotely access a centralized database, analyze a dataset using analytical tools, models, and algorithms, and extract predictive information, trends, etc. from the dataset. Further, the data management platform, method, and system include options that enable data analysis and model training using anonymized data. This then further enables applying a model trained on a dataset located external to the data platform and / or system to derive predictive information about that dataset.

Description

[Technical Field]

[0001] FIELD OF THE INVENTION The present invention relates to an advanced data and analytics management platform. The present invention also relates to a system and method for implementing an advanced data and analytics management platform. [Background technology]

[0002] Background of the Invention In many traditional organizations, the standard practice is to purge data after a specific period of time, or at best, to retain the data in a traditional data warehouse for long-term storage and basic reporting purposes.

[0003] In recent years, organizations have begun to address data in more sophisticated and advanced ways, influenced at least in part by the latest buzzwords, success stories, and trends in publications and seminars. As part of this process, there has been a growing, often voluntary, investment in different and disparate "analytics" solutions or tools.

[0004] During this transitional period from both an organizational and technology perspective, different teams and departments within an organization or group may be joining the "movement" - some quietly, others quite enthusiastically - and many teams or departments are investing in data and analytics tools through vendors (both traditional and new).

[0005] The result is a risk of fragmented data and analytical resources (especially in large organizations) rather than a unified, holistic, enterprise-wide, end-to-end solution. Some of the drawbacks of such fragmented systems include siloed data stores, suboptimal underlying analytical resources, disjointed and incompatible actions, dismal outcomes, wasted or duplicated organizational budgets and resources, and missed opportunities. Furthermore, any of these uncoordinated, disparate methods and myriad aggregated assets create new and / or reinforce existing organizational silos. There is no single source of truth and no single data point—and this also applies to analytical repositories and references. For example, a single key performance indicator (KPI), process, or use case may be defined and implemented differently within the same organization by different teams. This, in turn, can result in the same KPI being reported differently and different values ​​(numbers) being communicated across the organization and to external investors and regulators, for example. This can have a detrimental impact on the organization's performance, image, governance, and / or benchmarks.

[0006] These distributed, uncorrelated, and uncoordinated approaches to analysis work in ignorance and in unison with "each other," instead of working together toward common outcomes and goals within the organization. The practical results are suboptimal and often harmful due to mutual cannibalization, push-pull effects, etc.

[0007] Another significant issue in this regard is the unavailability of a variety and amount of data suitable for data science activities. Analytics is often most effective when it tightly couples large amounts of data of different types with the use of advanced analytical tools. In large organizations, each department or function may depend on each other to realize the overall organization's offering to customers. Similarly, in data and analytics, the fusion of different data and external data points can also help an organization achieve its true analytical potential.

[0008] Without the above, a siloed approach without a centralized, dedicated data and analytics platform can result in suboptimal effectiveness and predictive power of analytical assets (such as machine learning (ML) models). This leads to less accurate and impactful predictions and decisions. Without a single point of development and single point of production with accurate and complete data and its associated ecosystem, many of these analytical assets may remain on personal machines (e.g., locally on laptops) rather than being productized (implemented in business or IT systems) to benefit the organization. Naturally, this leads to significant duplication and waste, along with the other issues already mentioned above.

[0009] We've found that a common failure in leveraging an organization's big data assets to drive commercial value is typically not the creation of good actionable insights through ML models, but rather their application. Embedding these models into productized business systems is typically where data science teams fail (as opposed to failing to develop the models themselves) and where the majority of resource efforts can be focused. Summary of the Invention [Problem to be solved by the invention]

[0010] In view of the above, a need was identified for a holistic end-to-end solution that could address at least some of these problems. The inventors tried to find a solution in the public domain based on their own multi-domain cross-industry experience, but found that no single "off-the-shelf" tool or solution was available. This was not surprising due to the diverse requirements, components, processes, and services required to create such an end-to-end solution.

[0011] While research has been conducted in this area, and several entities have developed products / services that address aspects of the problem, e.g., Google's "Colossus" and "Bigtable" products, existing functionality is limited and does not provide the comprehensive solution desired. In particular, the present applicant has not been able to find a vendor-neutral, end-to-end, holistic analysis cycle solution that allows the myriad components, services, processes, and functions to interact harmoniously. Accordingly, to address this need, the present inventor has developed the present invention. [Means for solving the problem]

[0012] Summary of the Invention In general, the present invention provides an advanced data and analytics management platform. Aspects of the invention may include methods of operating the platform and systems that are part of or coupled to the platform, as described below and / or shown in the drawings.

[0013] For ease of reference, the Advanced Data and Analytics Management Platform will be referred to below and in some of the drawings using the acronym "ADAM."

[0014] The ADAM platform is configured to provide a central, single source for the development, management, production, repository, and monitoring of all analytical assets (particularly advanced analytical tools) across an organization, e.g., an organization including a group of companies or multiple groups of companies. In the following example and drawings, the organization is MTN, which includes an operating company (OpCo). The OpCo may be distributed across multiple countries, and in some countries, there may be one OpCo per country in which the business operates. It will be understood that reference to MTN is merely an example, and that the ADAM platform is applicable across different industries and organizations. In the case of MTN, the local / on-premise data system can be referred to as the "EVA" system, and therefore reference is made to the integration of the EVA system with the ADAM platform.

[0015] The ADAM platform provides a data science workbench and asset management platform to mature data utilization capabilities within an organization. The ADAM platform can help organizations evolve data science, foster natural talent, and enhance business streams.

[0016] Preferably, the platform should be centrally located, easily and securely accessible from anywhere, have the right amount of data of the right variety (that can be legally vetted), have a complete analytical resource ecosystem connected to each operating company within the group and the means to create, reuse and industrialize (automate) data or analytical resources across the group's footprint, on-premise at OpCo, in the cloud or at the edge (e.g., malls or airports), or with B2B clients.

[0017] Essentially, the ADAM platform can be configured to function as an analytics factory and / or analytics-as-a-service (AaaS) platform, for example, supporting collaboration, analytics code repository, model catalog, CICD (Continuous Integration Continuous Deployment) pipeline, vital organizational data sources (points), and a one-stop shop for analytics assets with supporting analytics algorithms, languages, etc.

[0018] The ADAM platform may include one or more of the following components / features: Easy availability of large volumes of diverse, curated organizational and external data in a single logical location; Support for various analytical tools and languages, Access to a library of modeling algorithms that can be researched and downloaded in a secure internal organization environment; Ability to support various types of analytics (e.g., AI / ML / DL / heuristics / simulation, etc.), Connecting to different organizational entities, e.g., Group and OpCo data source systems; The ability to upload data, download model code, and upload model performance again, for example via a CICD pipeline, for monitoring purposes; and / or Easy production (industrialization) for the automated and periodic generation of actionable insights, insight-based actions, and / or predictions.

[0019] The platform can empower users ranging from data scientists to basic analysts to use their preferred technologies, programming languages, and analytical algorithm libraries in an environment that is part of a broader, connected, and ubiquitously accessible enterprise-wide infrastructure. In use, users such as data scientists can connect directly to data sources in a central data lake with minimal setup to increase business productivity.

[0020] Thus, using ML / AI models as an example, the platform provides a technological solution that can facilitate the "unlocking" of the value of ML / AI across large organizations.

[0021] Embodiments of the present invention can extend to one or more computer program products for implementing an ADAM platform, the computer program product including at least one computer-readable storage medium having program instructions embodied therein, the program instructions being executable by at least one computer to cause the at least one computer to perform techniques and implement features substantially as described above.

[0022] The computer-readable storage medium may be a non-transitory storage medium. The computer program product may be embodied across multiple devices and locations, etc.

[0023] The ADAM platform may be or may include any suitable computer or server. The computer ADAM platform may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In distributed cloud computing environments, program modules executed by the ADAM platform may be located both locally and remotely.

[0024] According to a first aspect of the present invention, there is provided a data management platform, the data management platform comprising: a centralized database having benchmark data stored therein, the centralized database being configured to receive one or more data sets from one or more data sources, the centralized database allowing one or more users to remotely access the centralized database; an analysis module communicatively coupled to the centralized database, the analysis module including one or more analysis tools that enable data analysis of one or more data sets; A model module communicatively coupled to the centralized database, the model module including one or more algorithms that execute a set of instructions on one or more datasets, the model module being trainable by the one or more algorithms by comparing the one or more datasets to benchmark data and deriving one or more output datasets having predictive information for the one or more datasets.

[0025] The one or more data sources may be one or more data warehouses located in one or more countries. The one or more data sets may include customer data.

[0026] The data management platform may be configured to enable one or more users to remotely access the centralized database through a network connection to transfer one or more datasets from one or more data sources to the centralized database, the network connection enabling the one or more users to analyze the one or more datasets using an analysis module including an analysis tool, and the network connection enabling the one or more users to train a model module including one or more algorithms by comparing the one or more datasets to benchmark data and deriving an output dataset having predictive information for the one or more datasets.

[0027] The analytical module, which includes one or more analytical tools, and the model module, which includes one or more algorithms, may be dynamically updated and evolve as each instance of the one or more analytical tools analyzes one or more datasets and each instance of the model module is trained with one or more algorithms by comparing the one or more datasets to benchmark data and deriving one or more output datasets having predictive information for the one or more datasets.

[0028] Dynamically updating may refer to uploading data in real time.

[0029] Evolution can be an improvement in the operation of the analytical module and the model module, where the analytical module provides improved data analysis and the model module is able to provide faster and more powerful predictive information when applied to one or more data sets.

[0030] The benchmark data may be dynamically updated as each instance of one or more data sets is compared to the benchmark data.

[0031] Training a model module including one or more algorithms may enable faster derivation of each subsequent output dataset having predictive information and including additional predictive insights related to one or more datasets.

[0032] The data management platform may further include a processing module that processes the data into one or more vectors.

[0033] One or more vectors can be segmented into one or more use cases.

[0034] Each use case may be configured to be employed for a particular purpose.

[0035] Each objective may be the adoption of a vector of data into a particular type.

[0036] The one or more vectors may be stored in a data management platform as a repository, and the repository may be remotely accessed by one or more users to facilitate the application of a model module, including one or more algorithms, to one or more datasets.

[0037] The availability of one or more vectors stored as a repository in a data management platform may enable the application of a model module comprising one or more algorithms to one or more datasets in one or more countries.

[0038] The availability of one or more vectors stored as a repository in a data management platform may enable a model module including one or more algorithms to be applied to one or more datasets with less latency than transmitting one or more datasets to the data management platform.

[0039] The network connection can be either secure, private, or a combination thereof.

[0040] The one or more data sources may be one or more data warehouses that may be located in one or more countries.

[0041] The centralized database may be configured to receive only one or more data sets that have been de-identified for deriving the de-identified data.

[0042] The one or more analytics tools may be selected from the group consisting of Tableau, Oracle Business Intelligence, IBM Cognos Analytics, SAS, Microsoft Power BI, Amazon Redshift, Google BigQuery, Snowflake, Alteryx, Cloudera, Apache Hadoop, Google Vertex AI, Microsoft Azure Synapse, Microsoft Data Explorer, CosmosDB, Redis, Azure Cognitive Services, Azure Machine Learning, Spark, Databricks, Sqream, Confluent Kafka, Presto, Trino, Flare, HIDS, and combinations thereof.

[0043] The one or more algorithms may be selected from the group consisting of a machine learning algorithm, an artificial intelligence algorithm, a deep learning algorithm, a heuristic algorithm, and combinations thereof.

[0044] The one or more datasets may include customer usage information selected from the group consisting of customer voice call usage, customer screen time usage, customer data usage, customer messaging usage, customer device hardware specifications, customer transactions, customer interactions, customer behavior, customer revenue, network operations, network usage, network investments, internal operations, sales information, distribution information, agent operations, merchant operations, agent services, merchant operations, B2B products, B2B product services, digital products, over-the-top applications, customer value management, pricing, operations management, portfolio management, customer location, network location, network transport, network configuration, cybersecurity, and combinations thereof.

[0045] The one or more data sets may include information and may be selected from customer information relating to a customer's use of voice, internet, data, payment, digital services, enterprise services, network solutions, and combinations thereof.

[0046] Predictive information may include information about customer behavior for deriving user-specific product offerings.

[0047] An example of a user-specific product offering may offer a customer one or more products that correlate with the predictive information derived for the customer by the model module and one or more algorithms.

[0048] A more specific example of a user-specific product offering may recommend to a customer one or more products that include a voice minute, data, or a combination thereof.

[0049] The predictive information may include information indicating what the preferred form of communication is to increase the likelihood that a client will purchase the product offering.

[0050] The data management platform may include a data transmission module for transmitting the model module to a database that may be located outside the centralized database, and the model module including one or more algorithms may be applied to one or more datasets available in the database to derive an output dataset having predictive information for the one or more datasets.

[0051] The data transmission module may enable the trained model module and one or more algorithms to be stored on a computer-readable storage medium.

[0052] The computer-readable storage medium may be a non-transitory storage medium.

[0053] The computer-readable storage medium may be remote storage, which may include one or more instances or units of cloud storage, a remote server, a plurality of processors, computers communicatively coupled to each other, and combinations thereof.

[0054] The model module may be uploaded to any device or medium containing one or more datasets, and the model module is then applied to the one or more datasets.

[0055] Uploading the model modules to a location that can be external to the data management platform may allow for reduced latency.

[0056] Uploading a model module to a location that may be external to the data management platform may allow the model module to be applied to one or more datasets at a location, and allowing one or more datasets to be remote from that location may violate one or more data regulations.

[0057] Uploading the model module to a location that can be located outside the data management platform can enable the model module trained with anonymized data at the data management platform to derive predictive information for one or more datasets at that location, which can be used to derive user-specific product offerings for one or more customers included in the one or more datasets at that location.

[0058] The data management platform may further include an anonymization module that may be located outside the centralized database, the anonymization module comprising: a data module for receiving one or more data sets from one or more data sources; an anonymization algorithm for anonymizing one or more datasets to derive anonymized data; a transmitting module for transmitting the anonymized data to a centralized database; Includes.

[0059] The de-identified data may be used to train a model module with one or more algorithms that compare the de-identified data with benchmark data stored in a centralized database to derive an output dataset having predictive information about the de-identified data.

[0060] A model module including one or more algorithms may be configured to be trained with anonymized data, and the model module may be applied to one or more datasets that may be located in a location selected to comply with country-specific data protection and privacy regulations.

[0061] The data management platform may be communicatively coupled to an external data source that stores one or more data sets, the external data source being located outside the platform.

[0062] One or more data sets stored in the data sources may be anonymized by an anonymization module to derive anonymized data. A model module including one or more algorithms may be trained with the anonymized data receivable by the centralized database, and the trained model module including one or more algorithms may be applied to one or more data sets located in the data sources, which may be located at a location external to the centralized database.

[0063] The data management platform may further include an interface module communicatively coupled to the model module to receive the prediction information for the one or more datasets, the interface module communicatively coupled to one or more user devices thereby enabling the user devices to access the prediction information for the one or more datasets.

[0064] According to a second aspect of the present invention, there is provided a method of training a model using anonymised data and applying the model to one or more datasets located at selected locations, the method comprising: providing a database having benchmark data stored therein, the database being capable of receiving data from one or more data sources; providing an external data source communicatively coupled to the database, wherein one or more data sets stored in the external data source are to be de-identified by executing a set of instructions to derive de-identified data; enabling data analysis of the data stored in the database using one or more analytical tools; training a model including one or more algorithms by comparing the anonymized data to benchmark data; applying the trained model to one or more datasets, which may be located outside the database, thereby deriving predictive information for the one or more datasets; Includes:

[0065] The method may include storing the model on a storage medium, thereby allowing the model to be applied to one or more datasets communicatively coupled to the storage medium.

[0066] The method may include using the forecast information to derive user-specific product offerings.

[0067] According to a third aspect of the present invention, there is provided a digital management system, the digital management system comprising: a computing device comprising a processor communicatively coupled to a memory capable of storing one or more data sets obtainable from one or more data sources, the memory storing benchmark data; an analysis module including an analysis tool, the analysis module communicatively coupled to the memory, and a processor capable of executing an instruction set of the analysis tool to perform an analytical operation on one or more data sets; a model module including one or more algorithms, the model module communicatively coupled to the memory, the model module capable of being trained by a processor that applies the one or more algorithms by comparing one or more datasets to benchmark data to derive an output dataset having predictive information for the one or more datasets; Equipped with.

[0068] The memory may be selected from the group consisting of a non-transitory storage medium, a transitory storage medium, and combinations thereof.

[0069] According to a fourth aspect of the present invention, there is provided a computer readable storage medium having stored thereon instructions which, when executed by a computer, cause the computer to perform a method of using a computer system to train a model with anonymized data and apply the model to data located at selected locations, the method comprising: providing a database having benchmark data stored therein, the database being capable of receiving data from one or more data sources; providing an external data source communicatively coupled to the database, wherein one or more data sets stored in the external data source are to be de-identified by executing a set of instructions to derive de-identified data; enabling data analysis of the data stored in the database using one or more analytical tools; training a model including one or more algorithms by comparing the anonymized data to benchmark data; applying the trained model to an external dataset, which may be located outside the database, thereby deriving predictive information for the external dataset; Includes:

[0070] BRIEF DESCRIPTION OF THE DRAWINGS The invention will now be further described, by way of example, with reference to the accompanying drawings, in which: [Brief explanation of the drawings]

[0071] [Figure 1] FIG. 1 is a schematic diagram illustrating one example of how the ADAM platform can be integrated into an organization's enterprise data systems. [Figure 2] 1 is a schematic diagram illustrating how the ADAM platform can interact with anonymized data (personally identifiable information or "PII" data) available through the EVA system. [Figure 3]1 is a schematic diagram showing how the ADAM platform can be deployed as a "group platform." [Figure 4] 1 is an exemplary data system architecture including an example of an ADAM platform. [Figure 5] Provide a diagram of the data pipeline between the ADAM platform and on-premise systems. [Figure 6] 1 provides an overview of an exemplary ADAM platform in operation. [Figure 7] 1 is a table detailing an example platform's compliance with a first set of architectural principles. [Figure 8] 10 is a table detailing an example platform's compliance with a second set of architectural principles. [Figure 9] 10 is a table detailing an example platform's compliance with a third set of architectural principles. [Figure 10] FIG. 1 is a schematic diagram of an exemplary logical architecture that may be employed in embodiments of the present invention. [Figure 11] 1 is a schematic diagram showing a first option for integrating a group instance of ADAM with an operating company within an organization. [Figure 12] FIG. 1 is a schematic diagram illustrating a second option for integrating a group instance of ADAM with an operating company within an organization. [Figure 13] FIG. 1 is a block diagram of an exemplary computer system capable of executing computer program products to provide functionality and / or actions in accordance with various aspects of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0072] Detailed Description of Embodiments of the Invention The following description is provided as an enabling teaching of the invention, illustrating principles in accordance with the invention, and is not intended to limit the scope of the invention. Changes can be made to the illustrated and described embodiments without still obtaining the results of the invention and / or departing from the scope of the invention. Moreover, it will be understood that some of the results or advantages of the invention can be obtained by selecting some of the features of the invention without utilizing other features. Thus, those skilled in the art will recognize that modifications and adaptations to the invention may be possible and may even be desirable in certain circumstances and form a part of the invention.

[0073] Embodiments of the present invention provide a "one-stop shop": a centralized platform for end-to-end analytical asset lifecycle management. One example of such an asset is an ML model.

[0074] FIG. 1 is a schematic diagram illustrating one example of how the ADAM platform may be integrated into an organization's enterprise data systems. Data is received from various sources and stored in various formats, whether text, video, images, etc. Once stored, the data can then be utilized through a series of operations as shown in the "Organization and Consumption" zone. The operations then place the data in a suitable format so that the ADAM platform can then interact with the data. This series of operations and transformations of data, performed by each participant or contributor to the overall ADAM platform, is referred to as an EVA system, as discussed above. Importantly, each location or country collectively becomes an EVA system, contributing one or more unique data sets.

[0075] Once the data is appropriately stored, the ADAM platform may perform further operations on the data, including, but not limited to, analyzing, visualizing, modeling, training, and analyzing one or more datasets through the application of ML, DL, AI, heuristics, and other algorithms to analyze one or more datasets and make predictions related to one or more datasets.

[0076] A key feature of the ADAM platform is its centralization, which exposes the platform to and allows it to be trained with a variety of datasets received from diverse sources and sectors within one or more organizations, allowing for the close coupling, integration, and / or "cross-pollination" of similar unique datasets, which in turn allows the ADAM platform to make unique predictions not possible with platforms or models that are predominantly trained with similar datasets without the use of the present invention.

[0077] FIG. 2 is a schematic diagram illustrating how the ADAM Platform can interact with anonymized data (personally identifiable information or "PII" data) available through the EVA System. First, raw data is acquired by the EVA System from each location or country. Second, the raw data is anonymized through a series of operations performed by the EVA System. Third, the anonymized data is moved or transmitted from the location or country to a cloud-based server where the ADAM Platform is centrally hosted. Fourth, while still in an anonymized data format, the ADAM Platform can query and train using the anonymized data. Fifth, in contrast to the typical operation of sending or transmitting data to another medium that can interact with the data, the ADAM Platform and its algorithms and / or models are deployed to each individual location or country to analyze and make predictions on the actual data. Sixth, as a result of the availability of the relevant datasets, the generated analyses and predictions are unique to each individual location or country, thereby enabling monetization of these results for each EVA System (location or country).

[0078] This is a key feature of the present invention, as exporting data from each country would likely conflict with or violate data regulations such as GDPR or POPI. Thus, anonymized data is used to train the ADAM platform and associated models, which are then employed in each location on real data to obtain analytics and make predictions, enabling the utilization of vast data lakes without compromising user privacy.

[0079] FIG. 3 is a schematic diagram illustrating how the ADAM platform can be deployed as a "group platform." As previously described in FIG. 2, the ADAM platform can connect to operational enterprise data systems via CICD. Benefits of this can include IP and ownership retention, asset reusability, and a "build once deploy many" approach. In embodiments of the present invention, the ADAM platform aims to avoid the problems and drawbacks mentioned above by accelerating the model development process through testing and into production. Without a solution like ADAM, organizational resources would be required to build these systems using, for example, open-source (one-person or one-team laptop-based) solutions that are readily available but often have significant reliability and scalability issues. Models also require significant effort to remain operational.

[0080] While typical estimates for productionizing an ML model (through such individual open source technologies and methods) can exceed three months, with an ADAM platform embodiment, this can be reduced to, for example, two to three weeks with the same resource pool. This becomes important when considering the number of these models businesses need today to increase their returns. Therefore, an organization's modeling team can use a platform such as the one shown in the drawing to meet the organization's demands.

[0081] Some key steps in managing and implementing this platform may include: Use of governance Innovation hub, collaboration Internal crowdsourcing Analytical asset (e.g., model) end-to-end lifecycle - DevOpS / MLOpS leading to AiOps creation, comparison, Agile delivery, productionization, measurement, retraining / recreation, etc.

[0082] Some features / modules of the platform may include: ·Analysis Asset Catalog Analysis Code Repository Self-healing model Management model Central development & model management and collaboration environment Decision Science Workbench - Not necessarily just ML and DL, but also simulation, forecasting, AI, etc. Distributed development and deployment (make once, use many) Compliance with the organization's data warehouse (e.g., MTN EVA / DaaS) Batch or frequency modeling and streaming or real-time processing and modeling Access to model algorithms, packages, and live libraries Model interoperability ·execution ·Decision ·rule Recommended

[0083] In embodiments of the present invention, various users may interact with the ADAM platform: Data Scientist Coder - e.g., R, Python, SAS Miner, etc. Model / Release Manager Consumers - e.g., Insights, Excel users, business analysts, business and IT systems and processes, external B2B partners, etc.

[0084] Figure 4 illustrates an exemplary data systems architecture, including an example of an ADAM platform. The exemplary ADAM platform includes access to data related to OSS (Operations Support Systems) and BSS (Business Support Systems) software systems, as typically used by telecommunications and other service providers to manage operations and support business functions. Additionally, the ADAM platform allows for visualization and import of data from available external data sources. Several APIs are also integrated and readily available. ADAM models are then available for training and deployment on various datasets, including a large data lake that is constantly receiving additional datasets, thereby enabling more efficient training of the ADAM platform and any subsequent datasets to which the models are deployed.

[0085] Figure 5 provides a diagram of the data pipeline between the ADAM platform and on-premise systems. As discussed earlier, the on-premise data in each location or country is anonymised before being sent or uploaded to the ADAM platform through CI / CD (Continuous Integration / Continuous Delivery). Once trained, the ADAM platform can be deployed on any premises by downloading the model code for us with real data.

[0086] Figure 6 provides an overview of an exemplary ADAM platform in operation. The Business Semantic Layer ("BSL") contains the curated and governed data locations where business users will consume already generated metrics and KPIs.

[0087] 7-9 detail the adherence of an exemplary ADAM platform to a set of architectural principles.

[0088] FIG. 10 is a schematic diagram of an exemplary logical architecture that may be employed in embodiments of the present invention.

[0089] Table 1 below summarizes the various layers of an exemplary architecture blueprint to illustrate the overall responsibilities that each component layer of the architecture may provide to realize the ADAM platform.

[0090] [Table 1]

[0091] The ADAM platform can be divided into two logical components: the control / management plane and the user plane. The control / management plane can be centralized, for example, at the organizational group level, with most ADAM activities performed and provided by all connected OpCos. In some cases, the control / management plane may only have dummy or anonymized data. Some OpCos may be developed outside of ADAM, and models can be imported into ADAM. In the user plane, any models or other analytical assets developed in the ADAM platform are deployed and run locally at the OpCo (or other local / on-premise point), and the control / management plane can be configured to monitor model performance and accuracy. In the case of entities in banned countries, for example, developed models can run locally without requiring the ADAM control plane to have connectivity.

[0092] 11 and 12 show two exemplary options for integrating the ADAM platform into an OpCo entity, again using MTN as an example. Essentially, option 1 utilizes fiber network rings and network nodes as the network topology, and then utilizes the .NET software framework along with MPLS (Multi-Protocol Label Switching) as the routing technique. Option 2 in FIG. 12 utilizes CI / CD as the software development methodology to help improve the speed and efficiency of the software development process by allowing software to be built, tested, and deployed by building and testing code changes as they are committed to the code repository. Essentially, option

[0093] Table 2 below summarizes some exemplary features / modules of the ADAM platform.

[0094] [Table 2]

[0095] [Table 3]

[0096] The platform may accommodate collaboration, internal crowdsourcing, and asset utilization, and may be configured to allow cloud, edge, and on-premise local deployment and execution of analytical resources, for example, at group headquarters, any of the operating companies, satellite units, client premises, and / or public locations around the world.

[0097] The ADAM platform may further: Integrates the company's internal and external customers, partners such as operating companies, and group functions (CVM, Fintech, Sales, Enterprise, Network, Technology, Public-Private Partnerships). Enhance or improve existing ways of working, use cases, and enable and augment all lines of business within and outside the organization by providing entirely new types of intelligent AI / ML analytic solutions such as real-time insights and alert-based actions and data-driven decisions. Enhance the productivity and effectiveness of data scientists, business analysts, non-technical employees, and management. Strengthen the strategy to modernize the organization by changing its approach to data and analytics and fostering an environment that will exponentially increase the benefits of data and analytics.

[0098] One or more of the techniques described above may be implemented in or using one or more computer systems, such as computer system 100 shown in Figure 13. Computer system 100 may be or include any suitable computer or server. Computer system 100 may be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules executed by computer system 100 may be located both locally and remotely.

[0099] 13, computer system 100 has the functionality of a general-purpose computer. These components may include, but are not limited to, at least one processor 102, memory 104, and a bus 106 that couples various components of system 100, including memory 104, to processor 102. Bus 106 may have any suitable type of bus structure. Computer system 100 may include one or more different types of readable media, such as removable media, non-removable media, volatile media, and non-volatile media.

[0100] Thus, memory 104 may include volatile memory 108 (e.g., random access memory (RAM) and / or cache memory) and may further include other storage media, such as a storage system 110 configured to read from and write to non-removable, non-volatile media, such as a hard drive. It will be appreciated that computer system 100 may also include or be coupled to magnetic disk drives and / or optical disk drives (not shown) for writing to or reading from suitable non-volatile media, which may be connected to bus 106 by one or more data media interfaces.

[0101] The memory 104 may be configured to store program modules 112. The modules 112 may include, for example, an operating system, one or more application programs, other program modules, and program data, each of which may include implementations of a networked environment. The components of the computer system 100 may generally be implemented as modules 112 that perform the functions and / or methodologies of embodiments of the present invention as described herein. It will be understood that embodiments of the present invention may include or be implemented by multiple computer systems 100 that may be communicatively coupled to each other.

[0102] The computer system 100 may be operatively and communicatively coupled to at least one external device 114. For example, the computer system 100 may communicate with external devices 114 in the form of a modem, keyboard, and display. These communications may occur via a suitable input / output (I / O) interface 116.

[0103] Computer system 100 may be configured to communicate with at least one network 120 (e.g., the Internet or a local area network) via network interface device 118 / network adapter. Network interface device 118 may communicate with other elements of computer system 110 as described above via bus 106. It will be understood that the components shown in and described with reference to FIG. 13 are examples only, and that other components may be used instead of or in addition to those shown.

[0104] Usage example With reference to the teachings of Figures 1-13 above, the present invention can be illustrated through the use of example applications of the present invention within various OpCos of MTN.

[0105] EVA systems in several countries generate and / or acquire large datasets regarding customer behavior, spending habits, etc. This data is then anonymized by each of these EVA systems and uploaded to the ADAM platform. The ADAM model performs various models, algorithms, operations, and further functions on the anonymized dataset. Importantly, in each case, the ADAM model is trained on an anonymized dataset, regardless of the dataset's similarity to any other datasets, and as the ADAM model is successively trained, it is able to perform analysis and predictions on each anonymized dataset. Herein lies one of the unique features of the centralized ADAM model: it is not simply trained on homogenous datasets, but is continuously improved with unique anonymized datasets provided by OpCos.

[0106] Once the ADAM model is trained, the model code can be downloaded and deployed to each EVA system for use against real data.

[0107] With particular reference to MTN OpCo, the ADAM model continues to be trained and deployed as follows: -Predict X number of days that customers are likely to be passive so that they can be targeted with personalized campaigns. -Segment your customers into different segments in order to target them with tailored campaigns. -Identify trends in customer data usage to target customers with tailored campaigns at the right time. -Identifying whether a customer is at home, at work, in a hospital or in another organization and whether they are members of the same organization in order to target them with tailored campaigns.

[0108] These are just a few examples, but it is important to note that datasets from different OpCos in different sectors and / or with different functions allow the model to identify important trends that would not be possible if it simply used a homogenized dataset.

[0109] Further Considerations Aspects of the present invention may be embodied as a system, method, and / or computer program product. Accordingly, aspects of the present invention may take the form of hardware, software, and / or combinations of hardware and software, which may be generally referred to herein as "components," "units," "modules," "systems," "elements," etc.

[0110] As used in the claims below, a module will be understood to be a set of code or software program capable of performing one or more specific tasks. It will be further understood that each module may include multiple software programs or code capable of performing the same or similar functions.

[0111] Communicatively coupled refers to, but is not limited to, the exchange of information, commands, or data between devices or platforms.

[0112] Furthermore, aspects of the present invention may take the form of a computer program product having computer-readable program code embodied in one or more computer-readable storage media. The computer-readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or any suitable combination of the above. In the context of this specification, a computer-readable storage medium may be any suitable medium capable of storing a program running on or in connection with a system, apparatus, or device. The program code / instructions may be executed on a single device or on multiple devices (e.g., local and remote devices), and may be executed as a single program or as part of a larger system / package.

[0113] The present invention can be implemented in any suitable form of computer system, including a stand-alone computer or processor participating in a network of computers. Accordingly, a computer system programmed with instructions embodying the methods and / or systems disclosed herein, a computer system programmed to perform aspects of the present invention, and / or a medium having computer-readable instructions stored thereon for converting a general-purpose computer into a system according to aspects of the present invention, fall within the scope of the present invention.

[0114] The charts and / or diagrams included in the figures illustrate example implementations of one or more systems, methods, and / or computer program products according to one or more embodiments of the present invention. It should be understood that one or more blocks in the figures may represent components, segments, or portions of code that include one or more executable instructions for implementing the specified logical functions. In some alternative implementations, the actions or functions identified in the blocks may occur in a different order than shown in the figures, or may occur simultaneously.

[0115] It will be understood that the blocks or steps illustrated in the figures may be implemented by system components or computer program instructions, which may be provided to any suitable computer processor or other device such that the instructions, which may be executed via a computer processor or other device, establish or generate means for performing the functions or actions identified in the figures.

Claims

1. 1. A data management platform comprising: a centralized database having benchmark data stored therein, the centralized database being configured to receive one or more data sets from one or more data sources, the centralized database allowing one or more users to remotely access the centralized database; an analytics module communicatively coupled to the centralized database, the analytics module including one or more analytics tools that enable data analysis of the one or more data sets; a model module communicatively coupled to the centralized database, the model module including one or more algorithms that execute a set of instructions on the one or more datasets, the model module being trainable with the one or more algorithms by comparing the one or more datasets to the benchmark data and deriving one or more output datasets having predictive information for the one or more datasets; A data management platform with

2. The data management platform of claim 1 , wherein the one or more data sources are one or more data warehouses located in one or more countries.

3. 2. The data management platform of claim 1, wherein the data management platform is configured to enable the one or more users to remotely access the centralized database through a network connection to transfer one or more datasets from one or more data sources to the centralized database, the network connection enabling the one or more users to analyze the one or more datasets using the analysis module including an analysis tool, and the network connection enabling the one or more users to train the model module including one or more algorithms by comparing the one or more datasets to the benchmark data and deriving an output dataset having predictive information for the one or more datasets.

4. 2. The data management platform of claim 1, wherein the analytics module including the one or more analytics tools and the model module including the one or more algorithms are dynamically updated and evolved as each instance of the one or more analytics tools analyzes the one or more data sets and each instance of the model module is trained with the one or more algorithms by comparing the one or more data sets to the benchmark data and deriving one or more output data sets having predictive information for the one or more data sets.

5. 2. The data management platform of claim 1, wherein the one or more analytics tools are selected from the group consisting of Tableau, Oracle Business Intelligence, IBM Cognos Analytics, SAS, Microsoft Power BI, Amazon Redshift, Google BigQuery, Snowflake, Alteryx, Cloudera, Apache Hadoop, Google Vertex AI, Microsoft Azure Synapse, Microsoft Data Explorer, CosmosDB, Redis, Azure Cognitive Services, Azure Machine Learning, Spark, Databricks, Sqream, Confluent Kafka, Presto, Trino, Flare, HIDS, and combinations thereof.

6. The data management platform of claim 1 , wherein the one or more algorithms are selected from the group consisting of machine learning algorithms, artificial intelligence algorithms, deep learning algorithms, heuristic algorithms, and combinations thereof.

7. 2. The data management platform of claim 1, wherein the one or more datasets include customer usage information selected from the group consisting of customer voice call usage, customer screen time usage, customer data usage, customer messaging usage, customer device hardware specifications, customer transactions, customer interactions, customer behavior, customer revenue, network operations, network usage, network investments, internal operations, sales information, distribution information, agent operations, merchant operations, agent services, merchant operations, B2B products, B2B product services, digital products, over-the-top applications, customer value management, pricing, operations management, portfolio management, customer location, network location, network transport, network configuration, cybersecurity, and combinations thereof.

8. The data management platform of claim 1 , wherein the predictive information includes information about customer behavior for deriving user-specific product offerings.

9. The data management platform of claim 1 , wherein the centralized database is configured to receive only one or more de-identified data sets to derive de-identified data.

10. 2. The data management platform of claim 1, further comprising a data transmission module that transmits the model module to a database that may be located external to the centralized database, the model module including one or more algorithms that are applicable to one or more datasets available in the database to derive an output dataset having predictive information for the one or more datasets.

11. The data management platform of claim 10 , wherein the model module is capable of being stored on a storage medium.

12. The data management platform of claim 11 , wherein the storage medium is selected from the group consisting of a non-transitory storage medium, a transitory storage medium, and combinations thereof.

13. The data management platform further includes an anonymization module that can be located external to the centralized database, the anonymization module comprising: a data module receiving the one or more data sets from one or more data sources; an anonymization algorithm that anonymizes the one or more datasets to derive anonymized data; a transmission module that transmits the anonymized data to the centralized database; The data management platform of claim 1 .

14. 14. The data management platform of claim 13, wherein the anonymized data is used to train the model module with the one or more algorithms that compare the anonymized data to benchmark data stored in the centralized database to derive an output dataset having predictive information for the anonymized data.

15. 15. The data management platform of claim 14, wherein the model module is configured to be trained with anonymized data, and wherein the model module is applied to one or more datasets distributable at locations selected to comply with country-specific data protection and privacy regulations.

16. 2. The data management platform of claim 1, further comprising an interface module communicatively coupled to the model module to receive the predictive information for the one or more datasets, the interface module further communicatively coupled to one or more user devices thereby enabling the user devices to access the predictive information for the one or more datasets.

17. 1. A method of training a model using anonymized data and applying the model to one or more data sets located at selected locations, comprising: providing a database in which benchmark data is stored, said database being capable of receiving data from one or more data sources; providing an external data source communicatively coupled to the database, wherein one or more data sets stored in the external data source are de-identified by executing a set of instructions to derive de-identified data; enabling data analysis of the data stored in said database using one or more analytical tools; training a model, including one or more algorithms, by comparing the anonymized data to the benchmark data; applying the trained model to one or more datasets, which may be located external to the database, thereby deriving predictive information for the one or more datasets; The method includes:

18. 20. The method of claim 17, further comprising storing the model on a storage medium, thereby enabling the model to be applied to one or more data sets communicatively coupled to the storage medium.

19. 1. A digital management system comprising: a computing device having a processor communicatively coupled to a memory capable of storing one or more data sets obtainable from one or more data sources, the memory storing benchmark data; and an analysis module including an analysis tool, the analysis module communicatively coupled to the memory, the processor capable of executing a set of instructions for the analysis tool to perform an analytical operation on the one or more data sets; a model module including one or more algorithms, the model module communicatively coupled to the memory, the model module capable of being trained by the processor applying the one or more algorithms by comparing the one or more data sets to benchmark data to derive an output data set having predictive information for the one or more data sets; and Digital management system with

20. 20. The digital management system of claim 19, wherein the memory is selected from the group consisting of a non-transitory storage medium, a transitory storage medium, and combinations thereof.

Images