Methods of execution on a computer, non-temporary computer-readable media, and integrated computing entities

Abstract

This invention provides a method for programmatically generating and integrating APIs using machine learning techniques and / or artificial intelligence, as well as an integrated computing entity. [Solution] The method includes processing the integrated data object by one or more processors, at least partially based on an integrated machine learning model, in response to the reception of the integrated data object by one or more processors, in order to identify one or more integrated features associated with the integrated data object; programmatically generating an application programming interface (API) model corresponding to the integrated data object by one or more processors, at least partially based on one or more integrated features; and generating an API generation data object corresponding to the API model for execution by one or more processors.

Description

Technical Field

[0001] Exemplary embodiments generally relate to electronic communication technologies, particularly in the context of the development, integration, and implementation of application programming interfaces (APIs).

Background Art

[0002] In various applications, an API can facilitate communication and data exchange between software products and software services associated with different entities. An exemplary API can be implemented as an intermediate layer between an application and a server, and the server processes and transfers data between them. For example, using an API, a provider can provide data to an external third - party system to facilitate the provision of services and products that can be provided by the third - party system (e.g., a payment processing service). Further, in some embodiments, an API can operate to provide enhanced data security (e.g., by providing an encryption layer, etc.).

[0003] In various examples, the implementation of an API solution requires the integration between two or more systems and / or software platforms so that the two or more systems and / or software platforms can share data / information with each other. As an example, an application (such as a client application) can initiate an API call or a request to an API to obtain information. In response to receiving and validating the API call or request, the API can then call an external server or program and obtain the information requested from the external server or program. Thereafter, the API can transfer the data to the requesting application (such as a client application).

[0004] Traditional systems, methods, and devices for integrating APIs typically require manual development of the API through an iterative process of writing and compiling computer code by one or more software developers. Providers attempting to implement APIs / API solutions to provide third-party services may provide specifications describing target functionality, data structures (e.g., data dictionaries defining data types / definitions), and data structure attributes related to the provider database. In some cases, specifications may be unavailable or outdated, further prolonging the development process. For example, if specifications are unavailable, software developers may analyze and / or map aspects of the provider's system / platform to generate data structures and / or target functionality.

[0005] In another example, software developers may utilize pre-built API templates to develop APIs. However, such templates generally require additional customization and testing to function properly. In many cases, software developers need to repeatedly deploy test APIs throughout the entire integration process, requiring additional resources and time. Therefore, known development methods, even with pre-built API templates, can be inefficient and time-consuming, requiring significant computing resources and skilled labor to ensure system stability and the functionality of the deployed APIs. [Overview of the project] [Problems that the invention aims to solve]

[0006] The inventors of the inventions disclosed herein have identified these and other technical problems and have developed the solutions described herein or disclosed herein.

[0007] Therefore, methods, apparatus, systems, and computer program products for programmatically generating and integrating APIs using, for example, artificial intelligence / machine learning techniques are provided according to exemplary embodiments. [Means for solving the problem]

[0008] According to the first embodiment, a method is provided. The method may include: in response to receiving an integrated data object by one or more processors, processing the integrated data object by one or more processors at least partially based on an integrated machine learning model to identify one or more integrated features associated with the integrated data object; programmatically generating an application programming interface (API) model corresponding to the integrated data object by one or more processors at least partially based on one or more integrated features; and generating an API generation data object corresponding to the API model for execution by one or more processors.

[0009] In some embodiments, API-generated data objects are configured to facilitate the creation and / or modification of APIs and / or one or more API-based data objects.

[0010] In some embodiments, the method may further include periodically sending requests for integration information to update and / or improve the API model after the API model has been programmatically generated.

[0011] In some embodiments, the integrated machine learning model includes a pre-trained supervised machine learning model that is trained at least partially on multiple historical integrated data objects.

[0012] In some embodiments, one or more integration features include one or more of the following: data structure, predicted API type, country, and language.

[0013] In some embodiments, processing of integrated data objects by one or more processors includes performing text analysis on at least a portion of the integrated data objects.

[0014] In some embodiments, one or more API-based data objects are provided in connection with a payment processing service.

[0015] According to a second embodiment, an apparatus is provided. The apparatus may include a processor and a memory for storing program code, wherein the memory and program code are configured to use the processor to process the integrated data object at least in response to the receipt of the integrated data object, at least partially based on an integrated machine learning model, to identify one or more integrated features associated with the integrated data object, to programmatically generate an API model corresponding to the integrated data object at least partially based on one or more integrated features, and to generate an API generation data object corresponding to the API model for execution by one or more processors.

[0016] In some embodiments, API-generated data objects are configured to facilitate the creation and / or modification of APIs and / or one or more API-based data objects.

[0017] In some embodiments, the memory and program code are further configured to use the processor to periodically send requests for integrated information to update and / or improve the API model after the API model has been programmatically generated.

[0018] In some embodiments, the integrated machine learning model includes a pre-trained supervised machine learning model that is trained at least partially on multiple historical integrated data objects.

[0019] In some embodiments, one or more integration features include one or more of the following: data structure, predicted API type, country, and language.

[0020] In some embodiments, processing an integrated data object includes performing text analysis on at least a portion of the integrated data object.

[0021] In some embodiments, one or more API-based data objects are associated with a payment processing service.

[0022] According to a third embodiment, a computer program product is provided. The computer program product may include a non-temporary computer-readable medium for storing program instructions, and the program instructions are operable to cause, at least in response to the receipt of an integrated data object, to process the integrated data object to identify one or more integrated features associated with the integrated data object based at least partially on an integrated machine learning model, to cause the program to programmatically generate an API model corresponding to the integrated data object based at least partially on one or more integrated features, and to generate an API generation data object corresponding to the API model for execution.

[0023] In some embodiments, API-generated data objects are configured to facilitate the creation and / or modification of APIs and / or one or more API-based data objects.

[0024] In some embodiments, program instructions can be further configured to periodically send requests for integration information to update and / or improve the API model after the program has generated the API model.

[0025] In some embodiments, the integrated machine learning model includes a pre-trained supervised machine learning model that is trained at least partially on multiple historical integrated data objects.

[0026] In some embodiments, one or more integration features include one or more of a data structure, a predicted API type, a country, and a language.

[0027] In some embodiments, processing of an integrated data object includes performing text analysis on at least a portion of the integrated data object.

Brief Description of the Drawings

[0028] [Figure 1] It is a device diagram showing an integrated computing entity for executing one or more aspects of the present invention. [Figure 2] It is a diagram showing a system for executing one or more aspects of the present invention. [Figure 3A] It is a diagram showing a method for executing one or more aspects of the present invention. [Figure 3B] It is a diagram showing a method for executing one or more aspects of the present invention. [Figure 4] It is a schematic diagram showing a data structure according to one or more aspects of the present invention. [Figure 5] It is a signal diagram showing communication between a client device, an integrated computing entity, a provider system, and a third-party provider system according to one or more aspects of the present invention.

Embodiments of the Invention

[0029] Some embodiments of this disclosure are described in more detail below with reference to the accompanying drawings. The drawings illustrate some, but not all, embodiments of this disclosure. In fact, various embodiments of this disclosure can be embodied in many different forms and should not be construed as being limited to the embodiments described herein. Rather, these embodiments are provided so as to satisfy the applicable legal requirements of this disclosure. Similar reference numbers refer to similar elements throughout. The terms “data,” “content,” “information,” and similar terms used herein can be used interchangeably to refer to data that can be transmitted, received, and / or stored in accordance with embodiments of this disclosure. Accordingly, the use of such terms should not be construed as limiting the intent and scope of embodiments of this disclosure.

[0030] Furthermore, as used herein, the term “circuit” means (a) a hardware-only implementation of a circuit (e.g., an implementation in an analog circuit and / or a digital circuit), (b) a combination of a circuit and a computer program product including one or more software and / or firmware instructions stored in computer-readable memory that work together to cause a device to perform one or more functions described herein, or (c) a circuit such as one or more microprocessors or parts of one or more microprocessors that require software or firmware for operation even if the software or firmware is not physically present. This definition of “circuit” applies to all uses of this term herein, including in the claims. As another example, as used herein, the term “circuit” also includes an implementation including one or more processors and / or parts thereof, and accompanying software and / or firmware. As yet another example, as used herein, the term “circuit” also includes, for example, baseband integrated circuits or application processor integrated circuits for similar integrated circuits in a mobile phone or server, cellular network equipment, other network equipment (such as core network equipment), field-programmable gate arrays, and / or other computing devices.

[0031] As defined herein, “computer-readable storage medium” can be distinguished from “computer-readable transmission medium” which refers to a physical storage medium (e.g., a volatile or non-volatile memory device) as defined herein.

[0032] As used herein, the term “integration” may refer to the process of installing and configuring an application on a provider system / platform so that the provider system / platform can communicate with and / or exchange data with a third-party application or service application in order to provide a service with one or more functions.

[0033] As used herein, the term “integration data object” can refer to a data object that describes one or more integration features (e.g., those relating to a provider and / or provider platform) on which one or more data analysis and / or integration operations are performed. For example, to integrate a provider platform with a service provider platform (e.g., a third-party platform) via an API, an integration data object may be processed to generate an API in order to facilitate access to one or more services provided by the service provider platform. In some examples, an integration data object may be or include a specification describing a security layer, system protocol, provider requirements and / or target functionality. In some examples, an integration data object may describe a network endpoint or resource on which a communication link must be established to achieve integration between the provider platform and the service provider platform. In other examples, an integration data object may be or include unstructured data (e.g., documents). For example, if the provider is a utility company, the integration data object may include one or more transaction statements, invoices, bills and / or similar documents.

[0034] As defined herein, the term “integrated machine learning model” can refer to data objects that describe the behavior and / or parameters of a machine learning model configured to process integrated data objects to generate an API model. An integrated machine learning model can include multiple machine learning models and / or machine learning model components. For example, an integrated machine learning model can include one or more of the following: a trained supervised machine learning model, a similarity determination machine learning model, a convolutional neural network model, a language-based model, etc. An integrated machine learning model can be trained using multiple historical integrated data objects. For example, multiple historical integrated data objects may be or include multiple documents and / or other unstructured data, and each historical integrated data object may be associated with a specific provider system / platform type and / or multiple integrated features. For example, integrated features may include API model type or service type, country, spoken or written language, etc.

[0035] As defined herein, the term “API model” can refer to a data object that describes the behavior / parameters of an API configured to facilitate the delivery of one or more services, and may include data / information (e.g., computer executable code) necessary to integrate with a third-party application or service. For example, an API model can be associated with a particular set of functions. For example, a payment service can be associated with a payment gateway that facilitates the transfer of information between a payment portal and a bank. In another example, a user registration service can facilitate authentication via a third-party authentication system or sign-in to a provider platform. In yet another example, a translation service can facilitate the conversion of text information from a first language to a target language. Other types of API models include, but are not limited to, mapping services, document management services, search services, and so on. In various embodiments, a particular API model can be associated with a written / spoken language (e.g., English, French, Danish), a country, a computer language / software language (e.g., Java, JavaScript, Python, PHP.NET, Dart, Objective-C, Ruby, Go, Node.js, etc.). Furthermore, an exemplary API model can be associated with a data structure that defines one or more data types and one or more data operations that can be performed with respect to each data type. The exemplary data structure can further define methods for organizing, storing, retrieving, and processing data.

[0036] As used herein, the terms “service provider application” or “third-party application” may refer to a software program, platform, or service configured to provide services to one or more client devices in conjunction with another system / platform (e.g., the provider’s system / platform) via a communication interface. A service provider application may run on a separate compiled codebase or repository from those supporting the provider system / platform. In some embodiments, a service provider application may communicate with the provider system / platform using an API. For example, a service provider application may be a Software as a Service ("SaaS") product or application ("App") product provided, stored, and maintained by a third-party application provider.

[0037] As used herein, the term “Third-Party Application Provider” may refer to a provider of a service provider application via a remote network device, such as a server or processing unit, maintained by a third-party individual / entity, company, or organization. Client devices associated with the provider system can access the service provider application provided by the third-party application provider to perform functions, flows, or actions. In some embodiments, a function, flow, or action generates an effect (e.g., output, change, data modification, etc.) within a group-based communication system, for example, by manipulating data within the provider system (e.g., processing payments or updating user account profiles), or by performing other actions such as providing content to the provider system for rendering at an interface. In other embodiments, a function, flow, or action generates an effect within the third-party application provider to generate an effect within the third-party application provider. In yet another embodiment, a function, flow, or action generates an effect within the provider system, the third-party application provider, and various combinations of other servers or systems.

[0038] As used herein, the term “API-generating data object” may refer to a data object containing computer executable instructions for generating an API and / or, but not limited to, for performing integrated operations between, for example, a provider system (e.g., a utility) and a third-party provider system (e.g., a service provider).

[0039] As used herein, the term “API-based data object” can refer to a set of data and / or instructions representing an item or resource in a provider system / platform. In some embodiments, a service application may perform actions on one or more API-based data objects. Each API-based data object may be associated with an object identifier that uniquely identifies a particular API-based data object within the provider system, and an object type that describes the category of objects to which the API-based data object belongs. In some embodiments, a user may perform actions through a user interface that creates or modifies API-based data objects. Examples of API-based data objects include files created and maintained within the provider system, user account information, and the like.

[0040] The term “client device” can refer to computer hardware and / or software configured to access services made available by a server. In some examples, the server may be associated with another computer system / platform providing the service (such as a third-party application provider / platform). In such examples, the client device may access the service over a network. Client devices include, but are not limited to, smartphones, tablet computers, laptop computers, wearables, personal computers, and enterprise computers.

[0041] The term "user" can refer to an individual, a group of individuals, a company, an organization, etc. In various examples, a user may access a service or system using a client device. A user may also be associated with a user identifier, such as a unique number (e.g., an integer or a string).

[0042] The terms “database,” “datastore,” or “data repository” can refer to a location where data is stored, accessed, modified, and otherwise maintained by a system. Stored data may include user information, account information, and / or similar information associated with a particular provider platform. Exemplary databases, datastores, or repositories may be embodied as one or more data storage devices, one or more separate database servers, or a combination of data storage devices and separate database servers. In some embodiments, a database, datastore, or repository may be embodied as a distributed database / repository, such that some of the stored data is centrally stored in one location, while other data is stored in a single remote location or multiple remote locations. Alternatively, in some embodiments, the data may be distributed across only multiple remote storage locations.

[0043] The embodiments described herein generally relate to systems, methods, apparatus, and computer program products for programmatically generating and integrating APIs using machine learning techniques and / or artificial intelligence.

[0044] Embodiments of the present invention may be implemented in various ways, including computer program products that include manufactured articles. Such computer program products may include one or more software components, such as software objects, methods, data structures, etc. Software components may be coded in any of various programming languages. An exemplary programming language may be a low-level programming language, such as an assembly language associated with a particular hardware framework and / or operating system platform. A software component containing assembly language instructions may require conversion to executable machine code by an assembler before execution by the hardware framework and / or platform. Another exemplary programming language may be a high-level programming language that is portable across multiple frameworks. A software component containing high-level programming language instructions may require conversion to an intermediate representation by an interpreter or compiler before execution.

[0045] Other examples of programming languages ​​include, but are not limited to, macro languages, shell or command languages, job control languages, scripting languages, database query or search languages, and / or reporting languages. In one or more exemplary embodiments, a software component containing one instruction from one of the aforementioned examples of programming languages ​​may be executed directly by an operating system or other software component without first being converted to another form. Software components may be stored as files or other data storage constructs. Software components of similar type or functionally related may be stored together, for example, in a particular directory, folder, or library. Software components may be static (e.g., pre-configured or fixed) or dynamic (e.g., created or modified at runtime).

[0046] A computer program product may include non-temporary computer-readable storage media that store applications, programs, program modules, scripts, source code, program code, object code, bytecode, compiled code, interpreted code, machine code, executable instructions, etc. (also referred herein as executable instructions, execution instructions, computer program product, program code, and / or similar terms used interchangeably herein). Such non-temporary computer-readable storage media include all computer-readable media (including volatile and non-volatile media).

[0047] In one embodiment, the non-volatile computer-readable storage medium may include floppy disks, flexible disks, hard disks, solid-state storage (SSS) (e.g., solid-state drives (SSDs), solid-state cards (SSCs), solid-state modules (SSMs), enterprise flash drives, magnetic tape, or any other non-temporary magnetic media). The non-volatile computer-readable storage medium may also include punch cards, paper tape, optical mark sheets (or any other physical media having a pattern of holes or other optically recognizable markings), compact disc read-only memory (CD-ROM), compact disc rewritable (CD-RW), DVD (digital versatile This may include non-volatile computer-readable storage media such as Blu-ray discs (BDs), any other non-temporary optical media, etc. Such non-volatile computer-readable storage media may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory (e.g., serial, NAND, NOR and / or similar), multimedia memory cards (MMCs), secure digital (SD) memory cards, SmartMedia cards, CompactFlash® (CF) cards, memory sticks, etc. Furthermore, non-volatile computer-readable storage media may also include conductive bridging random access memory (CBRAM), phase-change random access memory (PRAM), ferroelectric random access memory (FeRAM), non-volatile random access memory (NVRAM), magnetoresistive random access memory (MRAM), resistive random access memory (RRAM), silicon oxide-nitride-oxide-silicon memory (SONOS), floating junction gate random access memory (FJG RAM), millipede memory, racetrack memory, and / or similar.

[0048] In one embodiment, the volatile computer-readable storage medium is a random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), fast page mode dynamic random access memory (FPM DRAM), extended data-out dynamic random access memory (EDO DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), double data rate type two synchronous dynamic random access memory (DDR2 SDRAM), double data rate type three synchronous dynamic random access memory (DDR3 SDRAM). This may include SDRAM, Rambus Dynamic Random Access Memory (RDRAM), Twin Transistor RAM (TTRAM), Thyristor RAM (T-RAM), Zero Capacitor (Z-RAM), Rambus Inline Memory Module (RIMM), Dual Inline Memory Module (DIMM), Single Inline Memory Module (SIMM), Video Random Access Memory (VRAM), Cache Memory (including various levels), Flash Memory, Register Memory, and / or similar. Where embodiments are described as using computer-readable storage media, it will be understood that other types of computer-readable storage media may be used instead of or in addition to the computer-readable storage media described above.

[0049] As can be understood, various embodiments of the present invention may be implemented as methods, apparatus, systems, computing devices, computing entities, and / or similar. Thus, embodiments of the present invention can perform specific steps or operations in the form of apparatus, systems, computing devices, computing entities, and / or similar that execute instructions stored on a computer-readable storage medium. Accordingly, embodiments of the present invention may take the form of complete hardware embodiments, complete computer program product embodiments, and / or embodiments that include a combination of a computer program product and hardware that performs specific steps or operations.

[0050] Embodiments of the present invention are described below with reference to block diagrams and flowcharts. Therefore, it should be understood that each block in the block diagrams and flowcharts may be implemented in the form of a computer program product, a complete hardware embodiment, a combination of hardware and a computer program product, and / or a device, system, computing device, computing entity, or similar terminology used interchangeably on a computer-readable storage medium for execution (e.g., executable instruction, execution instruction, program code, etc.). For example, the retrieval, loading, and execution of code may be performed sequentially, such that one instruction is retrieved, loaded, and / or executed at a time. In some exemplary embodiments, the retrieval, loading, and / or execution may be performed in parallel, such that multiple instructions are retrieved, loaded, and / or executed together. Thus, such embodiments can generate a specially configured machine that performs the steps or operations specified in the block diagrams and flowcharts. Therefore, the block diagrams and flowcharts support various combinations of embodiments for performing a specified instruction, operation, or step.

[0051] Referring here to Figure 1, an integrated computing entity 100 is shown for performing operations that lead to the generation and / or integration of APIs. APIs can be used to facilitate user sessions through APIs and / or other network entities. In some embodiments, the integrated computing entity 100 can access a provider system / platform and / or associated databases. The integrated computing entity 100 may comprise a computing device 102 including at least a processor 104 and one or both of non-volatile memory 106 and volatile memory 108. In some embodiments, the computing device 102 may be configured such that the processor 104 is operably coupled to or otherwise able to communicate with one or both of the non-volatile memory 106 and volatile memory 108. In some embodiments, the computing device 102 may comprise a laptop computer, desktop computer, cloud computing device, server, network, handheld computer, mobile computing device, mobile phone, personal digital assistant, tablet computer, or any combination thereof.

[0052] In some embodiments, the processor 104 may include any electronic circuitry configured to perform operations on memory such as non-volatile memory 106 or volatile memory 108. In some embodiments, the processor 104 may include a central processing unit, graphics processing unit, vision processing unit, tensor processing unit, neural processing unit, digital signal processor, image signal processor, synergistic processing element (SPE), field-programmable gate array, sound chip, etc. In some embodiments, the processor 104 may include an arithmetic logic unit (not shown), a control unit (not shown), a speed clock (not shown), etc. In some embodiments, the processor 104 may include one or more processing chips, microcontrollers, integrated chips, sockets, system-on-a-chip (SoC), array processors, vector processors, peripheral processing components, etc.

[0053] In some embodiments, the non-volatile memory 106 may include any computer memory or memory device that can retain stored information even when power is not supplied, such as read-only memory (ROM), flash memory, hard disk, floppy disk, magnetic tape, optical disk, FeRAM, CBRAM, PRAM, SONOS, RRAM, Racetrack memory, NRAM, Millipede, or combinations thereof.

[0054] In some embodiments, the volatile memory 108 may include any computer memory or memory device that requires power to maintain the stored information, such as static random access memory (RAM), dynamic RAM, Z-RAM, TTRAM, A-RAM, ETA RAM, or combinations thereof.

[0055] In some embodiments, the processor 104 or another such component of the computing device 102 may be configured to execute a process or method based on the computer program instructions 110. In some embodiments, the computer program instructions 110 may be stored in either non-volatile memory 106 or volatile memory 108. In some embodiments, the computer program instructions 110 may be operated to cause the processor 104 to execute any of the methods, approaches, processes, etc. disclosed herein. In some embodiments, the computer program instructions 110 may include computer-readable instructions, computer code, coded applications, etc.

[0056] The integrated computing entity 100, processor 104 (and / or coprocessor, or any other arbitrary circuitry assisting or otherwise related to processor 104) can communicate with memory 106 or 108 via a bus to pass information between components of the integrated computing entity 100. The memory device may include, for example, one or more volatile and / or non-volatile memories. In other words, for example, the memory device may be an electronic storage device (e.g., a computer-readable storage medium) including gates configured to store data (e.g., bits) that can be retrieved by a machine (e.g., a computing device such as processor 104). The memory device may be configured to store information, data, content, applications, instructions, etc., so that the device can perform various functions in accordance with the exemplary embodiments of this disclosure. For example, the memory device may be configured to buffer input data for processing by processor 104. Additionally or alternatively, the memory device may be configured to store instructions for execution by processor 104, such as storing messages executed by processor 104 and displayed in a user interface.

[0057] The integrated computing entity 100 can be embodied in various computing devices as described above in some embodiments. However, in some embodiments, the device can be embodied as a chip or chipset. In other words, the device may include one or more physical packages (e.g., a chip) including materials, components, and / or wires on a structural assembly (e.g., a baseboard). The structural assembly can provide physical strength, size preservation, and / or limitations on electrical interaction for the component circuits contained thereon. Thus, in some cases, the device may be configured to implement embodiments of the present disclosure on a single chip or as a single "SOC (system on a chip)". In this way, in some cases, the chip or chipset may constitute means for performing one or more operations to provide the functions described herein.

[0058] The processor 104 can be embodied in many different ways. For example, the processor 104 can be embodied as one or more of various hardware processing means, such as a coprocessor, microprocessor, controller, digital signal processor (DSP), associated processing elements with or without a DSP, or various other circuits including integrated circuits such as ASICs (Application-Specific Integrated Circuits), FPGAs (Field-Programmable Gate Arrays), microcontroller units (MCUs), hardware accelerators, and special-purpose computer chips. Thus, in some embodiments, the processor 104 may include one or more processing cores configured to run independently. A multicore processor 104 can enable multiprocessing within a single physical package. Additionally or alternatively, the processor 104 may include one or more processors 104 configured in tandem via a bus to enable independent instruction execution, pipeline processing, and / or multithreading.

[0059] In exemplary embodiments, the processor 104 may be configured to execute instructions stored in memory 106 or 108, or otherwise to execute instructions accessible to the processor 104. Alternatively or additionally, the processor 104 may be configured to execute hardcoded functions. Thus, whether configured by hardware or software, or a combination thereof, the processor 104 may represent entities (e.g., physically embodied in a circuit) capable of performing the operations according to embodiments of the present disclosure, insofar as they are configured accordingly. For example, if the processor 104 is embodied as an ASIC, FPGA, etc., the processor 104 may be hardware specifically configured to perform the operations described herein. Or, as another example, if the processor 104 is embodied as an instruction execution program, the instructions may specifically configure the processor 104 to perform the algorithms and / or operations described herein. However, in some cases, the processor 104 may be the processor 104 of a particular device (e.g., an encoder and / or decoder) configured to employ embodiments of the present disclosure by further configuring the processor 104 with instructions for performing the algorithms and / or operations described herein. The processor 104 may include, among other things, a clock, an arithmetic logic unit (ALU), and logic gates configured to support the operation of the processor 104.

[0060] In some embodiments, the integrated computing entity 100 may further include a communication interface. In some embodiments, the communication interface may be any means, such as a device or circuit embodied in either hardware or a combination of hardware and software, configured to receive and / or transmit data to and from a network and / or any other device or module communicating with the integrated computing entity 100, such as a wireless local area network (WLAN), a core network, a database or other storage device. In this regard, the communication interface may include, for example, an antenna (or a number of antennas), as well as supporting hardware and / or software to enable communication with a wireless communication network. Additionally or alternatively, the communication interface may include circuitry that interacts with the antenna to cause it to transmit signals through the antenna or to process the reception of signals received through the antenna. In some environments, the communication interface may also support wired communication, or alternatively. For example, the communication interface may include a communication modem and / or other hardware / software to support communication via cable, digital subscriber line (DSL), universal serial bus (USB) or other mechanisms.

[0061] In some embodiments, the integrated computing entity 100 may further include a user interface 112 configured to allow a user or viewer to input data, information, requests, commands, etc., into the computing device 102 via any suitable input approach. For example, in some embodiments, a user or viewer may input commands or other suitable input via signals such as optical or electrical signals, orally, in text, via any suitable computer language, digitally, visually, or a combination thereof. Thus, the user interface 112 may include any of a variety of input devices suitable for capturing user or viewer input. Some, but not all, suitable input devices include video cameras, microphones, digital pointing devices such as mice or touchpads, interactive touchscreens, virtual reality environments, augmented reality environments, one or more sensors configured to sense gestures made by the user or viewer, or a combination thereof.

[0062] In some embodiments, the processor 104 may be operably coupled to or otherwise communicate with the user interface 112 so that a user or viewer can input data, information, requests, commands, etc., to the computing device 102 via any appropriate input approach. As just one example, in some embodiments, the user interface 112 may include a video camera configured to capture video of the user or viewer, a microphone configured to capture audio from the user or viewer, and an audio / video processing unit configured to interpret gestures, voice, or other types of input from the user or viewer and interpret such input as commands, questions, data inputs, etc.

[0063] In some embodiments, the integrated computing entity 100 may further comprise a display 114 configured to present media content to a user or viewer. In some embodiments, the display 114 may be operably coupled to or otherwise communicate with a processor 104 or other such component of the computing device 102. In some embodiments, the display 114 may be coupled to or integrated with the same hardware device as the user interface 112 so that the computing device 102 can transmit media content to the display 114 to present media content to a user or viewer, or have the display 114 present media content while the same user or viewer transmits input to the computing device 102. As just one example, such an integrated hardware device including the user interface 112 and the display 114 may be an interactive display or monitor, a computer screen, a touch-sensitive display, a head-mounted display, a display with an integrated video camera and / or microphone, a display with integrated sensors, or a display configured to otherwise capture input information from a user or viewer (e.g., sound waves, voice information, commands, data, questions, comments, etc.).

[0064] In some embodiments, the integrated computing entity 100 may be either a server-side device or a user device. In some embodiments, the integrated computing entity 100 or its components may be configured to communicate via wired or wireless communication with a network, a server, communication equipment, a user device, another computing device, another processor, another memory device, and / or a mobile device such as a mobile phone or tablet.

[0065] Referring now to Figure 2, an exemplary system 200 is shown. In some embodiments, a user computing entity 202, such as a smart device, can be configured to communicate with an API 204. In some embodiments, the API 204 can be configured to communicate with one or more network entities 206, such as networks or databases of various organizations or businesses (e.g., provider systems or platforms). One or more network entities 206 can be configured to communicate and / or provide access to one or more databases via the API 204. In some embodiments, each of the user computing entity 202, the API 204, and the network entities 206 can be configured to connect to a network 208, such as the Internet, which can secure communications and route them along conventional channels for communication between network entities and between smart devices. As just one example, the network 208 can include a distributed mobile network or a public land mobile network (PLMN) so that the user computing entity 202 (e.g., a smart device) can directly establish association or connection to any of the API 204, network entities 206, etc., via the network 208. Other suitable network and communication technologies are described elsewhere in this specification, and other known network types and communication technologies not disclosed herein are also considered. In some embodiments, the network entity 206 may have access to an API or data exchange configured to retrieve information from one or more databases or network entities. Alternatively, a third-party service may establish a secure connection to the network entity 206 or a database of a particular company or organization via API 204 in order to provide a service or functionality.In some embodiments, the network entity 206 can be configured to generate one or more API-based data objects, which can then be provided (e.g., transmitted, sent) to the end-user interface for display and / or further manipulation. The API-based data objects can be used to dynamically update the user interface operated by the end-user, or to generate user interface data in response to queries / requests.

[0066] Next, referring to Figures 3A and 3B, exemplary methods 301 and 302 for carrying out one or more aspects of the present invention are provided. In some embodiments, methods 301 and 302 can be carried out by processing circuits (e.g., application-specific integrated circuits (ASICs), central processing units (CPUs)). In some examples, one or more of the steps described in Figures 3A and 3B can be carried out by computer program instructions stored in the memory (such as non-temporary memory) of a system employing an embodiment of the present invention and executed by the system's processing circuits (such as a processor). These computer program instructions can instruct the system to function in a particular way, such that the instructions stored in the memory circuit produce a product and its execution performs the function specified in the step / operation of the flowchart. Furthermore, the system may include one or more other circuits. Various circuits of the system may be electronically coupled to one another for transmitting and / or receiving energy, data, and / or information.

[0067] In some examples, embodiments may take the form of a computer program product on a non-temporary computer-readable storage medium that stores computer-readable program instructions (such as computer software). Any suitable computer-readable storage medium can be used, including non-temporary hard disks, CD-ROMs, flash memory, optical storage devices, or magnetic storage devices.

[0068] Referring to Figure 3A, a method 301 for carrying out one or more aspects of the present invention is provided. An exemplary method 301 begins with step / operation 303. In step / operation 303, a processor (such as, but not limited to, the processor of the network entity 206 illustrated in relation to Figure 2 above (e.g., the provider's system / platform)) transmits (e.g., provides, transmits) an integrated data object. As described herein, an integrated data object can refer to a data object that describes one or more integrated functions relating to the provider and / or provider platform. In some examples, an integrated data object may include one or more specifications describing security layers, system protocols, provider requirements, and / or target functions relating to the provider / provider platform. In other examples, an integrated data object may include unstructured data (e.g., one or more documents). For example, if the provider is a utility company, the integrated data object may include one or more transaction statements, invoices, bills, web page information, and / or similar. Additionally, and / or alternatively, integrated data objects may include specifications describing security layers, system protocols, provider requirements, and / or utility-related objectives.

[0069] Referring here to Figure 3B, the exemplary method 302 begins in step / operation 304. In step / operation 304, a processor (such as the processor of the integrated computing entity 100 shown in relation to Figure 1 above, but not limited to) receives an integrated data object.

[0070] In some embodiments, the integrated computing entity 100 utilizes an integrated machine learning model to process integrated data objects and, in step / operation 306, identify one or more integrated features. As described above, the integrated machine learning model may include one or more machine learning models or components. For example, the integrated machine learning model may include one or more trained supervised machine learning models, similarity determination machine learning models, convolutional neural network models, language-based models, or combinations thereof. For example, the integrated machine learning model may include a language-based model configured to process one or more documents using text analysis, including optical character recognition (OCR) in some examples, to extract multiple integrated features. Integrated features may include, for example, predicted API model type or service type, country, spoken or written language, and / or similar. For example, the integrated machine learning model may process multiple documents (e.g., invoices or transaction statements, specifications, web page data / code, combinations thereof, and / or similar) and determine one or more integrated features. As described above, the integrated machine learning model may be trained using multiple historical integrated data objects. For example, multiple historical integration data objects may be or contain multiple documents and / or other unstructured data, and each historical integration data object may be associated with a specific provider system / platform type and / or multiple integration features.For example, if the provider platform / system is a utility company, the integrated machine learning model can process multiple documents associated with and / or provided by the utility company and identify a specific country (e.g., the United States), language (e.g., English and / or Spanish), expected API type (e.g., payment services), and computer code / language (e.g., JavaScript, Python), one or more data types, one or more data operations that can be performed in relation to each data type, and / or a data structure that defines how to organize, store, retrieve, and process data from databases or repositories associated with the utility company.

[0071] In some examples, method 302 may include sending a request for additional integration information / data necessary to generate, update, or improve the API model in step / operation 308. In some embodiments, the integration computing entity 100 may determine that an integration data object describing information does not meet a threshold such that it cannot determine one or more integration features associated with the API model. For example, the integration computing entity 100 may determine that an integration data object does not contain enough information to determine a country, written / spoken language, computer language, data structure, one or more system protocols, or a combination thereof. In such an example, the integration computing entity 100 may send a request for the necessary integration information to the network entity 206 / provider system.

[0072] Returning to Figure 3A, in step / operation 305, the network entity 206 / provider system receives a request for additional integration information. After receiving the request for additional integration information, in step / operation 307, the network entity 206 / provider system sends the additional integration information. In some examples, the integration information may be provided automatically and / or manually. For example, a user may receive a request for additional integration information and provide (e.g., send) the requested information to the integrated computing entity 100. In some examples, the network entity 206 / provider system periodically sends updated integration information to the integrated computing entity 100 in order to dynamically update and / or improve the API model.

[0073] Returning to Figure 3B, at step 310, the integrated computing entity 100 receives the requested integration information. Next, in step / operation 312, the integrated computing entity 100 generates an API model based at least partially on one or more integration features. As detailed herein, the API model may include data objects that describe the behavior / parameters of an API configured to facilitate the provision of one or more services, and may include data / information (e.g., computer code) necessary to generate the API and / or integrate an application or service (e.g., a third-party application). An exemplary API model may further be associated with a specific set of features (e.g., a payment service that facilitates information transfer between a payment portal and a bank), a written / spoken language (e.g., English), a country (e.g., the United States), a computer / software language, a data structure, etc.

[0074] Following step / operation 312, the integrated computing entity 100 generates an API generation data object in step / operation 314, at least partially based on / corresponding to the API model. The API generation data object may be a data object containing computer executable instructions for generating APIs and / or performing integration operations. As an example, the API generation data object may include computer executable instructions for generating and integrating APIs, provider systems (e.g., utilities), and third-party provider systems (e.g., service providers).

[0075] Following step / operation 314, in step / operation 316, the integrated computing entity 100 sends (e.g., provides, transmits) an API generated data object. For example, the integrated computing entity 100 sends the API generated data object to the network entity 206 / provider system for execution.

[0076] Returning to Figure 3A, in step / operation 309, the network entity 206 / provider system receives an API-generated data object. After receiving the API-generated data object, the network entity 206 / provider system performs an integration operation in step / operation 311, at least partially based on the API-generated data object. Performing an integration operation may include generating an API based on the API model / API-generated data object. In some examples, performing an integration operation leads to providing or generating one or more API-based data objects. In some embodiments, an API-based data object contains a set of data and / or instructions representing resources of the provider system / platform. For example, a service application may perform actions on one or more API-based data objects. In some embodiments, a user may perform actions via a user interface that creates or modifies API-based data objects. Examples of API-based data objects include files created and maintained by the provider system, user account information, etc. The network entity 206 / provider system may provide (e.g., send, transmit) one or more API-based data objects for generating user interface data (e.g., on a client device operated by a user) for display and / or further operation. In some embodiments, the integrated computing entity 100 can dynamically provide data / information to update API-based data objects, either continuously, periodically, or in response to specific triggers and / or requests.

[0077] Referring here to Figure 4, a schematic diagram illustrating an exemplary data structure 400 according to one or more embodiments of the present invention. As described herein, the data structure 400 can define one or more data types, one or more data operations that can be performed in relation to each data type, and / or methods for organizing, storing, retrieving, and processing data from a database or repository. As shown in Figure 4, the data structure 400 includes a reference table that defines a plurality of data types. As illustrated, each data structure row is associated with a data field (as illustrated, customer number 401A, last name 401B, first name 401C, telephone number 401D, address 401E, and current balance 401F). Furthermore, each data structure 400 column describes attributes associated with the data field (e.g., data type, data format, field size, description, example). In various embodiments, the integrated computing entity 100 can generate the data structure 400 based on an analysis of integrated data objects (e.g., one or more documents) associated with a provider. Using the data structure, an API model / API can be programmatically generated that can process (e.g., retrieve, use, modify) data from a database or repository associated with another computing entity (for example, so that a provider system and a third-party system can exchange data via an API). It should be understood that the data structure 400 is not limited to the example provided in Figure 4 and may take other forms. For example, exemplary data structures may include hash tables, arrays, lists or linked lists, stacks, graphs, trees and / or similar.

[0078] Referring here to Figure 5, the signal diagram illustrates communication between a client device 501, an integrated computing entity 503, a provider system 505, and a third-party provider system 507 according to one or more aspects of the present invention. As shown, in 502, the provider system 505 sends an integration request to the integrated computing entity 503. In response to receiving the integration request, in 504, the integrated computing entity 503 sends a request for an integrated data object to the provider system 505. Next, in 506, the provider system 505 sends the integrated data object to the integrated computing entity 503. In 508, upon receiving the integrated data object, the integrated computing entity 503 processes the integrated data object to identify one or more integration features (e.g., target parameters, API type, etc.). Next, in 510, the integrated computing entity 503 generates an API model based at least partially on one or more integration features. In some examples, in 512, the integrated computing entity 503 sends a request for additional integration information to the provider system 505. In response to receiving a request for additional integration information, provider system 505 transmits the integration information at 514. At 516, the integration computing entity 503 updates its API model based at least partially on the received additional information. At 518, the integration computing entity 503 transmits an API generated data object to provider system 505. At 520, the API generated data object may contain instructions for programmatically generating the API and / or performing one or more integration operations between provider system 505 and third-party provider system 507. At 522, client device 501 initiates an API request or call via the API. As illustrated, at 524, provider system 505 requests resources from third-party provider system 507 in response to receiving the API request. At 526, third-party provider system 507 transmits the resources and fulfills the request.Next, in 528, the provider system provides / updates one or more API-based data objects that can be used to generate user interface data via the interface of the client device 501.

[0079] Using the techniques described above, APIs can be programmatically generated and integrated with minimal developer input (e.g., extensive inspection). Furthermore, the integrated computing entity can independently update the API model associated with the API when the system obtains new information from or about the provider system and / or similar provider systems.

[0080] In some embodiments, the blocks of a flowchart support combinations of means for performing a specified function, and combinations of actions for performing a specified function. It will also be understood that one or more blocks of a flowchart, and combinations of blocks within a flowchart, may be implemented by a dedicated hardware-based computer system, or by a combination of dedicated hardware and computer instructions, to perform the specified function.

[0081] In some embodiments, certain aspects of the above behaviors may be modified or further amplified. Furthermore, in some embodiments, additional optional behaviors may be included. Modifications, additions, or amplifications of the above behaviors may be made in any order and combination.

[0082] Therefore, methods, apparatus, and systems for programmatically generating and integrating APIs using, for example, artificial intelligence / machine learning techniques are provided according to exemplary embodiments.

[0083] According to the first embodiment, a method is provided. The method includes: processing the integrated data object by one or more processors, at least partially based on an integrated machine learning model, in response to the reception of the integrated data object by one or more processors, in order to identify one or more integrated features associated with the integrated data object; programmatically generating an application programming interface (API) model corresponding to the integrated data object by one or more processors, at least partially based on the one or more integrated features; and generating an API generation data object corresponding to the API model for execution by one or more processors.

[0084] In some embodiments, the API-generated data object is configured to facilitate the creation and / or modification of APIs and / or one or more API-based data objects.

[0085] In some embodiments, the method may further include periodically sending requests for integration information to update and / or improve the API model after the API model has been generated programmatically.

[0086] In some embodiments, the integrated machine learning model includes a trained supervised machine learning model that is trained at least partially on a plurality of historical integrated data objects.

[0087] In some embodiments, the one or more integration features include one or more of the following: data structure, prediction API type, country, and language.

[0088] In some embodiments, the processing of the integrated data object by one or more processors includes performing text analysis on at least a portion of the integrated data object.

[0089] In some embodiments, the one or more API-based data objects are associated with a payment processing service.

[0090] According to a second embodiment, an apparatus is provided. The apparatus comprises a processor and a memory for storing program code, wherein the memory and the program code are configured such that the processor processes the integrated data object in response to the reception of the integrated data object, at least based on an integrated machine learning model to identify one or more integrated features associated with the integrated data object, programmatically generates an API model corresponding to the integrated data object, at least based on the one or more integrated features, and the one or more processors generate an API generation data object corresponding to the API model for execution.

[0091] In some embodiments, the API-generated data object is configured to facilitate the creation and / or modification of APIs and / or one or more API-based data objects.

[0092] In some embodiments, the memory and the program code are further configured by the processor to periodically send requests for integrated information to update and / or improve the API model, at least after the API model has been programmatically generated.

[0093] In some embodiments, the integrated machine learning model includes a trained supervised machine learning model that is trained at least partially on a plurality of historical integrated data objects.

[0094] In some embodiments, the one or more integration features include one or more of the following: data structure, predicted API type, country, and language.

[0095] In some embodiments, processing the integrated data object includes performing text analysis on at least a portion of the integrated data object.

[0096] In some embodiments, the one or more API-based data objects are associated with a payment processing service.

[0097] According to a third embodiment, a computer program product is provided. The computer program product comprises a non-temporary computer-readable medium for storing program instructions, wherein the program instructions are operable to at least, in response to the receipt of an integrated data object, cause the integrated data object to be processed at least partially based on an integrated machine learning model to identify one or more integrated features associated with the integrated data object, cause the program to generate an API model corresponding to the integrated data object at least partially based on the integrated features, and generate an API generation data object corresponding to the API model for execution.

[0098] In some embodiments, the API-generated data object is configured to facilitate the creation and / or modification of APIs and / or one or more API-based data objects.

[0099] In some embodiments, the program instructions can be further configured to periodically send requests for integrated information to update and / or improve the API model, at least after the API model has been generated programmatically.

[0100] In some embodiments, the integrated machine learning model includes a trained supervised machine learning model that is trained at least partially on a plurality of historical integrated data objects.

[0101] In some embodiments, the one or more integration features include one or more of the following: data structure, prediction API type, country, and language.

[0102] In some embodiments, the processing of the integrated data object includes performing text analysis on at least a portion of the integrated data object.

[0103] Many modifications and other embodiments of the invention described herein will be conceived by those skilled in the art with regard to these inventions, benefiting from the teachings shown in the foregoing description and the accompanying drawings. It should be understood that the invention should not be limited to the specific embodiments disclosed, and that modifications and other embodiments are intended to be included within the scope of the appended claims. Furthermore, while the foregoing description and the accompanying drawings describe exemplary embodiments in the context of specific exemplary combinations of elements and / or functions, it should be understood that alternative embodiments may provide different combinations of elements and / or functions without departing from the scope of the appended claims. In this regard, for example, different combinations of elements and / or functions other than those explicitly described above are intended to be included within the scope of the appended claims. Certain terms are used herein, but they are used in a general and descriptive sense only and not for limiting purposes.

[0104] To provide an overall understanding, specific exemplary embodiments are described. However, it will be understood by those skilled in the art that the systems, apparatus, and methods described herein can be adapted and modified to provide systems, apparatus, and methods for other suitable applications, and that other additions and modifications can be made without departing from the scope of the systems, apparatus, and methods described herein.

[0105] While the embodiments described herein are illustrated and described in particular, it will be understood that various modifications of form and detail are possible. Unless otherwise specified, the illustrated embodiments are understood to provide exemplary features of various details of a particular embodiment, and therefore, unless otherwise specified, illustrated features, components, modules, and / or aspects can be combined, separated, replaced, and / or rearranged in other ways without departing from the disclosed system or method. Furthermore, the shapes and sizes of components are also exemplary and can be modified without affecting the scope of the exemplary system, apparatus, or method disclosed in this disclosure unless otherwise specified.

[0106] This specification uses conventional terminology in the fields of telecommunications, computing entities / devices, payment services, artificial intelligence, and machine learning. These terms are known in the art and are provided for convenience only as non-limiting examples. Accordingly, the interpretation of the corresponding terms in the claims is not limited to any specific definition unless otherwise specified. Accordingly, the terms used in the claims should be given the broadest reasonable interpretation.

[0107] While specific embodiments have been illustrated and described herein, it will be understood by those skilled in the art that any configuration adapted to achieve the same objective may substitute for the specific embodiments illustrated. Many adaptations are obvious to those skilled in the art. Therefore, this application is intended to cover all adaptations or variations.

[0108] The above detailed description includes references to accompanying drawings that form part of the detailed description. The drawings illustrate specific implementable embodiments. These embodiments are also referred to herein as “Examples.” Such embodiments may include elements in addition to those illustrated or described. However, the inventors also intend embodiments in which only the illustrated or described elements are provided. Furthermore, the inventors also intend embodiments that use any combination or arrangement of those illustrated or described elements (or one or more embodiments thereof) with respect to a particular embodiment (or one or more embodiments thereof) or to other embodiments (or one or more embodiments thereof) illustrated or described herein.

[0109] All publications, patents, and patent documents referenced herein are incorporated herein by reference in whole, as if they were incorporated individually by reference. Where there is a conflict between usage in this specification and those documents incorporated herein by reference, the usage in the incorporated reference should be considered to supplement the usage herein. In the event of an incompatible conflict, the usage herein shall prevail.

[0110] In this specification, the terms "a" or "an" are used to mean "one or more," regardless of other examples or uses of "at least one" or "one or more," as is common in patent documents. In this specification, unless otherwise indicated, the term "or" is used to mean non-exclusive "or," such that "A or B" includes "A but not B," "B but not A," and "A and B." In this specification, the terms "including" and "in which" are used as plain English equivalents of the terms "comprising" and "wherein," respectively. Also, in the following claims, the terms "including" and "comprising" are open-ended, meaning that a system, apparatus, article, or process that includes elements in addition to those enumerated after such terms in a claim is still considered to be within the scope of that claim. Furthermore, in the following claims, the terms “first,” “second,” “third,” and / or similar terms are used merely as labels and are not intended to impose numerical requirements or relative order of operations or organizations on their subjects.

[0111] The above description is intended to be illustrative and not limiting. For example, the above embodiments (or one or more aspects thereof) can be used in combination with one another. Other embodiments can be used, for example, by those skilled in the art after considering the above description. The abstract is provided in compliance with 37 CFR §1.72(b) to enable readers to quickly confirm the nature of the technical disclosure and is submitted with the understanding that it will not be used to interpret or limit the claims or their meaning.

[0112] In this detailed description, various features may be grouped together for the sake of clarity in the disclosure. This should not be interpreted as meaning that any disclosed features not included in the claims are essential to the claims. Rather, the subject matter of the invention may consist of fewer features than all of the features of a particular disclosed embodiment. Therefore, the following claims are incorporated herein into the detailed description, and each claim is considered independent as a separate embodiment, and such embodiments may be combined with one another in various combinations or rearrangements. The scope of the embodiments should be determined with reference to the appended claims, along with the entire scope of equivalents to which such claims are entitled.

Claims

1. The integrated computing entity provides an integrated machine learning model trained on at least historical information associated with past transactions facilitated by the integrated computing entity, In the integrated computing entity, integrated information relating to payment processing requests is received from a network device or a third-party provider's system, and the transaction between a client device associated with the payer and the network device associated with the recipient is initiated or facilitated, and the integrated information is: Security requirements of the aforementioned network device or the system of the aforementioned third-party provider, The functionality of the aforementioned network device or the system of the aforementioned third-party provider, The structure of the network device or the third-party provider's system, Transaction statements associated with the aforementioned payer, Invoices associated with the aforementioned payer or recipient, Invoices associated with the aforementioned payer or recipient, or The network, the third-party provider's system, or at least one type of client device, The integrated computing entity processes the integrated information using the integrated machine learning model and identifies one or more integrated features associated with the network device or the third-party provider's system. The one or more integrated features described above are: Predictive Application Programming Interface (API) type, country, Spoken language or written language, Including programming or software languages, Using the integrated computing entity, generate an API model corresponding to the integrated information, at least partially based on one or more integrated features. Using the aforementioned integrated computing entity, generate API generation data objects corresponding to the API model for execution, The integrated computing entity transmits the API-generated data object corresponding to the API model to the network device or the third-party provider's system. The API generation data object includes computer executable program code configured to be executed to generate an API used to initiate or facilitate the transaction between the payer and the recipient, Methods of execution on a computer, including [specific examples].

2. The method executed on a computer according to claim 1, wherein the API generated data object is further configured to facilitate one or more of the following when the API generated data object is executed: modifying the API, generating one or more API-based data objects, or modifying one or more API-based data objects.

3. A method performed on a computer according to claim 1, further comprising, following the generation of the API model, periodically sending from the integrated computing entity to the network device or the third-party provider's system one or more requests for additional integrated information to update and / or improve the API model.

4. The method performed on a computer according to claim 1, wherein processing the integrated information includes performing text analysis of at least a portion of the integrated information using the integrated machine learning model by the integrated computing entity.

5. The method executed on a computer according to claim 1, wherein the integrated information includes an invoice or bill provided to the integrated computing entity by the network device, the payer's device, or the third-party provider's system for initiating or facilitating the transaction between the payer and the recipient.

6. Processing the integrated information using the integrated machine learning model means that Using the integrated computing entity, identify or define multiple data fields of the invoice or bill associated with the requested transaction, Using the integrated computing entity, identify one or more values ​​or strings in each of the multiple data fields of the invoice or bill associated with the requested transaction. A method to be performed on a computer according to claim 5, further comprising:

7. Using the integrated computing entity, compare the data structure of the invoice or bill with one or more data structure requirements of the network device or the third-party provider's system. Using the integrated computing entity, identify one or more data operations necessary to align the data structure of the invoice or bill with one or more data structure requirements of the network device or the third-party provider's system. A method performed on a computer according to claim 6, further comprising:

8. The method performed on a computer according to claim 7, wherein the one or more data operations include one or more of the following: data organization operations, data reorganization operations, data reconstruction operations, data storage operations, data acquisition operations, or data processing operations.

9. Processing the integrated information using the integrated machine learning model means that A method performed on a computer according to claim 7, further comprising using the integrated computing entity to determine the predictive API model type based on one or more data restructuring operations necessary to align the data structure of the invoice with one or more data structure requirements of the network device or the third-party provider's system.

10. Generating the aforementioned API model is The method performed on a computer according to claim 6, further comprising the integrated computing entity generating the API model based at least in part on the predictive API model type and the one or more values ​​or strings of each of the plurality of data fields of the invoice or the invoice associated with the requested transaction.

11. The integrated machine learning model is a machine learning model trained by the integrated computing entity based on at least multiple documents and unstructured data associated with multiple different systems or platforms, and multiple different integrated features supported by the multiple different systems or platforms. The method to be executed on a computer as described in claim 1.

12. The method executed on a computer according to claim 1, wherein the recipient is a public utility company that provides public services to the payer.

13. The method executed on a computer according to claim 12, wherein the invoice or bill includes an account summary and a public utility bill from the utility company indicating the amount payable by the payer for the provision of public services from the recipient to the payer over a certain period of time.

14. A non-temporary computer-readable medium storing instructions that, when executed on at least one processor, causes it to perform the method according to any one of claims 1 to 13.

15. At least one processor, An integrated computing entity comprising at least one memory containing stored computer program instructions, wherein the computer program instructions are executed by the at least one processor, The integrated computing entity provides an integrated machine learning model trained on at least historical information associated with past transactions facilitated by the integrated computing entity, In the integrated computing entity, the integrated information relating to payment processing requests is received from a network device or a third-party provider, and the transaction between a client device associated with the payer and the network device associated with the recipient is initiated or facilitated, and the integrated information is: Security requirements of the aforementioned network device or the system of the aforementioned third-party provider, The functionality of the aforementioned network device or the system of the aforementioned third-party provider, The structure of the network device or the third-party provider's system, Transaction statements associated with the aforementioned payer, Invoices associated with the aforementioned payer or recipient, Invoices associated with the aforementioned payer or recipient, or The network, the third-party provider's system, or at least one type of client device, The integrated computing entity processes the integrated information using the integrated machine learning model and identifies one or more integrated features associated with the network device or the third-party provider system. The one or more of the aforementioned integrated information are Predictive Application Programming Interface (API) type, country, Spoken language or written language, Including programming or software languages, Using the integrated computing entity, generate an API model corresponding to the integrated information, at least partially based on one or more integrated features. Using the aforementioned integrated computing entity, generate API generation data objects corresponding to the API model for execution, The integrated computing entity transmits the API-generated data object corresponding to the API model to the network device or the third-party provider's system. The API generation data object includes computer executable program code configured to be executed to generate an API used to initiate or facilitate the transaction between the payer and the recipient, An integrated computing entity that causes the integrated computing entity to perform at least the following.

16. The integrated computing entity according to claim 15, wherein the API-generated data object is further configured to facilitate one or more of the following when the API-generated data object is executed: modifying the API, generating one or more API-based data objects, or modifying one or more API-based data objects.

17. When the computer program instructions stored in the at least one memory are executed by the at least one processor, The integrated computing entity according to claim 15, further causing the integrated computing entity to periodically send one or more requests for additional integration information to update and / or improve the API model to the network device or the third-party provider's system, following the generation of the API model.

18. The integrated computing entity according to claim 15, wherein processing the integrated information includes performing text analysis on at least a portion of the integrated information using the integrated machine learning model.

19. The integrated computing entity according to claim 15, wherein the integrated information includes an invoice or bill provided to the integrated computing entity by the network device, the payer's device, or the third-party provider's system for initiating or facilitating the transaction between the payer and the recipient.

20. When the computer program instructions stored in the at least one memory are executed by the at least one processor, at least, Using the integrated computing entity, identify or define multiple data fields of the invoice or bill associated with the requested transaction, Using the integrated computing entity, identify one or more values ​​or strings in each of the multiple data fields of the invoice or bill associated with the requested transaction. by, The integrated computing entity is made to process the integrated information using the integrated machine learning model. The integrated computing entity according to claim 19.

21. When the computer program instructions stored in the at least one memory are executed by the at least one processor, at least, Using the integrated computing entity, compare the data structure of the invoice or bill with one or more data structure requirements of the network device or the third-party provider's system. Using the integrated computing entity, identify one or more data operations necessary to align the data structure of the invoice or bill with one or more data structure requirements of the network device or the third-party provider's system. To have the integrated computing entity perform the following further: The integrated computing entity according to claim 20.

22. The integrated computing entity according to claim 21, wherein the one or more data operations include one or more of the following: data organization operations, data reorganization operations, data reconstruction operations, data storage operations, data retrieval operations, or data processing operations.

23. When the computer program instructions stored in the at least one memory are executed by the at least one processor, at least, Using the integrated computing entity, the integrated computing entity is instructed to process the integrated information using the integrated machine learning model by determining the predictive API model type based on one or more data restructuring operations necessary to align the data structure of the invoice with one or more data structure requirements of the network device or the third-party provider's system. The integrated computing entity according to claim 21.

24. When the computer program instructions stored in the at least one memory are executed by the at least one processor, The integrated computing entity according to claim 20, wherein the integrated computing entity further causes the integrated computing entity to generate the API model by generating the API model at least in part based on the predictive API model type and one or more values ​​or strings of each of the plurality of data fields of the invoice or the invoice associated with the requested transaction.

25. The integrated computing entity according to claim 15, wherein the integrated machine learning model is a machine learning model trained by the integrated computing entity on at least a plurality of documents and unstructured data associated with a plurality of different systems or platforms, and a plurality of different integrated features supported by the plurality of different systems or platforms.

26. The integrated computing entity according to claim 15, wherein the recipient is a public utility company that provides public services to the payer.

27. The integrated computing entity according to claim 26, wherein the invoice or bill includes a public utility bill from the utility company that provides an account summary and the amount of payment made by the payer for the provision of public services from the recipient to the payer over a certain period of time.

Images