Invented by Shahid N. Shah, Netspective Communications LLC

The market for blockchain systems for natural language processing (NLP) is rapidly growing, as companies seek to leverage the power of blockchain technology to improve the accuracy and efficiency of their NLP applications. Blockchain technology offers several advantages over traditional NLP systems, including increased security, transparency, and decentralization.

One of the key benefits of blockchain technology is its ability to provide a secure and transparent platform for data sharing and collaboration. This is particularly important in the field of NLP, where large amounts of data are often required to train and improve machine learning models. By using a blockchain-based system, companies can ensure that their data is secure and tamper-proof, while also allowing for easy collaboration with other organizations.

Another advantage of blockchain technology is its ability to decentralize data storage and processing. This means that data can be stored and processed on a distributed network of computers, rather than being centralized on a single server. This can help to improve the scalability and performance of NLP applications, as well as reducing the risk of data loss or corruption.

The market for blockchain systems for NLP is expected to grow significantly in the coming years, as more companies recognize the potential benefits of this technology. According to a recent report by MarketsandMarkets, the global market for blockchain in healthcare is expected to grow from $176.8 million in 2018 to $5.61 billion by 2025, at a compound annual growth rate (CAGR) of 63.85%.

One of the key drivers of this growth is the increasing demand for NLP applications in healthcare, as healthcare providers seek to improve patient outcomes and reduce costs. NLP can be used to analyze large amounts of medical data, such as electronic health records, to identify patterns and insights that can help to improve diagnosis and treatment.

Other industries that are expected to drive demand for blockchain systems for NLP include finance, legal, and customer service. In these industries, NLP can be used to automate repetitive tasks, such as customer support inquiries or legal document analysis, freeing up time for more complex tasks that require human expertise.

Overall, the market for blockchain systems for NLP is poised for significant growth in the coming years, as companies seek to leverage the power of blockchain technology to improve the accuracy and efficiency of their NLP applications. With its ability to provide secure and transparent data sharing, decentralized processing, and scalability, blockchain technology is well-positioned to become a key enabler of the next generation of NLP applications.

The Netspective Communications LLC invention works as follows

A blockchain-configured system includes a record bank and a router configured for blockchains. The router converts the data into a standard format. The blockchain-configured record bank can be coupled or include a data repository. The blockchain configured record banks can be configured so that they are coupled to the data providers through a router via a communication network. The blockchain configured records bank can store the data that is received from the data providers and be accessed or searched from inside or outside of the blockchain configured record banks. The blockchain configured recordbank can be coupled with or include a data log unit that maintains the metadata associated with data and is configured to facilitate natural-language processing capabilities. The router and blockchain configured record banks may be coupled with machine learning system metadata validation system and master data validity system.

Background for Blockchain System for Natural Language Processing

Technical Field

The embodiments described herein relate generally to blockchain systems and, more specifically, to blockchain systems that are used with natural-language processing systems.

Description of Related Art

Hospitals and other medical providers, such as nursing homes or centers, medical offices or centers, or medical centers, keep records on their patients’ medical history, demographic information, or any other type of record. These records can include information like demographics of patients, medical histories, diagnostic and pathology results of patients, prescriptions or medical reports, etc. These sources of medical care can use this information for many different purposes. Some examples include, but are not limited to, tracking patients and their records; billing; historical assessments; future care-taking, appropriate ongoing medical or health assessment, treatment or evaluation, or other similar purposes.

The medical sources could require data to be collected from multiple sources and stored in a central repository. Data from different sources can be in different digital formats, and not all of them are standardized to a specific format. The medical sources may have difficulty handling the data, resulting in data leakage, loss, data asynchronization or other losses.

In cases where data is not standardised, it may be difficult to search for the data in general or a particular portion. It can be difficult to search for data within metadata, whether you are searching from the source itself or outside.

There is also a requirement for a system that can retrieve data from various medical sources, convert it into a standard digital format and then store it in the data bank of medical source. It is also necessary to have a system that can be configured to use natural language on metadata and master data, and to make indexing and search from the medical source itself or from the outside easy.

An embodiment of the invention provides a geographically distributed system based on a blockchain configuration for transforming semi-structured data into structured computerized data for a records database with a network of content-based routers that are connected to a plurality blockchain configured records databases receiving unstructured and semi-structured data from a number of computers providing data in a network enabled by blockchain. The system comprises a primary proxy database stored on a non-transitory tangible computer readable medium, and a special purpose processor implemented on a chip. The first proxy device creates a backup for data associated with a data provider computer in a digital format. The first proxy device communicates with the computer of the first data source to back up the data. This is done through a proxy object. The system comprises a first content-based router configured for blockchain, which is one of a plurality of content-based routers configured for blockchain. This router includes a special purpose processor implemented on a secondary integrated circuit chip. It is configured to collect data from the first proxy databases and convert it to a structured computerized dataset according to a standard digital format associated with blockchain configured records database. The first content-based router configured for blockchain is located physically at a gateway that is associated with the data provider computer, providing the data provider computer with a first digital access point to the distributed blockchain configured records databases. The system comprises the blockchain configured records databases stored on a tangible non-transitory medium, including a special purpose processor implemented on a 5th integrated circuit chip for storing and indexing the structured computerized data in the standardized format. It also provides a plurality distributed digital access points which includes the 1st digital data point communicating with the 1st data provider computer via the distributed 1st digital access point. The system comprises a master database validation system that is communicatively and operationally coupled with the blockchain configured records databases and the first content-based router, and includes a repository for master data instances stored in a standardized digital format. The system also includes a metadata verification system that is separate and not located with the master data confirmation system. It is communicatively and operationally coupled to the first content-based router configured on blockchain, the records database configured on blockchain, and the master validation system. The first content-based router configured on blockchain is communicatively connected to a machine-learning system. The machine learning system contains internal extensible taxonomies that are built in a computerized form based on the structured data in the records database. Internal extensible taxonomies can be defined by a computerized profile, which includes digitally-stored parent terms and child terms as well as digital identifiers that indicate the digitally-stored parent terms. The computerized profile also includes pointers that show mutual connections between the digitally-stored parent terms, child terms and pointers. The machine learning system also includes external taxonomies that are pulled from other systems, not directly connected to the blockchain configured records databases. These external systems can be accessed by a crawler enabled by a search engine and merged digitally with the internal taxonomies by mapping similar terms. The machine learning system has a memory to store both the internal extensible taxes and the external taxonomies which are digitally combined with the internal extensible taxes. The machine learning system includes a semantics appliance consisting of a special purpose processor implemented on a 7th integrated circuit chip, configured to map the unstructured or semistructured dataset that is inflowing with the structured computerized data already stored in blockchain configured records databases and master data and metadata. The first local computer is housed within a material frame and is physically and communicatively attached to the first computer. It also communicates with the remote blockchain configured record database.

These and other aspects of embodiments will be easier to appreciate and understand when they are viewed in conjunction with the accompanying drawings and description. The following descriptions are intended to illustrate and not limit the possibilities of preferred embodiments. You can make many modifications and changes within the scope of these embodiments without departing from its spirit. The embodiments include all such modifications.

The embodiments and their various features and beneficial details are described in detail with the help of the non-limiting embodiments, which are shown in the accompanying illustrations and detailed in this description. The descriptions of well-known components are left out to avoid confusing the embodiments. These examples are provided to aid in understanding the various ways the embodiments can be used and to make it easier for those skilled in the art to use the methods. The examples are not meant to limit the scope of the embodiments described herein.

In the following detailed description, we refer to the accompanying drawings which form a part of this document. These are used to illustrate specific embodiments that can be practiced. These embodiments are also known as “examples” in this document. These embodiments, also referred to herein as “examples”, are sufficiently detailed to allow those skilled in art to use them. It is also to be understood that embodiments can be combined or that other embodiments may have been utilized.

In this document the terms?a?” or?an? are used. “The terms?a????? or?an?? are used in this document. As is usual in patent documents, they are used to include more than one. The term “or” is used in this document. This document uses the term?or? to mean a?nonexclusive? Unless otherwise stated.

The embodiments provide a method and system for transforming unstructured or semi-structured data to structured data using machine learning tools, systems and metadata. Now, let’s look at the drawings and in particular to FIGS. “Preferred embodiments are illustrated in FIGS. 1 through 4 where the same reference characters indicate corresponding features throughout all figures.

FIG. The FIG. 1 is intended to illustrate, in a general way, but without limitation, an example high-level system architecture 100, according to a particular embodiment. The architecture 100 may include a records data base 126 for storing health records from various sources, such as a plurality clinical data providers via an HLR content based router (CBR)108. The records database can also be configured to manage the metadata and master data associated with health records. The records database can be configured in order to create natural-language data processing capabilities based on the metadata and master data defined over a communications network 128.

As shown in FIG. A social network platform (130) and a number of clinical data providers (102, 124) can serve as sources for health records. For example, the clinical data provider 102 can be a doctor’s office, a hospital or clinic. As shown in FIG. As shown in FIG. 1, the clinical data providers 102 may include internal systems. These can include, for example databases or data storage capabilities. The clinical data providers 102 can be configured so that they interact with the proxy database 104 in order to back up the data related to them. The clinical data provider can backup data from the proxy database through one or more proxy object 106. The one or multiple proxy objects 106 can include references to proxy database to establish a link between the clinical data providers 102 and proxy database through database drivers. The database drivers will be explained in greater detail with FIG. 2. “The data described herein may include, but not be limited to, doctor visits, laboratory tests, hospital stays and clinical trials. It can also include patient problems, health information about patients, patient habits, medical history of patients, patient appointments, medical insurance for patients, patient medical bills, and other related data.

The Health Level 7 (HL7) content-based router (CBR) can be configured as a hardware device that is linked to a database, data storage facility, or capability. It can also include a local interface for handling direct links, such as 110 or 112, or 114 or 116 or 120 or 122, to communicate with nodes, such as the clinical information providers 102 and 124 and the records database 126, over the communication network 128, The HL7 CBR 108, for example, can be located at a gateway to allow the various sources of health records, such as the clinical providers 102, 124 and the network platform 130, or the records database 126, to communicate with each other via the communication network 128, in an example. In some embodiments several HL7 CBRs like the HL7 CBRs 108 may be located at each or more of the gateways. In the figure, for example, there are three HL7-CBRs. 1. For example, each HL7 CBR can be configured at the endpoints of the clinical data providers (102, 124), the network platform (130) or the records database (126), to allow them to communicate over the communication network (128). In some embodiments, one HL7 CBR may be configured as an endpoint or gateway for the records databases 126. This allows the records database to exchange, integrate and share data with other nodes, including the clinical data providers 102 or 124 or the social networking platform 130 or any node. In an embodiment, the CBR 108 can be managed, controlled, and operated by the records data base 126. It may also be located proximate to the records database 126 but remote from the clinical providers 102, 124 and 130. The HL7 108 CBR can be configured for data collection from one or more proxy database such as proxy database 104, 132. The HL7 CBR 108 is configured to convert data into a standard digital format, such as HL7. This allows the data to be validated and conform to a standard mechanism or standard. The HL7 standard described in this document may provide a framework to exchange, integrate, share, or retrieve health information from the records database 126. The HL7 standard may also refer to specific standards, such as HL7 v2.x or v3.0 and HL7 reference information model (RIM), for example. The organization may have created the clinical data providers (102 and 124), the social networking platform (130) or the records database (126).

In one example, the clinical provider 102 can interact with another clinical provider 124 via the HL7 CBR (108), either through records database or without records databases 126. This allows them to exchange data. The clinical data providers 124 can be configured with a proxy database to backup the clinical data that is associated with them. The clinical data provider can include one or multiple proxy objects 134 for backing up data in the proxy database. The proxy objects 134 may refer to the proxy data 132 in order to establish a link between the clinical data providers 124 and 132. The proxy database can be configured to interface with the HL7 CR 108 via direct links, such as 114 116 118 120 122 136 or 138, to communicate with nodes, such as the other content service providers and records database 126, over the communication network 128,.

The communication network described herein may be configured to facilitate a communication interconnection between various nodes, such as the clinical information providers 102,124, the records databases 126, social networking platform 130, and any other node within the communication network 128, The communication network 128, configured in accordance with HL7, can facilitate data exchange, integration, sharing, receiving or providing between nodes. Communication network 128 can be either a wireless communication network or wireline communications network. Wireless communications networks include, but are not limited to: a digital cellular system, such as the Global System for Mobile Telecommunications Network (GSM), Personal Communication System (PCS), or any other wireless communication network. Wire line communication networks can include, but are not limited to: Public Switched Telephone Networks (PSTN), proprietary long-distance and local communications networks, or any other type of wire line network. The communication network 128 may include one or more networks, including public networks like the Internet and private networks, that may use any protocol or networking technology, such as Ethernet or Token Ring. In one embodiment, the social network platform 130 can generate data from different aggregators or user profiles in a number of digital formats. Each digital format is associated with a unique structure. For the data coming from social networking platform 130, it may be necessary to map fields and elements in order to transform them into a unified format as required by records database 126. The social networking platform may contain information relating to one or several clinical data providers, such as those of type 104 and 124. The social networking platform, for example, may host the social profiles of clinical data providers, where they can store and update personal, professional, or similar details, or communicate with friends, family, relatives, or other networking contacts regarding healthcare information or information generated by patients or medical devices in a network. The social networking platform may be defined by an arbitrary number of computers that are connected to the network. This includes clinical data providers. The social network platform 130 can facilitate the posting and sharing of online profiles, data and clinical reviews. It may also allow for the uploading and sharing of data generated by devices, patients, IoT, sensors, IoT data and other data.

In one example, where the records database 126 has a common and single HL7 CBR, the communication system 128 can be configured to convert or translate the data in the common CBR to allow data to be exchanged, integrated, shared, received, or provided to or from various nodes that are connected to the communication network 128 by using machine learning, metadata, and master data validation as discussed further on in this document. The common HL7 format 108 can be used to validate the data according to a single standard such as HL7, when the information is first entered into the records database 126.

The records database described herein may be decentralized, centralized, or blockchain-configured to allow access to the records database through a distributed network configured with blockchain, as discussed later along with FIG. 9. In some embodiments, both the records database and various content-based routers 108 can be configured to use blockchain technology. The blockchain-configured records database 126, and its associated components (also referred to as “smart contracts based distributed integrity networks”), may not need a central health information exchange operator, because all participants can have access to distributed ledgers in order to maintain a safe exchange without breaking trust. It is possible to remove human intermediaries from the chain of participants, such as clinical data providers 102 and 124, and networks 130. The health records can also be distributed over multiple storage locations on the blockchain, which are accessible to all participants at the same time. This allows for updates in almost real-time. The blockchain-configured ecosystem offers a distributed, secure and disintermediated framework that can be used to integrate healthcare data across multiple stakeholders and uses defined by entities. The blockchain configured digital eco-system, also known as a distributed integrity network based on smart contracts, provides a distributed and secured framework for digital patient identities. This allows access to connected health devices such as body worn devices, devices connected to the internet at home or other locations, servers and storage devices hosting medical records, etc., using private and public key cryptography. It protects identity by restricting access to specific clinical providers in accordance to dynamic rules and policies, and utilizing strong identity validation mechanisms utilizing blockchain configured validation devices throughout the The distributed nature allows for near-real-time updates to be shared across the network without a need for central authority or exchange.

Click here to view the patent on Google Patents.