Voice activated medical transcription system

Abstract

A method, includes receiving an audio input and converting the audio input into a computer readable text, processing the computer readable text through a natural language process to generate a natural language phrase, to determine a medical category to which the natural language phrase belongs, to determine the medical category, assigning the natural language phrase with the determined medical category to a medical form section based at least in part on an association between the determined medical category and a form part definition and storing the medical form section in a database.

Description

VOICE ACTIVATED MEDICAL TRANSCRIPTION SYSTEMFIELD OF INVENTION

[0001] The present invention relates, generally, to speech to text conversion, and, more specifically, to a contextual natural language learning model system.BACKGROUND OF INVENTION

[0002] Computer assisted voice transcription services have been in use for some time. There remains a strong need for improvements of such services.SUMMARY OF INVENTION

[0003] The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. This summary is not an extensive overview of the invention. It is not intended to identify key / critical elements of the invention or to delineate the scope of the invention. Its sole purpose is to present some concepts of the invention in a simplified form as a prelude to the more detailed description that is presented later.

[0004] In accordance with an exemplary and non-limiting embodiment, a method, comprises receiving an audio input and converting the audio input into a computer readable text, processing the computer readable text through a natural language process to generate a natural language phrase, processing the natural language phrase through a context based artificial intelligence process to determine a medical category to which the natural language phrase belongs, wherein the context based artificial intelligence process has been trained to consider a job description of a person making the audio input and a medical database comprising information concerning at least one of a drug type's approved usage, patient diagnosis indication, and diagnosis treatment plan, each relating to a field of practice relating to the job description, to determine the medical category, assigning the natural language phrase with the determined medical category to a medical form section based at least in part on an association between the determined medical category and a form part definition and storing the medical form section in a database.

[0005] In accordance with an exemplary and non-limiting embodiment, an apparatus, comprises an audio input mechanism, a processor in communication with the audio inputmechanism; and a memory in communication with the processor, the memory storing instructions that when executed by the processor cause the processor to receive an audio input and convert the audio input into a computer readable text, process the computer readable text through a natural language process to generate a natural language phrase, process the natural language phrase through a context based artificial intelligence process to determine a medical category to which the natural language phrase belongs, wherein the context based artificial intelligence process has been trained to consider a job description of a person making the audio input and a medical database comprising information concerning at least one of a drug type's approved usage, patient diagnosis indication, and diagnosis treatment plan, each relating to a field of practice relating to the job description, to determine the medical category, assign the natural language phrase with the determined medical category to a medical form section based at least in part on an association between the determined medical category and a form part definition and store the medical form section in a database.SUMMARY OF FIGURES

[0006] An understanding of embodiments described herein and many of the attendant advantages thereof may be readily obtained by reference to the following detailed description when considered with the accompanying drawings, wherein:

[0007] Fig. 1 is an exemplary and non-limiting illustration of a computer process in accordance with the principles of the present disclosure.DETAIUED DESCRIPTION

[0008] In the following paragraphs, the present invention will be described in detail by way of example with reference to the attached drawings. Throughout this description, the preferred embodiment and examples shown should be considered as exemplars, rather than as limitations on the present invention. As used herein, the “present invention” refers to any one of the embodiments of the invention described herein, and any equivalents. Furthermore, reference to various feature(s) of the “present invention” throughout this document does not mean that all claimed embodiments or methods must include the referenced feature(s).

[0009] Aspects of the present disclosure relate to computer programs that provide voice to text and various natural language understanding process used in connection with transcription and documentation in spoken language. Aspects also relate to managing variousaccents and domain specific vocabulary. For example, in the field of medical transcription there are many medical domain and sub-domain and various spoken accents that must be very accurately converted into text and then analyzed with various natural language understanding models. Transcribing, via a voice to text module, generally creates text that may then be analyzed with a different NLU models for better documentation and analytics. The NLU model(s) may need to determine what the spoken words, as represented by the text, is intended to convey, and potentially need to be analyzed within a context. The inventors discovered problems and solutions to managing various accents, domain specific vocabulary and context specific NLU models to automate the transcription and documentation accurately.

[0010] As a non-limiting example, if we think of a hospital, doctor’ s office, field office, emergency field situation, etc. we understand that the doctors, nurses, social workers, and other professionals have many things going on and while making records of the transpiring events is very important it is not intuitive, efficient, or what the professionals are thinking about most. As a result, record keeping of the various events can be less than desirable. Not only does this result in potentially poor record keeping from a patient / doctor standpoint, but it can also be sub- optimal in providing accurate prescriptions, diagnosis, insurance submissions, identification of disease progression through a society, etc. The inventors discovered and developed computer- based system using speech to text, language modeling and autocharacterization to solve many of these problems.

[0011] Fig. 1 illustrates a computer process 116 in accordance with the principles of the present disclosure. The process begins with a model selection process 100. This model selection process is manual and / or automatic. A user speaks into a microphone and the audio is automatically converted into text using process 104 with proper model selection using process from 102. The converted text will be processed through a contextual natural language processing system 106 (e.g., natural language understanding), however, in embodiments, a natural language understanding system 108 needs to be selected 106. The selection may be based on a number of different variables or processes, which will be explained in more detail below. Once selected, which in this embodiment is NLU 108A, the text is processed by NL 108A. The CNLU is converted to some further action and / or stored in a database (e.g., relational database, blockchain, etc.) 110. The store data can further be used in 114 for analytics and in 112 for user level model upgradation in embodiment of 102 and 108.

[0012] The selection process 100 may be manual or automated. A manual operationmay be configured into a user interface. For example, a user may select that she is in the U.S. and an appropriate accent and gender model may be chosen based on the setting. For example, domain specific vocabulary may be chosen form user profile (work type, affiliation) etc. A selection may be based on geography, a person’s native language, a person’s gender, a person’s office affiliation or from any other metadata from 102. The selection may be automated by automatically receiving an indication of the location of the user (e.g., address, GPS, etc.), accent and / or gender identification from audio and domain identification from text.

[0013] The NLU 106 process may be an artificial intelligence process that uses the natural language interpretation from the NLPA 108. For example, one may want to categorize the natural language such that when a spoken word is converted it can be automatically identified as a certain type of information and / or to perform certain actions. For example, a user may want spoken text identified as a patient history, diagnosis, prescription information, standard codes, standard and user specific actions etc. A properly trained NLU system may have been trained using both the natural language and contextual information such as how the information has been categorized. Once the system is properly trained, a user of the computer process 116 may speak words and have them converted, categorized, and used to fill and / or edit a form / document automatically without the need for the user to make a predestined location for the language. In embodiments, the categorized information may be stored in a database 110 (relational, blockchain, public, private, etc.) where the information can be later accessed for a follow-up process 112 and / or 114. A follow-up process may be, for example, patient trend analysis, screening, group or societal tendencies and trends in 114 and for improving user experience using auto updating the model in 112

[0014] In accordance with some exemplary and non-limiting embodiments, the analyzed and updated personal data from database 110 may be used to update databases 102, 108 in either an individualized manner or in a manner wherein the updated data is aggregated across a plurality of users.

[0015] Another aspect of the present invention relates to a selection of a language model based on contextual information determined by natural language processing of a language sample. In embodiments, the computer process 100 may request that a user simply speak for a short period of time. The computer process may then run a natural language process on the spoken words, following conversion of the spoken words to text, for thedetection of indications of language type (e.g., English) and accent (e.g., regional prose). The language model may then indicate the predicted language and accent. The indication may be provided to the user for confirmation and / or the indication may be used to select the appropriate language model for the user (e.g., an English language model with a British accent). Further, the computer process 100 may request that the user speak about something relevant to her work. The user may, for example, describe their position, title, or speak something she might typically want to transcribe. The work relevant speech may be converted to text and then processed through the selected model for proper language and accent, and further processed through a natural language model for context such that a model reflective of the user’s domain can be understood. The user, for example, may describe an X-Ray how a lab technician typically would (e.g., “ x-ray shows that the patient has a broken femur”). The contextual based language model may then determine a subject of the language based on a comparison to known attributes of types of work, jobs, situations, etc. For example, the above phrase may be compared with an attributes database (e.g., including medical technician language samples as well as other types of work language) to determine that the language is representative of a medical technician who reads various medical test results. Once it is understood that the person is a medical technician and speaks English with a British accent, the computer system 100 may then select a model targeting the user’s use scenario.

[0016] Another aspect of the present invention relates to categorizing statements, phrases, sentences, etc. that are processed through a natural language model targeting a user’s use scenario. Similar to the comparison of attributes to determine the use scenario, each phrase, sentence and or statement can be categorized. A category may be a category in a particular form that needs to be filed out, identification of a symptom of a disease, stage of a condition, medical history, diagnosis, prescription, etc.

[0017] Another aspect of the present invention relates to using categorized statements for the automatic filling of forms, databases, data analysis programs, etc. For example, if a medical technician is reviewing an x-ray and orally describing his analysis to the computer system 106, the technician may need to fill out a particular form. The computer system 106 may either learn or be otherwise programmed to understand what each field in the form is to contain. Then the computer system 106 may load each of the categorized phrases into the appropriate field in the form without user input. This creates a very efficient process for the medical technician; she speaks and the form is automatically filled out.

[0018] As described, the system 106 may derive a destination and / or a format, such as that of a particular form, for the spoken input. For, example, the system may recognize the use of terms such as “x-ray” as indicating that the inputted text should be entered into a particular form. In other exemplary instances, the name of the form may be included in the audio input and may be utilized to trigger the filling out of an appropriate form.

[0019] With reference to Fig. 2, there is illustrated an alternative exemplary and nonlimiting embodiment. As illustrated, the model selection and speech to text functions are further described as occurring in block 118. Specifically, the audio input may be subjected to Diarization and pure voice analytics. As illustrated, the outputs of the speech to text function may be combined with the Diarization with the resulting output serving as an input for a speaker / language label transcript function.

[0020] The audio input may be comprised of a single user with the resulting audio signal being monolingual and / or multilingual as when a user dictates audio content. In other instances, such as a multiuser scenario, the audio input may be comprised of monolingual and / or multilingual audio resulting from, for example, an interview, a doctor-patient conversation, a customer- agent conversation, a podcast, a meeting conversation, and the like. A language specific model needs to be selected from DB 1.

[0021] The Diarization function serves to partition an audio stream containing human speech into homogeneous segments according to the identity of each speaker and / or spoken language.

[0022] Diarization may be performed based on speakers is known as Speaker Diarization while Diarization performed based on languages spoken in a given audio source is known as Language Diarization. In some embodiments, the Diarization model may need to be selected based on input data.An example Speaker diarization is as follows:Speaker label : Time stamp [HH:MM:SS] : Transcript• SPK1 : [00:00:00 - 00:00:3.33] : Hello, how are you doing today• SPK2: [00:00:3.56 - 00:00:6.61] : I am good how are you?• SPK1 : [00:00:7.51 - 00:00:11.50] : Ok, Good how can I help you today?An example of Language diarization is as follows:Language label : Time stamp [HH:MM:SS] : Transcript• Languagel : [00:00:00 - 00:00:1.33] : Hello• Language2: [00:00:3.56 - 00:00:6.61] :• Languagel : [00:00:7.51 - 00:00:8.50] : Ok, Good

[0023] Audio input that may be analyzed using voice only may be treated as pure voice analytics. Broadly, pure voice analytics covers voice biomarkers, voice disorders and audio emotion detection, audio accent detection, spoken language identification, speaker identification. Audio / voice may be analyzed to detect various biomarker, disease, emotion, speaker, accent, language etc. For example, during doctor patient conversation audio, one may extract patient voice only and detect an emotional state and / or neurodegenerative and psychological disease or any other disease which may impact voice. In some instances, autodetected conditions may be shared with doctor for better clinical care. These conditions may be stored in database 110 without the need for a text conversion.

[0024] As illustrated, NLU 106 is a streaming NLU. Based on output text received, NLU 106 processes the received text with context and performs documentation improvement i.e., nudging / suggesting the user to check certain things, asking for some information for more clarity, detecting errors, flagging contrastive statements, detecting unusual patterns, etc. In some embodiments, the frequency at which a user may receive suggestions may be configurable. The system may further solicit feedback to improve the overall methods. The system may detect and suggest various aspects of the received output text including, but not limited to, spelling, acronym disambiguation, grammar, clinical disorder, clinical code, clinical suggestion, negative sentences, constative sentence, type of sentence and keyword suggestion.Rules of Interpretation

[0025] Numerous embodiments are described in this disclosure, and are presented for illustrative purposes only. The described embodiments are not, and are not intended to be, limiting in any sense. The presently disclosed invention(s) are widely applicable to numerous embodiments, as is readily apparent from the disclosure. One of ordinary skill in the art will recognize that the disclosed invention(s) may be practiced with various modifications and alterations, such as structural, logical, software, and electrical modifications. Although particular features of the disclosed invention(s) may be described with reference to one or more particular embodiments and / or drawings, it should be understood that such features are not limited to usage in the one or more particular embodiments or drawings with reference to which they are described, unless expressly specified otherwise.

[0026] The present disclosure is neither a literal description of all embodiments nor a listing of features of the invention that must be present in all embodiments.

[0027] Neither the Title (set forth at the beginning of the first page of this disclosure) nor the Abstract (set forth at the end of this disclosure) is to be taken as limiting in any way as the scope of the disclosed invention(s).

[0028] The term “product” means any machine, manufacture and / or composition of matter as contemplated by 35 U.S.C. §101, unless expressly specified otherwise.

[0029] The terms “an embodiment”, “embodiment”, “embodiments”, “the embodiment”, “the embodiments”, “one or more embodiments”, “some embodiments”, “one embodiment” and the like mean “one or more (but not all) disclosed embodiments”, unless expressly specified otherwise.

[0030] The terms “the invention” and “the present invention” and the like mean “one or more embodiments of the present invention.”

[0031] A reference to “another embodiment” in describing an embodiment does not imply that the referenced embodiment is mutually exclusive with another embodiment (e.g., an embodiment described before the referenced embodiment), unless expressly specified otherwise.

[0032] The terms “including”, “comprising” and variations thereof mean “including but not limited to”, unless expressly specified otherwise.

[0033] The terms “a”, “an” and “the” mean “one or more”, unless expressly specified otherwise.

[0034] The term “plurality” means “two or more”, unless expressly specified otherwise.

[0035] The term “herein” means “in the present disclosure, including anything which may be incorporated by reference”, unless expressly specified otherwise.

[0036] The phrase “at least one of’, when such phrase modifies a plurality of things (such as an enumerated list of things) means any combination of one or more of those things, unless expressly specified otherwise. For example, the phrase at least one of a widget, a carand a wheel means either (i) a widget, (ii) a car, (iii) a wheel, (iv) a widget and a car, (v) a widget and a wheel, (vi) a car and a wheel, or (vii) a widget, a car and a wheel.

[0037] The phrase “based on” does not mean “based only on”, unless expressly specified otherwise. In other words, the phrase “based on” describes both “based only on” and “based at least on”.

[0038] Where a limitation of a first claim would cover one of a feature as well as more than one of a feature (e.g., a limitation such as “at least one widget” covers one widget as well as more than one widget), and where in a second claim that depends on the first claim, the second claim uses a definite article “the” to refer to the limitation (e.g., “the widget”), this does not imply that the first claim covers only one of the feature, and this does not imply that the second claim covers only one of the feature (e.g., “the widget” can cover both one widget and more than one widget).

[0039] Each process (whether called a method, algorithm or otherwise) inherently includes one or more steps, and therefore all references to a “step” or “steps” of a process have an inherent antecedent basis in the mere recitation of the term ‘process’ or a like term. Accordingly, any reference in a claim to a ‘ step’ or ‘ steps’ of a process has sufficient antecedent basis.

[0040] When an ordinal number (such as “first”, “second”, “third” and so on) is used as an adjective before a term, that ordinal number is used (unless expressly specified otherwise) merely to indicate a particular feature, such as to distinguish that particular feature from another feature that is described by the same term or by a similar term. For example, a “first widget” may be so named merely to distinguish it from, e.g., a “second widget”. Thus, the mere usage of the ordinal numbers “first” and “second” before the term “widget” does not indicate any other relationship between the two widgets, and likewise does not indicate any other characteristics of either or both widgets. For example, the mere usage of the ordinal numbers “first” and “second” before the term “widget” (1) does not indicate that either widget comes before or after any other in order or location; (2) does not indicate that either widget occurs or acts before or after any other in time; and (3) does not indicate that either widget ranks above or below any other, as in importance or quality. In addition, the mere usage of ordinal numbers does not define a numerical limit to the features identified with the ordinal numbers. Forexample, the mere usage of the ordinal numbers “first” and “second” before the term “widget” does not indicate that there must be no more than two widgets.

[0041] When a single device or article is described herein, more than one device or article (whether or not they cooperate) may alternatively be used in place of the single device or article that is described. Accordingly, the functionality that is described as being possessed by a device may alternatively be possessed by more than one device or article (whether or not they cooperate).

[0042] Similarly, where more than one device or article is described herein (whether or not they cooperate), a single device or article may alternatively be used in place of the more than one device or article that is described. For example, a plurality of computer-based devices may be substituted with a single computer-based device. Accordingly, the various functionality that is described as being possessed by more than one device or article may alternatively be possessed by a single device or article.

[0043] The functionality and / or the features of a single device that is described may be alternatively embodied by one or more other devices that are described but are not explicitly described as having such functionality and / or features. Thus, other embodiments need not include the described device itself, but rather can include the one or more other devices which would, in those other embodiments, have such functionality / features.

[0044] Devices that are in communication with each other need not be in continuous communication with each other, unless expressly specified otherwise. On the contrary, such devices need only transmit to each other as necessary or desirable, and may actually refrain from exchanging data most of the time. For example, a machine in communication with another machine via the Internet may not transmit data to the other machine for weeks at a time. In addition, devices that are in communication with each other may communicate directly or indirectly through one or more intermediaries.

[0045] A description of an embodiment with several components or features does not imply that all or even any of such components and / or features are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the present invention(s). Unless otherwise specified explicitly, no component and / or feature is essential or required.

[0046] Further, although process steps, algorithms or the like may be described in a sequential order, such processes may be configured to work in different orders. In other words, any sequence or order of steps that may be explicitly described does not necessarily indicate a requirement that the steps be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously despite being described or implied as occurring non-simultaneously (e.g., because one step is described after the other step). Moreover, the illustration of a process by its depiction in a drawing does not imply that the illustrated process is exclusive of other variations and modifications thereto, does not imply that the illustrated process or any of its steps are necessary to the invention, and does not imply that the illustrated process is preferred.

[0047] Although a process may be described as including a plurality of steps, that does not indicate that all or even any of the steps are essential or required. Various other embodiments within the scope of the described invention(s) include other processes that omit some or all of the described steps. Unless otherwise specified explicitly, no step is essential or required.

[0048] Although a product may be described as including a plurality of components, aspects, qualities, characteristics and / or features, that does not indicate that all of the plurality are essential or required. Various other embodiments within the scope of the described invention(s) include other products that omit some or all of the described plurality.

[0049] An enumerated list of items (which may or may not be numbered) does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. Likewise, an enumerated list of items (which may or may not be numbered) does not imply that any or all of the items are comprehensive of any category, unless expressly specified otherwise. For example, the enumerated list “a computer, a laptop, a PDA” does not imply that any or all of the three items of that list are mutually exclusive and does not imply that any or all of the three items of that list are comprehensive of any category.

[0050] Headings of sections provided in this disclosure are for convenience only, and are not to be taken as limiting the disclosure in any way.

[0051] “Determining” something can be performed in a variety of manners and therefore the term “determining” (and like terms) includes calculating, computing, deriving, looking up (e.g., in a table, database or data structure), ascertaining, recognizing, and the like.

[0052] A “display” as that term is used herein is an area that conveys information to a viewer. The information may be dynamic, in which case, an LCD, LED, CRT, Digital Light Processing (DLP), rear projection, front projection, or the like may be used to form the display. The aspect ratio of the display may be 4:3, 16:9, or the like. Furthermore, the resolution of the display may be any appropriate resolution such as 480i, 480p, 720p, 1080i, 1080p or the like. The format of information sent to the display may be any appropriate format such as Standard Definition TeleVision (SDTV), Enhanced Definition TV (EDTV), High Definition TV (HDTV), or the like. The information may likewise be static, in which case, painted glass may be used to form the display. Note that static information may be presented on a display capable of displaying dynamic information if desired. Some displays may be interactive and may include touch screen features or associated keypads as is well understood.

[0053] A control system, as that term is used herein, may be a computer processor coupled with an operating system, device drivers, and appropriate programs (collectively “software”) with instructions to provide the functionality described for the control system. The software is stored in an associated memory device (sometimes referred to as a computer readable medium). While it is contemplated that an appropriately programmed general purpose computer or computing device may be used, it is also contemplated that hard-wired circuitry or custom hardware (e.g., an application specific integrated circuit (ASIC)) may be used in place of, or in combination with, software instructions for implementation of the processes of various embodiments. Thus, embodiments are not limited to any specific combination of hardware and software.

[0054] A “processor” means any one or more microprocessors, Central Processing Unit (CPU) devices, computing devices, microcontrollers, digital signal processors, or like devices. Exemplary processors are the INTEL PENTIUM or AMD ATHLON processors.

[0055] The term “computer-readable medium” refers to any medium that participates in providing data (e.g., instructions) that may be read by a computer, a processor or a like device. Such a medium may take many forms, including but not limited to, non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical or magnetic disks and other persistent memory. Volatile media include DRAM, which typically constitutes the main memory. Transmission media include coaxial cables, copper wire and fiber optics, including the wires that comprise a system bus coupled to the processor. Transmission media may include or convey acoustic waves, light waves and electromagnetic emissions, suchas those generated during RF and IR data communications. Common forms of computer- readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, Digital Video Disc (DVD), any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, a RAM, a PROM, an EPROM, a FLASH-EEPROM, a USB memory stick, a dongle, any other memory chip or cartridge, a carrier wave as described hereinafter, or any other medium from which a computer can read. The terms “computer-readable memory” and / or “tangible media” specifically exclude signals, waves, and wave forms or other intangible media that may nevertheless be readable by a computer.

[0056] Various forms of computer readable media may be involved in carrying sequences of instructions to a processor. For example, sequences of instruction (i) may be delivered from RAM to a processor, (ii) may be carried over a wireless transmission medium, and / or (iii) may be formatted according to numerous formats, standards or protocols. For a more exhaustive list of protocols, the term “network” is defined below and includes many exemplary protocols that are also applicable here.

[0057] It will be readily apparent that the various methods and algorithms described herein may be implemented by a control system and / or the instructions of the software may be designed to carry out the processes of the present invention.

[0058] Where databases are described, it will be understood by one of ordinary skill in the art that (i) alternative database structures to those described may be readily employed, and (ii) other memory structures besides databases may be readily employed. Any illustrations or descriptions of any sample databases presented herein are illustrative arrangements for stored representations of information. Any number of other arrangements may be employed besides those suggested by, e.g., tables illustrated in drawings or elsewhere. Similarly, any illustrated entries of the databases represent exemplary information only; one of ordinary skill in the art will understand that the number and content of the entries can be different from those described herein. Further, despite any depiction of the databases as tables, other formats (including relational databases, object-based models, hierarchical electronic file structures, and / or distributed databases) could be used to store and manipulate the data types described herein. Eikewise, object methods or behaviors of a database can be used to implement various processes, such as those described herein. In addition, the databases may, in a known manner, be stored locally or remotely from a device that accesses data in such a database. Furthermore,while unified databases may be contemplated, it is also possible that the databases may be distributed and / or duplicated amongst a variety of devices.

[0059] As used herein a “network” is an environment wherein one or more computing devices may communicate with one another. Such devices may communicate directly or indirectly, via a wired or wireless medium such as the Internet, LAN, WAN or Ethernet (or IEEE 802.3), Token Ring, or via any appropriate communications means or combination of communications means. Exemplary protocols include but are not limited to: Bluetooth™, Time Division Multiple Access (TDMA), Code Division Multiple Access (CDMA), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), General Packet Radio Service (GPRS), Wideband CDMA (WCDMA), Advanced Mobile Phone System (AMPS), Digital AMPS (D-AMPS), IEEE 802.11 (WI-FI), IEEE 802.3, SAP, SAS™ by IGT, OASIS™ by Aristocrat Technologies, SDS by Bally Gaming and Systems, ATP, TCP / IP, GDS published by the Gaming Standards Association of Fremont Calif., the best of breed (BOB), system to system (S2S), or the like. Note that if video signals or large files are being sent over the network, a broadband network may be used to alleviate delays associated with the transfer of such large files, however, such is not strictly required. Each of the devices is adapted to communicate on such a communication means. Any number and type of machines may be in communication via the network. Where the network is the Internet, communications over the Internet may be through a website maintained by a computer on a remote server or over an online data network including commercial online service providers, bulletin board systems, and the like. In yet other embodiments, the devices may communicate with one another over RF, cable TV, satellite links, and the like. Where appropriate encryption or other security measures such as logins and passwords may be provided to protect proprietary or confidential information.

[0060] Communication among computers and devices may be encrypted to insure privacy and prevent fraud in any of a variety of ways well known in the art. Appropriate cryptographic protocols for bolstering system security are described in Schneier, APPLIED CRYPTOGRAPHY, PROTOCOLS, ALGORITHMS, AND SOURCE CODE IN C, John Wiley & Sons, Inc. 2d ed., 1996, which is incorporated by reference in its entirety.

[0061] The term “whereby” is used herein only to precede a clause or other set of words that express only the intended result, objective or consequence of something that is previously and explicitly recited. Thus, when the term “whereby” is used in a claim, the clause or otherwords that the term “whereby” modifies do not establish specific further limitations of the claim or otherwise restricts the meaning or scope of the claim.

[0062] It will be readily apparent that the various methods and algorithms described herein may be implemented by, e.g., appropriately programmed general purpose computers and computing devices. Typically a processor (e.g., one or more microprocessors) will receive instructions from a memory or like device, and execute those instructions, thereby performing one or more processes defined by those instructions. Further, programs that implement such methods and algorithms may be stored and transmitted using a variety of media (e.g., computer readable media) in a number of manners. In some embodiments, hard-wired circuitry or custom hardware may be used in place of, or in combination with, software instructions for implementation of the processes of various embodiments. Thus, embodiments are not limited to any specific combination of hardware and software.

[0063] These and other advantages may be realized in accordance with the specific embodiments described as well as other variations. It is to be understood that the above description is intended to be illustrative, and not restrictive. Many other embodiments and modifications within the spirit and scope of the claims will be apparent to those of skill in the art upon reviewing the above description. The scope of the invention should, therefore, be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

Claims

CLAIMS1. A method, comprising: receiving an audio input and converting the audio input into a computer readable text; processing the computer readable text through a natural language process to generate a natural language phrase; processing the natural language phrase through a context based artificial intelligence process to determine a medical category to which the natural language phrase belongs, wherein the context based artificial intelligence process has been trained to consider a job description of a person making the audio input and a medical database comprising information concerning at least one of a drug type's approved usage, patient diagnosis indication, and diagnosis treatment plan, each relating to a field of practice relating to the job description, to determine the medical category; assigning the natural language phrase with the determined medical category to a medical form section based at least in part on an association between the determined medical category and a form part definition; and storing the medical form section in a database.

2. The method of claim 1 wherein the context -based artificial intelligence process is trained, at least in part, by processing a plurality of data sets causing it to consider a relationship between the job description and to the information concerning at least one of a drug type's approved usage, patient diagnosis indication, and diagnosis treatment plan.

3. The method of claim 1, wherein the audio input is a verbal utterance.

4. The method of claim 1, wherein processing the computer readable text through the natural language process comprises selecting a first model from a first database.

5. The method of claim 4, wherein the first model is selected from the group consisting of an accent model, a gender model and a vocabulary model.

6. The method of claim 4, further comprising analyzing the medical form section to update the first database.

7. The method of claim 1, wherein processing the natural language phrase comprises selecting a second model from a second database.

8. The method of claim 7, further comprising analyzing the medical form section to update the first database.

9. The method of claim 7, wherein the second model is selected from the group consisting of a coding model and a text classifier model.

10. The method of claim 1, wherein converting the audio input comprises applying at least one of Diarization and pure voice analytics to the audio input.

11. The method of claim 10, wherein the Diarization is selected from the group consisting of speaker Diarization and language Diarization.

12. The method of claim 10 wherein the application of pure voice analytics results in a determination of an attribute of the audio input selected from the group consisting of a voice biomarker, a voice disorder, audio emotion detection, audio accent detection, spoken language identification, and speaker identification.

13. An apparatus, comprising: an audio input mechanism: a processor in communication with the audio input mechanism; and a memory in communication with the processor, the memory storing instructions that when executed by the processor cause the processor to: receive an audio input and convert the audio input into a computer readable text; process the computer readable text through a natural language process to generate a natural language phrase; process the natural language phrase through a context based artificial intelligence process to determine a medical category to which the natural language phrase belongs, wherein the context based artificial intelligence process has been trained to consider a job description of a person making the audio input and a medical database comprising information concerning at least one of a drug type's approved usage, patient diagnosis indication, and diagnosistreatment plan, each relating to a field of practice relating to the job description, to determine the medical category; assign the natural language phrase with the determined medical category to a medical form section based at least in part on an association between the determined medical category and a form part definition; and store the medical form section in a database.

14. The apparatus of claim 13 wherein the context -based artificial intelligence process is trained, at least in part, by processing a plurality of data sets causing it to consider a relationship between the job description and to the information concerning at least one of a drug type's approved usage, patient diagnosis indication, and diagnosis treatment plan.

115. The apparatus of claim 13, wherein the audio input is a verbal utterance.

16. The apparatus of claim 13, wherein processing the computer readable text through the natural language process comprises selecting a first model from a first database.

17. The apparatus of claim 16, wherein the first model is selected from the group consisting of an accent model, a gender model and a vocabulary model.

18. The apparatus of claim 16, further comprising analyzing the medical form section to update the first database.

19. The apparatus of claim 13, wherein processing the natural language phrase comprises selecting a second model from a second database.

20. The apparatus of claim 19, further comprising analyzing the medical form section to update the first database.

21. The apparatus of claim 19, wherein the second model is selected from the group consisting of a coding model and a text classifier model.

22. The method of claim 13, wherein converting the audio input comprises applying at least one of Diarization and pure voice analytics to the audio input.

23. The method of claim 22, wherein the Diarization is selected from the group consisting of speaker Diarization and language Diarization.

24. The method of claim 22 wherein the application of pure voice analytics results in a determination of an attribute of the audio input selected from the group consisting of a voice biomarker, a voice disorder, audio emotion detection, audio accent detection, spoken language identification, and speaker identification.

Images