US-12626016-B1 - Real time translation system and method involving burdened and unburdened content

Abstract

Embodiments of a system and method as disclosed herein translate content such as discharge instructions received in English, scan, parse, remove and store burdened content such as protected health information (PHI) from the discharge instructions, apply a translation memory to the unburdened content, optionally employ artificial intelligence (AI) translation of text not addressed by the translation memory, optionally employ post editing (PE) or other post-processing, import the translated text back into the translation memory for improved future processing, and reassemble and transmit the final translation product including burdened and unburdened content together, with translation of the unburdened content. In various embodiments, burdened content is stored in a first jurisdiction and unburdened content is translated and/or otherwise processed in a second jurisdiction different from the first jurisdiction.

Inventors

• Giovanni Donatelli

Assignees

• The Language Group, LLC

Dates

Publication Date

20260512

Application Date

20251117

Claims (20)

1. 1 . A system, comprising: a control server geographically bound within a first jurisdiction, wherein the control server comprises a processor and a memory storing instructions which, when executed by the processor, cause the processor to: receive encrypted documentation; decrypt at least a first portion of the received encrypted documentation, wherein the decrypted portion of the received encrypted documentation comprises unburdened content in a first language; store a second portion of the encrypted documentation; transmit the unburdened content to a geographically unbound system, wherein the geographically unbound system comprises an automated translation system operable to automatically compare the unburdened content to a set of stored translations from the first language to a second language to produce an initial unburdened content translation; receive a second language translation of the unburdened content in the first language from the geographically unbound system; decrypt the second portion of the encrypted documentation, wherein the second portion comprises burdened content; combine the burdened content and the second language translation of the unburdened content into a combined translation; encrypt the combined translation; and transmit the encrypted combined translation to an output system.
2. 2 . The system of claim 1 , wherein the instructions further cause the processor to measure the volume and timing of transmissions sent to and received from the geographically unbound system, and upon the volume or timing of transmissions exceeding a congestion threshold, staggering the transmission of the combined translations over time.
3. 3 . The system of claim 1 , wherein the instructions further cause the processor to transmit the unburdened content in the first language to a supplemental external system upon the second language translation producing an accuracy metric that falls below a predetermined accuracy threshold.
4. 4 . The system of claim 3 , wherein the instructions further cause the processor to receive a supplemental second language translation of the unburdened content in the first language from the supplemental external system that produces a supplemental accuracy metric that meets or exceeds the predetermined accuracy threshold.
5. 5 . The system of claim 1 , wherein the instructions further cause the processor to transmit the second language translation of the unburdened content to a training component for the geographically unbound computing system.
6. 6 . The system of claim 5 , wherein the instructions cause the processor to transmit the second language translation of the unburdened content to the training component upon the second language translations producing an accuracy metric that exceeds a predetermined accuracy threshold.
7. 7 . A system, comprising: a control server geographically bound within a first jurisdiction, wherein the control server comprises a processor and a memory storing instructions which, when executed by the processor, cause the processor to: parse received documentation in a first language for burdened content, wherein the received documentation comprises respective healthcare-related documentation for each of a plurality of identifiable individuals from a plurality of output systems; remove the burdened content in the first language from the respective healthcare-related documentation for each identifiable individual of a plurality of identifiable individuals and, for each identifiable individual of the plurality of identifiable individuals, store the burdened content; transmit unburdened content in the first language for the respective healthcare-related documentation for each identifiable individual to a geographically unbound system, wherein the geographically unbound system comprises an automated translation system operable to automatically compare the unburdened content to a set of stored translations from the first language to a second language to produce an initial unburdened content translation; receive, for each identifiable individual of the plurality of identifiable individuals, a second language translation of the unburdened content in the first language from the geographically unbound system; for each identifiable individual of the plurality of identifiable individuals, combine the burdened content and the second language translation of the unburdened content for each of the respective healthcare-related discharge instructions into combined translations; and transmit, in parallel, each respective one of the combined translations to a respective associated output system of the plurality of output systems.
8. 8 . The system of claim 7 , wherein the second language is different for the unburdened content as between at least two of the identifiable individuals.
9. 9 . The system of claim 7 , wherein the instructions further cause the processor to transmit the second language translations to a training component for the control server.
10. 10 . The system of claim 9 , wherein the instructions cause the processor to transmit the second language translations to the training component upon the second language translations producing an accuracy metric that exceeds a predetermined accuracy threshold.
11. 11 . The system of claim 7 , wherein the instructions further cause the processor to transmit the unburdened content in the first language to a supplemental external system upon the second language translation producing an accuracy metric that falls below a predetermined accuracy threshold.
12. 12 . The system of claim 11 , wherein the instructions further cause the processor to receive a supplemental second language translation of the unburdened content in the first language from the supplemental external system that produces a supplemental accuracy metric that meets or exceeds the predetermined accuracy threshold.
13. 13 . The system of claim 7 , wherein the instructions further cause the processor to measure the volume and timing of transmissions sent to and received from the geographically unbound system, and upon the volume or timing of transmissions exceeding a congestion threshold, staggering the transmission of the combined translations over time.
14. 14 . A computer-implemented method, comprising: parsing received documentation in a first language for burdened content, wherein the received documentation is received from a plurality of output systems and comprises respective healthcare-related documentation for each identifiable individual of a plurality of identifiable individuals; removing the burdened content in the first language from the respective healthcare-related documentation for each identifiable individual of the plurality of identifiable individuals, and storing the burdened content in a geographically bound computing system; transmitting unburdened content in the first language from the respective healthcare-related documentation for each identifiable individual of the plurality of identifiable individuals to a geographically unbound system, wherein the geographically unbound system comprises an automated translation system operable to automatically compare the unburdened content to a set of stored translations from the first language to a second language to produce a second language translation of the unburdened content; receiving, by the geographically bound computing system from the geographically unbound system, the second language translation of the unburdened content for the respective healthcare-related documentation for each identifiable individual of the plurality of identifiable individuals; combining the burdened content and the second language translation of the unburdened content into combined translations for each identifiable individual; and transmitting, in parallel, each respective one of the combined translations to a respective associated output system of the plurality of output systems.
15. 15 . The computer-implemented method of claim 14 , wherein the second language is different for the unburdened content as between at least two of the identifiable individuals.
16. 16 . The computer-implemented method of claim 14 , further comprising transmitting the second language translation of the unburdened content to a training component for the geographically unbound computing system.
17. 17 . The computer-implemented method of claim 16 , wherein the second language translations are transmitted to the training component upon the second language translations producing an accuracy metric that exceeds a predetermined accuracy threshold.
18. 18 . The computer-implemented method of claim 14 , further comprising transmitting the unburdened content in the first language to a supplemental external system upon the second language translation producing an accuracy metric that falls below a predetermined accuracy threshold.
19. 19 . The computer-implemented method of claim 18 , further comprising receiving a supplemental second language translation of the unburdened content in the first language from the supplemental external system that produces a supplemental accuracy metric that meets or exceeds the predetermined accuracy threshold.
20. 20 . The computer-implemented method of claim 14 , further comprising measuring the volume and timing of transmissions sent to and received from the geographically unbound system, and upon the volume or timing of transmissions exceeding a congestion threshold, staggering the transmission of the combined translations over time.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS The present application is a continuation of U.S. patent application Ser. No. 19/286,965, filed on Jul. 31, 2025, which is a continuation-in-part application of U.S. patent application Ser. No. 19/068,128 filed on Mar. 3, 2025, the disclosures of which are incorporated by reference herein in their entireties. TECHNICAL FIELD The present disclosure relates to translation systems, and more particularly to a real-time translation system and method facilitating transmission of various content types. BACKGROUND AND SUMMARY Presently, patients are generally discharged from hospital care with English only care instructions and summaries. This causes a problem for hospitals because non-English speaking patients cannot read these instructions and therefore will likely have difficulties understanding actions to take, with a commensurate increased risk of readmission compared to the English-speaking population. Complicating this problem, health care and personally identifiable information (“protected health information” or “PHI”) is highly regulated and/or protected in many jurisdictions. In some cases, transmission of PHI is prohibited or at least highly restricted outside of a jurisdiction. In other cases, storage of PHI is prohibited or at least highly restricted. A related challenge is obtaining accurate and quick translations. In some cases, external and/or extraterritorial computing systems can most rapidly and accurately translate content. However, overall speed is affected by the available network connections between electronic systems and any required encryption/decryption of the content. Also, limiting packet size and frequency of transmission of content to be translated is desirable to facilitate speedy processing. Further, it is not always desirable or permissible to provide external and/or extraterritorial computing systems with the ability to decrypt encrypted communications. As such, a technical solution is needed to facilitate accuracy and speed of unburdened content translation while maintaining security of protected content. Embodiments as disclosed herein translate content such as discharge instructions received in a first language such as English, scan, parse, remove and store burdened content such as PHI from the discharge instructions, apply a translation memory to the unburdened content, optionally employ artificial intelligence (AI) translation of text not addressed by the translation memory, optionally employ post editing (PE) or other post-processing, import the translated text back into the translation memory for improved future processing, and reassemble and transmit the final translation product including burdened and unburdened content together, with necessary translation into a second language. In various embodiments, burdened content is stored in a first jurisdiction and unburdened content is translated and/or otherwise processed in a second jurisdiction. In various embodiments, the received content is encrypted to prevent the content from being unnecessarily exposed. In such cases, embodiments described herein can decrypt all or a portion of the encrypted content, optionally retain burdened content in encrypted form and segment out unburdened content to be unencrypted for translation. In various embodiments, translated unburdened content is re-encrypted along with matching burdened content to facilitate protection of the burdened content throughout the translation process. In various embodiments, multiple messages containing the final translation product are transmitting to different users of different computers in parallel. In various embodiments, the multiple messages may differ in language translation or other aspect based on the recipient. In various embodiments, an artificial intelligence component improves functioning of embodiments of the system and method as disclosed herein in one or more stages. In various additional embodiments, memory usage for alternative translation options is tracked for memory/storage optimization. According to additional embodiments, network traffic volume during translation processing is tracked and the timing of messages, memory updates and component training is dynamically adjusted to improve network functioning. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a schematic diagram of one or more systems illustrating processing of burdened and unburdened content according to embodiments of the present disclosure. FIGS. 2 and 3 are flow diagrams illustrating exemplary process flows according to embodiments of the present disclosure. FIG. 4 is a schematic diagram of a system illustrating processing of burdened and unburdened content according to embodiments of the present disclosure. DETAILED DESCRIPTION OF EMBODIMENTS The presently disclosed subject matter now will be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the presently disclosed subject