US2017162202A1PendingUtilityA1

Automated voice-to-reporting/management systems and method for voice call-ins of events/crimes

Assignee: TEN EIGHT TECH INCPriority: Feb 28, 2012Filed: Feb 24, 2017Published: Jun 8, 2017
Est. expiryFeb 28, 2032(~5.6 yrs left)· nominal 20-yr term from priority
H04M 2242/04G10L 2015/088G10L 15/22G10L 15/265H04M 3/5116G10L 2015/228G10L 15/08G10L 15/26
28
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

A system for institutions (particularly public safety) to accept spoken information such that users can report incident details as required to convey an official incident (e.g., crime) report and to aid in the investigation of the incident. Similarly, users can employ a combination of voice or text input, media submission, [GUI menu screens] and information download to aid in the immediate analysis of incident information to facilitate a rapid response for the incident. This method of interaction with institutions enables reporting parties to more quickly and efficiently convey incident information when direct interaction by an official is not possible or is subject to delay. This helps institutions, for example, police to provide better services while using less staff and resources.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
         1 . An automated, computerized incident reporting apparatus, comprising:
 a call-in system, adapted to receive a call-in containing at least one of received voice and text from a user reporting an incident;   a web-services connection system, adapted to access at least one of a Computer Aided Dispatch (CAD) system, Records Management System (RMS), and emergency public-safety access point system, to provide at least one of complementary information and verification information concerning at least one of the user and the incident; and   an automated voice processing service, adapted to receive at least one of the complementary information and verification information, perform an automatic analysis of at least one of the received voice and text, respond to the user with context and key word sensitive questions, associate an ID to the incident, forward the received voice to a transcription service, receive a transcription from the transcription service, create from the transcription and text (if received from the user) and from the complementary information and verification information a report detailing facts of the incident, provide an authorized person the report to review and edit the report, and create a finalized report of the incident,   wherein the context and key word sensitive questions utilize a questioning structure with fixed and dynamic properties.   
     
     
         2 . The apparatus of  claim 1 , wherein at least one of the call-in system and automated voice processing service is further adapted to determine a response capability of a device used by the user during the call-in and provide an incident reporting assistance application to be downloaded onto the device if it is capable of running the application, to proxy oral querying. 
     
     
         3 . The apparatus of  claim 1 , further comprising a transcription mode selector adapted to select a mode of transcription based on a criteria of at least one of transcription service costs, process duration, transcription quality, current service performance levels, transcription processing time, and a nature of information being transcribed. 
     
     
         4 . The apparatus of  claim 3 , wherein the transcription service is further adapted to repeat original responses by a secondary person whose voice is directly linked to automated speech recognition services with higher accuracy. 
     
     
         5 . The apparatus of  claim 1 , wherein the context determined by the automated voice processing service is used to establish a designated sequence of questioning and to dynamically determine at least one of institution-specific settings, source of initial connection to the reporting system, mode of communication, quality of transmission, quality of recent transcriptions, institutional operational conditions, user and incident location, previous responses input by the user, and system status. 
     
     
         6 . The apparatus of  claim 5 , wherein the questioning sequence is adapted to include fields representative of fields contained in a report of a target institution, wherein each question has a designation of whether it is required or optional relative to a nature of the incident. 
     
     
         7 . The apparatus of  claim 6 , wherein responses to the questioning sequence are compared to a glossary of significant key words or phrases and, when detected, trigger at least one of a search of historical premise information at a location of the incident, a comparison to other incidents within a geographic region to the incident, a chronological alignment with other incidents, and a comparison of suspect information received from other incident reports. 
     
     
         8 . The apparatus of  claim 1 , wherein the complementary information and verification information is obtained from an external crime database system and is used to identify and document potential correlations with other incident data, thereby enhancing decision support during investigation activities. 
     
     
         9 . The apparatus of  claim 1 , wherein the automated voice processing service is further adapted to transmit an incident report in part or in whole to at least one of an external public safety system, a select recipient via email, a concerned party via an outbound computerized telephone call or text-message or instant messaging service. 
     
     
         10 . The apparatus of  claim 9 , wherein the the automated voice processing service is further adapted to enable a reporting party to provide follow-up information and follow-up action for the incident after completion of the call-in or prohibit further input of information into the incident report. 
     
     
         11 . The apparatus of  claim 5 , wherein the automated voice processing service is further configured with a computerized display for displaying a graphical representation of an institution's report template, the template comprising:
 text of responses provided by the user;   time of response input;   highlight of required elements for the incident;   context-sensitive pre-defined lists of responses associated with select elements in the template;   field-specific access to audio recordings of utterances from the user;   access to media uploaded by the user; and   ability for the user to override an initial response while retaining it for future reference.   
     
     
         12 . The apparatus of  claim 11 , wherein the automated voice processing service is further adapted to include computerized vocalizations which include audio annunciations organized by the institution's report template, the vocalizations comprising:
 field names and responses for minimum-required information;   actual audio response if the transcription for the user's response is missing or of low confidence;   optional playback of non-required report information submitted by the user;   field-specific access to audio recordings of utterances from the user; and   access to audio media uploaded by the user.   
     
     
         13 . The apparatus of  claim 1 , wherein the automatic analysis comprises:
 pre-designation of incident types with required and optional elements needed to fully complete the report;   dynamic generation of a listing of required but not yet received report information;   automatic field-level comparison of a selected report to other reports to merge data from duplicate incident reports; and   supplemental notification of a detection of user-uttered key words or phrases, with a suggested corresponding action.   
     
     
         14 . The apparatus of  claim 1 , wherein the automated voice processing service is adapted to further provide for the authorized person an access control for follow-up editing of the report, the access control comprising, a combination of unique record identifier, code, phone number, or user credential, wherein based on a selection by the authorized person, specific report details are made available to the user for review, input or revision in the follow-up, and a modified questioning is performed by the automated voice processing service. 
     
     
         15 . The apparatus as in any of the preceding claims, wherein the automated voice processing service is adapted to enable the user to perform an action of at least one of purchasing a ticket, buying insurance, reporting an incident, reporting an accident, or reporting a crime. 
     
     
         16 . A method for automatically generating an incident report, comprising:
 receiving a call-in containing at least one of received voice and text from a user reporting an incident at a call-in system;   accessing at least one of a Computer Aided Dispatch (CAD) system, Records Management System (RMS), and emergency public-safety access point system, to provide at least one of complementary information and verification information concerning at least one of the user and the incident via a web-services connection system; and   receiving at least one of the complementary information and verification information, perform an automatic analysis of at least one of the received voice and text, respond to the user with context and key word sensitive questions, associate an ID to the incident, forward the received voice to a transcription service, receive a transcription from the transcription service, create from the transcription and text (if received from the user) and from the complementary information and verification information a report detailing facts of the incident, provide an authorized person the report to review and edit the report, and create a finalized report of the incident, via automated voice processing service,   wherein the context and key word sensitive questions utilize a questioning structure with fixed and dynamic properties.   
     
     
         17 . The method of  claim 16 , wherein the context is used to establish questioning sequences and dynamically determined details including at least one of institution-specific settings, source of initial connection to the system, mode of communication, quality of transmission, quality of recent transcriptions, operational conditions of the institution, user and incident location, previous responses input by the user, and system status. 
     
     
         18 . The method of  claim 16 , wherein the questioning sequence includes fields contained in a typical report of a target institution, and each question includes designations of whether it is required or optional relative to a nature of the incident, a target level of transcription timeliness, and a desired level of transcription accuracy. 
     
     
         19 . The method of  claim 18 , wherein a response to the questioning sequence is compared to a glossary of significant key words or phrases and, when detected, trigger at least one of a search of historical premise information at a incident location, a comparison to other incidents within a geographic region, a chronological alignment with other incidents, and a comparison of suspect information received with other incident reports. 
     
     
         20 . The method of  claim 19 , wherein the automated voice processing service enables the user to perform an action of at least one of purchasing a ticket, buying insurance, reporting an incident, reporting an accident, or reporting a crime.

Join the waitlist — get patent alerts

Track US2017162202A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.