An award-winning approach for police call centres

Read how IV and HPE helped one UK police force improve their call handing and service delivery


Contact Centre Demand Mapping and Demand Handling

Police contact centres more than ever need support to deliver effective services. In the case of the UK’s 999 emergency service, “around 35% of calls do not involve actual requests” for police help, emergency or otherwise. Intelligent Voice’s award-winning speech to text technology can be applied to solve many intractable challenges in these important, high call volume services.

IV’s demand mapping technology addresses this challenge by being able to identify and categorize different types of demand placed on police service contact centres through emergency (999/911) and/or urgent (101) lines. This provides insight into the complexity of the demand placed on the police by members of the public that is not available via other means.

IV’s Demand Mapping tool aids advisers to handle call demands more effectively, while logging caller intents accurately based on audio analysis, thereby enhancing performance and service to the public. The opportunity to reduce non-actionable demand can save a significant amount of resources and costs for re-investment in other policing work.

LexiQal logo trademark

Conversational analytics

Following on Demand Mapping, which utilises IV’s Automatic Speech Recognition (ASR) services described above, Intelligent Voice’s latest LexiQal product provides unique Conversational Analytics that identifies behavioural characteristics of speakers in recorded speech, tuned to the output from ASR. The analysis provides insights into the speaker’s credibility, emotional state or behavioural changes that are significant in context. LexiQal can also measure caller sentiment (positive, netural, negative) at utterance level with a high degree of accuracy, unique to IV.

LexiQal logo trademark

Conversational analytics works by detecting patterns in speech via a series of markers, and the time-based proximity of these indicators being triggered. LexiQal has a decision engine, that makes recommendations to the administrators regarding calls/recordings of interest. LexiQal can be used to assess the caller, the call handler or both sides of the call.

LexiQal’s scoring method of the markers (Emotional Recognition) uses linguistic analysis only to determine the likely behaviour of interest, whether of the caller or the call handler, or both. The technology automatically identifies these conversational features, weighs their significance, and makes recommendations. The insights are valuable across both sides of the call, agent and caller alike, with recommendations used to ‘inform’ human-made decisions to act or not.

Scenarios or call-types where this technology can be applied include:

  • Hoax Calls detection: is the caller lacking credibility in describing the emergency scenario, into which they are trying to lure a response?
  • Withheld Information: is the caller being transparent, or evasive?
  • Vulnerability: is the caller exhibiting behavioral features that align to mental health or other welfare concerns?
  • Agent Welfare: is a control room operator exhibiting signs of stress or fatigue that merit supervisor intervention?
  • Emotional State, whether Caller or Handler. E.g. is a caller merely angry (perhaps understandably so) or being wilfully aggressive or abusive?
Smart transcript

Smart Audio Transcription

From a criminal justice perspective, transcripts from audio are still required in high volume. This may include transcripts of calls e.g. from 999 police emergency calls. Digitally recorded interviews are also a significant source as there is the potential to run ASR to improve both productivity and intelligence. In addition, audio from other sources may also be used e.g. covert, human intelligence and Body Worn Video (BWV).

Intelligent Voice’s ASR offers an evolution to standard speech-to-text solutions. IV’s SmartTranscript solution can identify topics discussed in a conversation and find alerts for specified keywords. Reviewers can click topics and alerts to navigate to a specific part of the audio.

Organisations can identify calls of interest, based on topics and keywords they define, and prioritise those calls for further review through clickable links within the transcript that navigate to the related parts of audio. See Lancashire Police Case Study below to understand how IV’s award-winning solution significantly improved the force’s call handing and service delivery to the public.

Award Winning Solution

Read how IV and HPE helped one UK police force improve their call handing and service delivery. The work that IV and HPE did at the Constabulary can be viewed in the full article on Policing Insight.

The Constabulary embarked on a collaborative project with Intelligent Voice (IV) and Hewlett Packard Enterprise (HPE) to develop a real time understanding of all unlogged demand through the development of a voice to text transcription solution. Additionally, Intelligent Voice, partnering with HPE Pointnext Services, won the “2020 Security Innovation Award” for speech recognition and analysis to categorize calls, recognized for the innovative capabilities and services developed.

Use the form below to contact us and find out how you can be a part of this award-winning solution and further improve your force’s call handing service.

Contact Us