Abstract: A process of extending retention periods of records. In operation, an electronic computing device identifies a retention period associated with the record. The device obtains information related to a future event. The information includes a time period during which the future event is predicted or scheduled to occur and a location at which the future event is predicted or scheduled to occur. When the device determines that the record is contextually related to the future event based at least in part on the time period or the location of the future event, the retention period associated with the record is extended. The device may also automatically extend retention periods of records based on a number of other retention-related factors associated with the record including recording content, record trustworthiness, recording time, recording location, recording data type, recording source, recording officers' profile and their association, crime statistics, incident severity, and the like.

Abstract: A process of evaluating the expertise of participants during a group call. In operation, an electronic computing device analyzes speech content of participants on a group call to determine a call context associated with the group call. The electronic computing device then assigns an expected expertise score for the participant by correlating the call context with a participant profile and further determines a demonstrated expertise score for the participant as a function of the expected expertise score and a call participation score indicating a duration of time that the participant has spoken during the group call. When the electronic computing device detects that a decision is being made with respect to the call context, the electronic computing device provides a visual or audio output on a corresponding visual or audio output device indicating the demonstrated expertise score of at least one of the participants.

Abstract: Methods and systems for identifying watchers of an object of interest at an incident scene. One method includes receiving, with an electronic processor, an object identifier corresponding to the object of interest. The method includes determining a watcher status for the object of interest. The method includes generating a notification based on the watcher status and the object identifier. The method includes transmitting, with a communication interface communicatively coupled to the electronic processor, the notification to an available watcher at the incident scene.

Abstract: A process of extending retention periods of records. In operation, an electronic computing device identifies a retention period associated with the record. The device obtains information related to a future event. The information includes a time period during which the future event is predicted or scheduled to occur and a location at which the future event is predicted or scheduled to occur. When the device determines that the record is contextually related to the future event based at least in part on the time period or the location of the future event, the retention period associated with the record is extended. The device may also automatically extend retention periods of records based on a number of other retention-related factors associated with the record including recording content, record trustworthiness, recording time, recording location, recording data type, recording source, recording officers’ profile and their association, crime statistics, incident severity, and the like.

Abstract: Techniques for eliminating bias in selectively edited videos are provided. A request to release a video capturing a public safety incident is received. The video is edited to create an edited video. At least one civilian score and at least one public safety official score based on the sentiment of the video is computed. At least one edited civilian score and at least one edited public safety official score based on the sentiment of the video is computed. A first score is computed based on a combination of the civilian score and public safety official score. A second score is computed based on a combination of the edited civilian score and edited public safety official score. The first and second score are compared to determine if a difference between the scores exceed a threshold. The edited video is released when the scores do not exceed the threshold.

Abstract: A process of evaluating the expertise of participants during a group call. In operation, an electronic computing device analyzes speech content of participants on a group call to determine a call context associated with the group call. The electronic computing device then assigns an expected expertise score for the participant by correlating the call context with a participant profile and further determines a demonstrated expertise score for the participant as a function of the expected expertise score and a call participation score indicating a duration of time that the participant has spoken during the group call. When the electronic computing device detects that a decision is being made with respect to the call context, the electronic computing device provides a visual or audio output on a corresponding visual or audio output device indicating the demonstrated expertise score of at least one of the participants.

Abstract: Techniques for redaction of data that is incidentally recorded are provided. A request for information is received from a user. The requested information includes confidential information. The request is received via a first device. The requested information is sent to the first device for output to the user by the first device. A second device within proximity to the first device is determined. The second device causes the output from the first device to be recorded based on the proximity of the second device to the first device. The recording from the second device is marked as redactable. A portion of the recording from the second device that includes the confidential information is redacted when the recording from the second device is output.

Abstract: A process of redacting records based on a contextual correlation with a previously redacted record. In operation, an electronic computing device obtains redaction metadata associated with a previously redacted record and uses the redaction metadata to identify a segment within an unredacted record that was redacted to generate the previously redacted record. The device then processes the segment to detect characteristics of a person or the object captured in the unredacted record and further redacted in the redacted record. The device also determines a context in which the redacted person or object was captured within the segment of the unredacted record. The device then redacts a person or object captured in other unredacted records when such person or object is contextually related to the redacted person or object captured in the unredacted record corresponding to the previously redacted record.

Abstract: Methods and systems for identifying watchers of an object of interest at an incident scene. One method includes receiving, with an electronic processor, an object identifier corresponding to the object of interest. The method includes determining a watcher status for the object of interest. The method includes generating a notification based on the watcher status and the object identifier. The method includes transmitting, with a communication interface communicatively coupled to the electronic processor, the notification to an available watcher at the incident scene.

Abstract: Methods and systems for identifying watchers of an object of interest at an incident scene. One method includes receiving, with an electronic processor, an object identifier corresponding to the object of interest. The method includes determining a watcher status for the object of interest. The method includes generating a notification based on the watcher status and the object identifier. The method includes transmitting, with a communication interface communicatively coupled to the electronic processor, the notification to an available watcher at the incident scene.

Abstract: An analysis engine of an anomaly detection system receives an input captured by a monitoring device, determines, based on a currently used anomaly detection model, that the input represents an object or event that should not be classified as an anomaly, and determines, based on a previously used model, that the input was previously classified as an anomaly. In response, the analysis engine determines a respective classification result for the input based on additional models used between the currently and previously used models, determines, based on the respective classification results, that it is likely that the anomaly detection system has been deliberately re-trained to falsely classify the input, and initiates an action to correctly classify the input as representing an object or event that should be classified as an anomaly. The anomaly detection models and classification results may be stored in a training repository for the anomaly detection system.

Abstract: Methods and systems for identifying watchers of an object of interest at an incident scene. One method includes receiving, with an electronic processor, an object identifier corresponding to the object of interest. The method includes determining a watcher status for the object of interest. The method includes generating a notification based on the watcher status and the object identifier. The method includes transmitting, with a communication interface communicatively coupled to the electronic processor, the notification to an available watcher at the incident scene.