Drone response to loss detection event and repeat offender

Abstract

Examples described herein generally relate to a system and method for deploying an unmanned drone in response to a suspected loss event. The system is configured to detect a suspected loss condition at a premises. The system is configured to deploy a drone in response to the suspected loss condition. The drone is configured to identify a suspected person involved in the suspected loss condition at a first location within the premises. The drone is configured to follow the suspected person from the first location to a second location outside the premises. The drone can detect a first characteristic associated with a person that matches a record in a repeat offender database; monitor a second characteristic from the record in the repeat offender database; and activate a security measure for the premises prior to the person entering the premises based on a risk score for the record.

Description

DRONE RESPONSE TO LOSS DETECTION EVENT AND REPEAT OFFENDERCROSS REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims priority to U.S. Provisional Application No. 63 / 601,454 filed November 21, 2023, U.S. Provisional Application No. 63 / 601,593 filed November 21, 2023, U.S. Provisional Application No. 63 / 728,070 filed December 4, 2024, and U.S. Provisional Application No. 63 / 728,071 filed December 4, 2024, all of which are assigned to the assignee hereof and incorporated by reference herein in their entireties.TECHNICAL FIELD

[0002] The present disclosure relates to systems for communicating with customers in a retail environment, and more particularly to systems and methods for a drone to respond to a loss detection event and repeat offender.BACKGROUND

[0003] Retailers detect movement of goods using a security tag attached to the goods and sensors that detect the location of the security tag. For example, Electronic Article Surveillance (EAS) systems use various types of EAS tags to determine when products are being removed from a retail environment without authorization. Inventory control systems monitor product inventory available for sale and are often integrated with point-of-sale (POS) systems so that inventory can be monitored in real time. Customer relationship management (CRM) systems allow stores to track the identity and buying patterns of customers. Video cameras capture images showing in-store activity. A security system may include an exit system (e.g., a pedestal including a reader) that detects the presence of a tag. While such security systems are useful in detecting a surreptitious theft of an item, such technology may be limited to active events inside a premises.

[0004] While such security systems are useful in detecting a surreptitious theft of an item, such technology lacks effective communication with customers and suspected thieves. For example, an EAS system may trigger an audible alarm, but a generic alarm may not convey enough information. For instance, audible alarms are often ignored bycustomers that believe the alarm is intended for someone else. Often, personnel are deployed in response to an alarm. The ability of the personnel to correctly identify and respond to an event, however, may be limited due to lack of information as well as laws, policies, or potential violence.

[0005] A security system may include a repeat offender database that tracks information of known offenders. For example, a known offender database may store images or a facial recognition pattern of a person suspected of shoplifting. The security system may detect a match to the known offender database and provide a notification to security personnel.

[0006] One issue with implementations of a known offender database is that the known offender may not be identified until the known offender has entered a premises. Because the known offender is already in the premises, the options for handling the known offender may be restricted. For instance, audible alarms are often ignored by known offenders. T

[0007] In view of the foregoing, there is a need for technological improvements to technology in premises such as retail environments.SUMMARY

[0008] The following presents a simplified summary of one or more implementations of the present disclosure in order to provide a basic understanding of such implementations. This summary is not an extensive overview of all contemplated implementations, and is intended to neither identify key or critical elements of all implementations nor delineate the scope of any or all implementations. Its sole purpose is to present some concepts of one or more implementations of the present disclosure in a simplified form as a prelude to the more detailed description that is presented later.

[0009] In some aspects, the techniques described herein relate to a system including: one or more memories, individually or in combination, storing computer-executable instructions; and one or more processors, individually or in combination, configured to execute the instructions to: detect a suspected loss condition at a premises; and deploy a drone in response to the suspected loss condition, wherein the drone is configured to: identify a suspected person involved in the suspected loss condition at a first location within the premises; and follow the suspected person from the first location to a second location outside the premises.

[0010] In some aspects, the techniques described herein relate to a system, further including the drone, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi -pedal robot, or a track vehicle.

[0011] In some aspects, the techniques described herein relate to a system, wherein the drone is configured to capture a video of the suspected person.

[0012] In some aspects, the techniques described herein relate to a system, wherein the drone is configured to position itself with respect to the suspected person to frame, in the video, one or more of: a face of the suspected person; a vehicle of the suspected person; one or more people associated with the suspected person; or a gait of the suspected person.

[0013] In some aspects, the techniques described herein relate to a system, wherein the drone is configured to read one or more wireless signals associated with the suspected person, wherein the one or more wireless signals associated with the suspected person include one or more of: an identifier of a mobile device carried by the suspected person; or an identifier of an electronic tag associated with an item involved in the suspected loss condition.

[0014] In some aspects, the techniques described herein relate to a system, wherein to detect the suspected loss condition at the premises, the one or more processors, individually or in combination, are configured to detect unauthorized movement of a radio frequency identification tag associated with an item.

[0015] In some aspects, the techniques described herein relate to a system, wherein the drone is configured to project an image near the suspected person.

[0016] In some aspects, the techniques described herein relate to a system, wherein the drone is configured to output an audible message near the suspected person.

[0017] In some aspects, the techniques described herein relate to a system, wherein the one or more processors, individually or in combination, are configured to deploy a second drone to follow the suspected person outside of the premises.

[0018] In some aspects, the techniques described herein relate to a method including: detecting a suspected loss condition at a premises; and deploying a drone in response to the suspected loss condition, wherein the drone is configured to: identify a suspected person involved in the suspected loss condition at a first location within the premises; and follow the suspected person from the first location to a second location outside the premises.

[0019] In some aspects, the techniques described herein relate to a method, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi -pedal robot, or a track vehicle.

[0020] In some aspects, the techniques described herein relate to a method, wherein the drone is configured to capture a video of the suspected person.

[0021] In some aspects, the techniques described herein relate to a method, wherein the drone is configured to position itself with respect to the suspected person to frame, in the video, one or more of: a face of the suspected person; a vehicle of the suspected person; one or more people associated with the suspected person; or a gait of the suspected person.

[0022] In some aspects, the techniques described herein relate to a method, wherein the drone is configured to read one or more wireless signals associated with the suspected person, wherein the one or more wireless signals associated with the suspected person include one or more of: an identifier of a mobile device carried by the suspected person; or an identifier of an electronic tag associated with an item involved in the suspected loss condition.

[0023] In some aspects, the techniques described herein relate to a method, wherein detecting the suspected loss condition at the premises includes detecting unauthorized movement of a radio frequency identification tag associated with an item.

[0024] In some aspects, the techniques described herein relate to a method, wherein the drone is configured to project an image near the suspected person.

[0025] In some aspects, the techniques described herein relate to a method, wherein the drone is configured to output an audible message near the suspected person.

[0026] In some aspects, the techniques described herein relate to a method, further including deploying a second drone to follow the suspected person outside of the premises.

[0027] In some aspects, the techniques described herein relate to a system including: one or more memories, individually or in combination, storing computer-executable instructions; and one or more processors, individually or in combination, configured to execute the instructions to: detect, via a drone deployed external to a premises, a first characteristic associated with a person that matches a record in a repeat offender database; monitor, via the drone in response to detecting the first characteristic, a second characteristic from the record in the repeat offender database; and activate asecurity measure for the premises prior to the person entering the premises based on a risk score for the record in the repeat offender database.

[0028] In some aspects, the techniques described herein relate to a system, wherein the first characteristic and the second characteristic are selected from: a mobile device identifier; a size of the person; a facial recognition of the person; a gait profile of the person; associated people; or a vehicle identifier.

[0029] In some aspects, the techniques described herein relate to a system, wherein to monitor the second characteristic from the record in the repeat offender database, the one or more processors, individually or in combination, are configured to: determine a set of available characteristics in the record; select a characteristic that the drone is capable of monitoring as the second characteristic; and position the drone with respect to the person to monitor the second characteristic.

[0030] In some aspects, the techniques described herein relate to a system, wherein the risk score is based on a threat score for the record and a confidence score based on at least the first characteristic and the second characteristic.

[0031] In some aspects, the techniques described herein relate to a system, wherein to activate the security measure the one or more processors, individually or in combination, are configured to select the security measure based on the threat score.

[0032] In some aspects, the techniques described herein relate to a system, wherein to activate the security measure the one or more processors, individually or in combination, are configured to automatically lock one or more doors that prevent the person from entering the premises.

[0033] In some aspects, the techniques described herein relate to a system, wherein the one or more processors, individually or in combination, are configured to add a third characteristic detected by the drone to the repeat offender database in response to a confidence score satisfying a threshold.

[0034] In some aspects, the techniques described herein relate to a system, further including the drone, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi -pedal robot, or a track vehicle.

[0035] In some aspects, the techniques described herein relate to a system, wherein to activate the security measure the one or more processors, individually or in combination, are configured to deploy a second drone to follow the person inside of the premises.

[0036] In some aspects, the techniques described herein relate to a method including: detecting, by a drone deployed external to a premises, a first characteristic associated with a person that matches a record in a repeat offender database; monitoring, by the drone in response to detecting the first characteristic, a second characteristic from the record in the repeat offender database; and activating a security measure for the premises prior to the person entering the premises based on a risk score for the record in the repeat offender database.

[0037] In some aspects, the techniques described herein relate to a method, wherein the first characteristic and the second characteristic are selected from: a mobile device identifier; a size of the person; a facial recognition of the person; a gait profile of the person; associated people; or a vehicle identifier.

[0038] In some aspects, the techniques described herein relate to a method, wherein monitoring the second characteristic from the record in the repeat offender database includes: determining a set of available characteristics in the record; selecting a characteristic that the drone is capable of monitoring as the second characteristic; and positioning the drone with respect to the person to monitor the second characteristic.

[0039] In some aspects, the techniques described herein relate to a method, wherein the risk score is based on a threat score for the record and a confidence score based on at least the first characteristic and the second characteristic.

[0040] In some aspects, the techniques described herein relate to a method, wherein activating the security measure includes selecting the security measure based on the threat score.

[0041] In some aspects, the techniques described herein relate to a method, wherein activating the security measure includes automatically locking one or more doors that prevent the person from entering the premises.

[0042] In some aspects, the techniques described herein relate to a method, further including adding a third characteristic detected by the drone to the repeat offender database in response to a confidence score satisfying a threshold.

[0043] In some aspects, the techniques described herein relate to a method, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi -pedal robot, or a track vehicle.

[0044] In some aspects, the techniques described herein relate to a method, wherein activating the security measure includes deploying a second drone to follow the person inside of the premises.

[0045] Additional advantages and novel features relating to implementations of the present disclosure will be set forth in part in the description that follows, and in part will become more apparent to those skilled in the art upon examination of the following or upon learning by practice thereof.BRIEF DESCRIPTION OF THE FIGURES

[0046] In the drawings:

[0047] FIG. 1 is a schematic diagram of an example retail location including a drone control system for responding to loss events with an unmanned drone..

[0048] FIG. 2 is a schematic diagram of example drone control system and drone.

[0049] FIG. 3 is a diagram of example records in a repeat offender database, in accordance with an implementation of the present disclosure.

[0050] FIG. 4 is a flowchart of an example method of operating a drone in response to a suspected loss condition, in accordance with an implementation of the present disclosure.

[0051] FIG. 5 is a flowchart of an example method of operating a drone to activate security measures based on a repeat offender database, in accordance with an implementation of the present disclosure.

[0052] FIG. 6 is a schematic block diagram of an example computer device, in accordance with an implementation of the present disclosure.DETAILED DESCRIPTION

[0053] The present disclosure provides systems and methods for deploying an unmanned drone in response to a suspected loss event. In an aspect, when a suspected loss event is detected within a premises, the drone may follow a suspected person out of the premises into a surrounding area such as a communal area, mall, plaza, or parking lot. The drone may communicate with the suspected person and other nearby people. The drone may use sensors to capture additional information. In some implementations, the drone may detect and respond to a suspected repeat offender.

[0054] Electronic Article Surveillance (EAS) systems are commonly used in retail stores and other settings to prevent the unauthorized removal of goods from a protected area. Typically, a detection system is configured at an exit from the protected area, which comprises one or more transmitters and antennas (“pedestals”) capable of generating an electromagnetic field across the exit, known as the “interrogation zone.”Articles to be protected are tagged with a security tag (such as an RFID and / or an acousto-magnetic (AM) tag), also known as an EAS marker, that, when active, generates a response signal when passed through this interrogation zone. An antenna and receiver in the same or another “pedestal” detects this response signal and generates an alarm. EAS systems may also be deployed throughout a premises to detect movement of items prior to the items approaching an exit.

[0055] A premises may also use monitoring devices such as security cameras and microphones to detect potential loss events. In some cases, the cameras may be distributed throughout a retail location and provide additional context with respect to a potential loss event. For example, an EAS system may detect movement of tagged items and a camera may record a video of the person interacting with the items. The video may be reviewed by security personnel or a trained artificial intelligence (Al). For example, the Al may perform facial recognition or gait pattern analysis to determine whether the person is a known offender.

[0056] While security technology for a premises helps identify suspected loss events, current systems are limited in interaction with suspected people. Typically, the system generates an alarm in response to a suspected loss event. In the case of organized retail crime (ORC), an alarm may be insufficient to stop theft of an item. For example, a thief may simply ignore an alarm and proceed out of the retail location. A thief may evade security personnel or law enforcement officers. Further, having personnel confront a thief at the retail location may escalate the situation and possibly put customers at risk. Further, a generic audible alarm may be confusing to other customers, who may believe they triggered the alarm. Additionally, while monitoring systems are useful for gathering information about a suspected person, such information can be limited. For example, a thief may target products outside of view of a camera, or may position himself to avoid detection or identification. Fixed cameras and / or sensor devices may be located outside of a premises to provide additional information to a security system. Such fixed systems, however, may provide limited information with a relatively low confidence level. For instance, a fixed camera that reads license plates may identify vehicles in a known offender database, but may not be able to capture detailed information about people in the vehicle and may be limited to a detection at a single place and time. Such information may be an inadequate basis to invoke a security measure or may result in too many activations.

[0057] In an aspect, the present disclosure provides system and methods for deploying one or more drones in response to a suspected loss event. The term “drone” broadly refers to a mobile unmanned robot. The drone carries one or more sensors that can gather information about a suspected person. The drone may carry one or more output devices to communicate with the suspected person. The drone may be flying or ground based. For instance, example drones include unmanned aerial vehicles (UAVs) such as quadcopters, wheeled or legged robots, or track guided robots. Articles may be tagged with a security tag that is configured to transmit an article identifier. The security tag may be scanned at one or more locations to determine a status of the article . A point of sale (POS) system may provide further information regarding the status of the article. For example, an article may have a status of unpurchased, at checkout, or purchased. The drone may be deployed based on a status of an article. In an example use case, a tag may be scanned near an exit of a retail location. The status of the tag may be used to determine whether to deploy the drone. For example, if the tag has an unpurchased status and is detected by a sensor located between a checkout and the exit, a drone may be deployed to follow a suspected person.

[0058] In an aspect, the drone may follow the suspected person out of the premises, or a second drone may be deployed outside of the premises. The drone may communicate with the suspected person, for example, by outputting an audible message indicating why the drone is following the suspected person or outputting a command. The drone may also capture additional information about the suspected person. In particular, information such as an identification of a vehicle used by the suspected person or identification of other people with whom the suspected person interacts may be useful for prosecuting a theft and / or recovering stolen goods. In an aspect, the drone extends the physical presence of a security system outside of the boundaries of the premises, while also reducing risks associated with involvement of human personnel.

[0059] In an aspect, one or more unmanned drones may be deployed to an area external to a premises. For example, in the case of a retail location, the drones may be deployed in a parking lot, plaza, or indoor mall. The drone may detect a first characteristic associated with a person that matches a record in a repeat offender database. Such database hits may be fairly common as some innocent people are likely to have characteristics in common with known offenders. The drone may monitor a suspected person in response to detecting the first characteristic to detect a second characteristic from the record in the repeat offender database. For instance, if the droneidentifies a vehicle that is associated with a record in the repeat offender database, the drone may monitor a person that exits the vehicle for a known characteristic such as a facial profile, size, or gait profile. The drone or associated system may determine a risk score of the person based on characteristics matching the record. Based on the risk score, the system can activate a security measure for the premises prior to the person entering the premises.

[0060] In an aspect, the drone extends the physical presence of a security system outside of the boundaries of the premises, while also reducing risks associated with involvement of human personnel. For example, a drone may follow a person exiting a vehicle to detect additional characteristics that increase a confidence that the person is the repeat offender associated with a record in the database. Because the drone operates outside of the premises, a decision on a security measure may be made before the suspected person enters the premises. Accordingly, pre-emptive security measures such as locking doors or display cases may be taken to provide additional physical security.

[0061] Referring now to FIG. 1, an example premises 100 (e.g., a retail location) includes multiple regions where tagged products may be located. For example, the premises 100 may include an open display area 110, a front end 112, aisles 114, an entrance / exit area 116, and a security room 118. Customers 130 may be located within the different regions. Workers 132 may be stationed at locations such as check out registers and the security room 118. The workers 132 may operate a point of sale (POS) system 134. In some implementations, the POS system 134 may include self-service kiosks or a mobile application. A person of skill in the art would understand that the disclosed systems and methods are applicable to a variety of retail locations and the present disclosure is not limited to the example retail location or areas.

[0062] As discussed above, retailers (e.g., consumer products and apparel retailers) have deployed security tags such as radio frequency identification (RFID) systems in stores to track product movements as they arrive at stores, are placed on display on the sales floor, and are sold. By adopting RFID, retailers are able to reduce the amount of time that the store employees spend counting the inventory (e.g., manually counting inventor that is on the floor and in stock room), as well as increase merchandise visibility within each store, thereby enabling shoppers in the store and online to find what they seek. RFID uses radio waves to read and capture information stored on a tag attached to an object such as a good, product, or merchandise. Additionally, RFID tagsmay be used with a security system to detect inventory changes and possible loss events. For example, RFID tags may be read by an exit system to determine whether a tagged article 122 is leaving the retail location.

[0063] In an aspect, a tag (e.g., tag 124) may be configured to transmit an article identifier 128 to a sensor device. The article identifier 128 may be a unique code such as a serial number that identifies the tag 124. The article identifier 128 may be associated with an article, for example, when the article is tagged. In some implementations, the article 122 may be tagged with the tag 124 during manufacture or packaging in a process known as source labeling or source tagging. Accordingly, the article identifier 128 and / or tag 124 may be used to track the article throughout a distribution chain. For example, the active radio tag may be configured to transmit the article identifier prior to any unauthorized removal and until deactivated at a point of sale. In some implementations, the tag 124 may include an RFID tag 126 (e.g., an electronic article surveillance (EAS) tag). The RFID tag 154 may be read from up to several feet away by a reader and does not need to be within direct line-of-sight of the reader to be tracked.

[0064] An RFID system may be made up of two parts: a tag or label (e.g., EPC tag 126) and a reader (e.g., exit system 140). RFID tags (which may also be referred to as labels) are embedded with an RFID transmitter and a receiver. The RFID component on the tags may include a microchip that stores and processes information, and an antenna to receive and transmit signals. The EPC tag may further contain the specific serial number for each specific object (e.g., an electronic product code (EPC)). The EPC may also be embedded in the tag 124. For example, in one implementation, the tag 124 may include multiple memory banks such as a reserved memory, EPC memory, tag identification (TID) memory, and user memory. The reserved memory bank may include an access password and a kill password. The EPC memory may include the EPC, a protocol control, and a cyclic redundancy check value. The TID memory may include a tag identification. The user memory may store custom data.

[0065] The POS system 134 may be configured to deactivate a tag 124 upon purchase of the tagged article 122. In some implementations, the POS system 134 may deactivate the tag 124 itself, for example, using the kill password to prevent the tag 124 from transmitting. In some implementations, the POS system 134 may deactivate the tag 124 within the security system 102, for example, by setting a status of the tag 124 to deactivated.

[0066] To read the information encoded on the tag 124, a two-way radio transmitterreceiver called a sensing device, interrogator, or reader (e.g., exit system 140) emits a signal to the EPC tag using the antenna (e.g., internal antennas). The exit system 140 may apply filtering to indicate what memory bank the EPC tag 124 should use to respond to the emitted signal. The EPC tag 124 may respond with the information (e.g., EPC value or serial number) written in the memory bank. The EPC tag data set may include any information stored on the EPC tag 124 as well as information about reading the EPC tag 124. For example, the EPC tag data set may include: a timestamp, a location, a signal transmission power, a received signal strength indication (RSSI), and an identifier of the RFID reader (e.g., exit system 140). For purposes of this disclosure, the terms, the EPC tag and RFID tag may be used interchangeably. The EPC tag 124 may be a passive tag or a battery powered EPC tag. A passive RFID tag may use the radio wave energy of the RFID interrogator or receiver to relay the stored information back to the interrogator. In contrast, a battery powered EPC tag 124 may be embedded with a small battery that powers the relay of information.

[0067] In an aspect, a sensing device 148 may be located away from the exit system 140. For example, a sensing device 148 may be embedded in a floor or ceiling. In some implementations, a sensing device 148 may be located near the front end 112, for example in a queuing area to detect articles prior to purchase. In some implementations, a sensing device 148 may be located between the front end 112 and the exit system 140 to detect tags that were not deactivated by the POS system 134.

[0068] The security system 102 may detect suspected loss conditions. For example, the security system 102 may detect a suspected loss condition when a tag passes the exit system 140 without being deactivated by the POS system 134. As another example, the security system 102 may detect a suspected loss condition when a camera 120 detects a suspicious behavior such as a tagged item being concealed.

[0069] A conventional security system may be limited to a singular premises 100. For example, a retailer may lease the premises 100 and install security equipment therein. An exit system 140 may detect suspected loss events as a suspected person is leaving the premises 100. In some cases, detecting a suspected loss event near an exit may not be idea. In some cases, a security system may identify a suspected person as associated with a record in a repeat offender database prior to the suspected person approaching the exit system 140. Identification of a repeat offender may provide an earlier warning regarding potential loss events, but when the security system is limitedto the premises 100, the repeat offender is already in the premises 100 when identified. Accordingly, a response to an identified repeat offender may be limited. For example, the suspected person may exit the retail location before a worker 132 is able to respond.

[0070] In an aspect, the present disclosure provides a drone control system 160 that can extend a security system 102 beyond a premises 100. For example, the drone control system 160 may dispatch a drone 162 to follow a suspected person 164 to a location outside of the premises 100 such as a common area 170 or a parking lot 180. For instance, the common area 170 may be a shopping mall or plaza connecting other retail locations 172. The drone 162 may collect information about the suspected person 164 and / or communicate with the suspected person 164 in the location outside the premises 100. Additionally, the drone control system 160 may operate one or more drones 162 in areas external to the premises 100 for monitoring.

[0071] The drone 162 may include various unmanned mobile machines. For example, the drone may be an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi -pedal robot, or a track vehicle. The drone 162 may alternatively be referred to as a robot or an autonomous mobile machine. In some implementations, the drone 162 may be semi-autonomous and may allow input from on operator such as a worker 132.

[0072] For example, the drone 162 may include a camera capture a video of the suspected person. In contrast to a fixed camera system, the drone 162 may position itself with respect to the suspected person 164 to capture specific information. For instance, the drone 162 may position itself to capture a face of the suspected person 164, a vehicle 182 of the suspected person, one or more people associated with the suspected person, and / or a gait of the suspected person. The drone 162 may also include a wireless receiver that can listen for wireless signals associated with the suspected person 164. For instance, the drone 162 may receive an identifier of a mobile device carried by the suspected person or an identifier of an electronic tag associated with an item involved in the suspected loss condition.

[0073] The drone 162 may detect a first characteristic of a person 164 that matches a known offender database. The person 164 may be considered a suspected person on the basis of the matching characteristic. The drone 162 may collect information about the suspected person 164 and / or communicate with the suspected person 164 in the location outside the premises 100. In an aspect, the drone 162 may monitor a second characteristic of the suspected person 164 from the record in the repeat offenderdatabase. For example, the repeat offender database may have sparse information in a record. The drone control system 160 and / or the drone 162 may select a characteristic that is in the record for monitoring. The drone 162 may position itself to monitor the selected characteristic. For example, the drone 162 may move to a front of the suspected person 164 if the record includes a facial profile. As another example, the drone 162 may activate a wireless receiver and / or perform a wireless protocol if the record includes an identifier of a wireless device.

[0074] In an aspect, the drone 162 may gather information about the suspected person 164 in order to determine a risk score. In some implementations, the risk score may be based on a threat score and a confidence score. The threat score may be based on the record in the repeat offender database. For instance, the record may include a threat score based on past offenses committed by the person associated with the record. For instance, factors such as violence, weapons, or high value items may increase the threat score. The confidence score may be based on the characteristics of the suspected person that match the record. For instance, the confidence score may be based on a number of matching characteristics and / or a strength of each match. For instance, a size profile may match numerous people, but a facial profile is more likely to match a single person and may be associated with a stronger confidence score.

[0075] The drone control system 160 is configured to activate a security measure for the premises 100 prior to the suspected person entering the premises 100. The security measure may be selected based on the risk score for the suspected person. Example security measures may include: alerting a worker, increasing monitoring of the suspected person, alerting law enforcement, locking displays, locking a door, sounding an announcement and / or alarm.

[0076] Communications with the suspected person 164 may include audio and / or visual communications. For instance, the drone 162 may output an audible message (e .g . , via a speaker) . The audible message may provide information about the suspected loss event and / or the suspected person. For instance, the audible message may inform the suspected person that they are suspected of the loss event and are being recorded. The audible message may instruct the suspected person to return items to the premises 100 and / or leave the items at a current location. The visual communications may include lights to draw attention to and / or illuminate the suspected person. In some implementations, the visual communications may include an image or message projected from the drone 162 to an area near the suspected person 164. For example,the drone 162 may project an image of an item that triggered the suspected loss condition.

[0077] In some implementations, the drone control system 160 may deploy a first drone 162 inside the premises 100 and deploy a second drone 162 outside the premises 100. For example, the first drone 162 may be suitable for indoor operation. For instance, the first drone may be a wheeled or legged robot or may be guided by a track mounted in the premises 100. The second drone may be suitable for outdoor operation. For example, the second drone 162 may be a UAV or a larger wheeled or legged robot. The second drone 162 may have greater mobility or speed than the first drone 162.

[0078] The drone control system 160 may be a computer device programmed to control one or more drones 162. The drone control system 160 may be, for example, any mobile or fixed computer device including but not limited to a computer server, desktop or laptop or tablet computer, a cellular telephone, a personal digital assistant (PDA), a handheld device, any other computer device having wired and / or wireless connection capability with one or more other devices, or any other type of computerized device. In some implementations, the drone control system 160 may be located separately from the premises 100. For example, the drone control system 160 or a component thereof may be hosted on a server or datacenter of a cloud network and communicate with components of the security system 102 at the premises 100.

[0079] Turning to FIG. 2, an example drone control system 160 may be implemented as a computer device 240 configured to execute a drone control application 260. Whether the computer device 240 is located at the premises 100 or remotely, the computer device 240 may include a central processing unit (CPU) 242 that executes instructions stored in memory 244. For example, the CPU 242 may execute an operating system 252 and one or more applications 254, which may include the RFID reader configuration application 260. The computer device 240 may include a storage device 246 for storing data (e.g., POS system events and exit system measurements). The computer device 240 may also include a network interface 248 for communication with external devices via a network. For example, the computer device 240 may communicate with the POS system 134, the sensing devices 148, and / or the exit system 140.

[0080] The computer device 240 may optionally include a display 250. The display 250 may be, for example, a computer monitor and / or a touch-screen. The display 250may provide information to an operator and allow the operator to configure the computer device 240.

[0081] Memory 244 may be configured for storing data and / or computer-executable instructions defining and / or associated with an operating system 252 and / or application 254, and CPU 242 may execute operating system 252 and / or application 254. Memory 244 may represent one or more hardware memory devices accessible to computer device 240. An example of memory 244 can include, but is not limited to, a type of memory usable by a computer, such as random access memory (RAM), read only memory (ROM), tapes, magnetic discs, optical discs, volatile memory, non-volatile memory, and any combination thereof. Memory 244 may store local versions of applications being executed by CPU 242. In an implementation, the memory 244 may include a storage device, which may be a non-volatile memory.

[0082] The CPU 242 may include one or more processors for executing instructions. An example of CPU 242 can include, but is not limited to, any processor specially programmed as described herein, including a controller, microcontroller, application specific integrated circuit (ASIC), field programmable gate array (FPGA), system on chip (SoC), or other programmable logic or state machine. The CPU 242 may include other processing components such as an arithmetic logic unit (AUU), registers, and a control unit. The CPU 242 may include multiple cores and may be able to process different sets of instructions and / or data concurrently using the multiple cores to execute multiple threads.

[0083] The operating system 252 may include instructions (such as applications 254) stored in memory 244 and executable by the CPU 242. The applications 254 may include the item-tracking application 260 configured to track items that have been removed from the premises 100 without authorization. In some implementations, the drone control application 260 may be configured to identify a repeat offender using one or more drones 162.

[0084] The drone control application 260 include an event detection component 262 and a deployment component 264. The drone control application 260 may optionally include an identification component 270, a tracking component 272, a capture component 274, and / or a communication component 276. In some implementations, the drone control application 260 may optionally include an suspect detection component 263, a monitoring component 265 activation component 266 and a scoring component 268. The identification component 270, the tracking component 272, thecapture component 274, and / or the communication component 276 may optionally be implemented in whole or in part on the drone 162. In some implementations, one or more of the detection component 262, the monitoring component 264, the activation component 266, or the scoring component 268 may optionally be implemented in whole or in part on the drone 162.

[0085] The drone 162 includes hardware components for performing various functions controlled by the drone control application 260. For example, the drone 162 includes a camera 280, a microphone 282, a projector 284, a speaker 286, and a radio component 288.

[0086] The event detection component 262 is configured to detect a suspected loss condition at a premises. For example, the detection component 262 may receive input from the cameras 120, sensing devices 148, and / or exit system 140. The detection component 262 may apply the inputs to rules. For example, the detection component 262 may determine whether a location of a tag is outside of an allowed area. The detection component 262 may output a suspected loss event in response to detecting a suspected loss condition. For example, a suspected loss event may include known information about the event such as an item or tag identifier and a location. The suspected loss event may be associated with records such as a video recording or a known offender database record. The deployment component 264 is configured to deploy the drone 162 in response to the suspected loss condition. For example, the deployment component may select an available drone, which may be a drone that is ready for deployment (e.g., charged as a base) or a drone that is already in the retail location. For instance, the deployment component may select a drone that is closest to a location of the suspected loss condition. The deployment component 264 may provide the location of the suspect loss condition to the selected drone 162 with instructions to observe the location in search of a suspected person.

[0087] In some implementations, the suspect detection component 263 is configured to detect, using the drone 162, a first characteristic associated with a person that matches a record in a repeat offender database. For example, the suspect detection component 263 may control the drone 162 to follow an observation pattern to observe people in an area outside the premises 100. The drone 162 may collect various information to check against the repeat offender database. For example, the drone 162 may prioritize vehicle identification in a parking lot 180 or listen for wireless device identifiers. The drone 162 may send collected information to the drone control system160. The drone control system 160 may query the repeat offender database 150 with the collected information. If the repeat offender database 150 returns a record matching the collected information, the suspect detection component 263 provides the record to the monitoring component 265.

[0088] The monitoring component 265 is configured to monitor, using the drone 162, a second characteristic from the record in the repeat offender database. The monitoring component 265 receives the record from the suspect detection component 263 or the repeat offender database 150. The monitoring component 265 may select the second characteristic to monitor. For example, the monitoring component 265 may determine a set of available characteristics in the record (i.e., known characteristics of a repeat offender). The monitoring component 265 may select a characteristic that the drone is capable of monitoring as the second characteristic. The monitoring component 265 may send instructions to position the drone with respect to the person to monitor the second characteristic.

[0089] The scoring component 268 is configured to determine a risk score of a suspected person 164. For example, the risk score may be based on a threat score for the record and a confidence score based on at least the first characteristic and the second characteristic. The scoring component 268 may obtain the threat score from the record in the repeat offender database 150. The scoring component 268 may determine the confidence score based on detected characteristics of the suspected person 164. Generally, each detected characteristic that matches the record increases the confidence score. Weights may be assigned to individual characteristics, and a match may be associated with a match score based on strength of a match. In some implementations, a threat score may be associated with a threshold confidence score. For example, if a record indicates a known armed robber, a threshold confidence score (e.g., two matching characteristics) may be sufficient to determine a high risk score.

[0090] The activation component 266 is configured to activate a security measure for the premises prior to the person entering the premises based on a risk score for the record in the repeat offender database. For example, the activation component 266 may compare the risk score to a threshold for each potential security measure to determine whether to activate the security measure. In some implementations, the activation component 266 may select the security measure based on the threat score. For example, different threat levels may be associated with different security measures, as long as the confidence level satisfies a threshold. In an example, the activation component 266may automatically lock one or more doors that prevent the person from entering the premises. For instance, the activation component 266 may cause an actuator to change a door from an open or unlocked state to a closed and locked state. In another example, the activation component 266 may deploy a second drone to follow the person inside of the premises 100.

[0091] The identification component 270 is configured to cause the drone 162 to identify a suspected person involved in the suspected loss condition at a first location within the premises. For example, when the drone 162 arrives at the location of the suspected loss event, the drone 162 may identify the suspected person at the location. In some implementations, the drone 162 may receive an image of the suspected person from the cameras 120. The drone 162 may use image analysis to reidentify the suspected person from images captured by the drone 162. In implementations where an image of the suspected person is not available, the drone 162 may identify a closest person to the location of the suspected loss event. In some implementations, the drone 162 may include an RFID reader capable of detecting a tag associated with the suspected loss condition and identify a person associated with the tag.

[0092] The tracking component 272 is configured to cause the drone 162 to follow the suspected person from the first location to a second location outside the premises. The tracking component 272 provides navigation instructions to the drone 162. For example, the tracking component may determine movement of the suspected person and provide navigation instructions that keep the drone 162 at a specified distance from the suspected person. The drone 162 may use a combination of location sensors such as GPS and video to determine location.

[0093] The capture component 274 is configured to cause the drone 162 to capture information about the suspected person. For example, information may include a face of the suspected person; a vehicle of the suspected person; one or more people associated with the suspected person, or a gait of the suspected person. The capture component 274 may control the drone 162 to position the camera 280 to capture the information in a frame of the camera. In another implementation, the information may include wireless signals associated with the suspected person such an identifier of a mobile device carried by the suspected person or an identifier of an electronic tag associated with an item involved in the suspected loss condition. The capture component 274 may position the drone 162 within range of wireless signals associated with the suspected. In some implementations, the capture component 274 may initiatea wireless communication, for example, by querying RFID tags or providing a local Wi-Fi or cellular hotspot.

[0094] The communication component 276 is configured to communicate with the suspected person. For example, the communication component 276 may control the projector 284 and / or speaker 286 of the drone 162 to output a message. For instance, the communication component 276 may project an image near the suspected person or output an audible message near the suspected person.

[0095] FIG 3 is a diagram 300 of an example repeat offender database 150. The repeat offender database 150 may store known information about people who are suspected of committing offenses. For example, the repeat offender database 150 may be maintained by an operator of a single premises, an operator of a chain of premises, or a security company that monitors multiple premises. The records in the repeat offender database may include multiple fields, but the records may be sparsely populated because the information is gathered as it becomes available. For example, a video may record a person shoplifting from a retail location, and traits such as a size and gait may be detected, but the suspected person may conceal their face.

[0096] In the illustrated example, the repeat offender database 150 includes an identifier 310, a threat level 320, and traits such as a facial profile 330, gait profile 332, size profile 334, associates 336, vehicle 338, mobile device identifier 340, and name 342. The identifier 310 may be a unique identifier assigned to a record. In some cases, when multiple records are determined to refer to the same person (e.g., based on a number of matching traits), the records may be combined into a record with a single identifier 310. The threat level 320 may be a rating assigned based on the number and types of offenses committed. For example, a single suspected low-value shoplifting offense may be assigned a low value, whereas a violent offense including a weapon (i.e., armed robbery) may be assigned a high value. A record may include a value for a trait or indicate that the value is unknown (e.g., “-”). The value for each trait may be defined for each trait. For illustrative purposes, alphanumeric sequences are shown to represent unique values.

[0097] In an aspect, the drone control system 160 may operate the drone 162 to identify a repeat offender by matching characteristics of a suspected person 164 to a record in the repeat offender database 150. The illustrated example shows records 350, 352, 354 for three known offenders. The record 350 may represent an offender with a high risk level. The record 352 may represent an offender associated with the record350 (e.g., a getaway driver). The record 354 may represent a low-level offender with some similarities to the record 350.

[0098] In an example scenario, the drone 162 may capture video of people in the parking lot 180. The drone 162 may capture an image of the suspected person 164 and the detection component 262 may perform an image analysis to estimate the size of the suspected person. The estimated size may match both record 350 and record 354. In some implementations, the drone control system 160 may prioritize the record 350 due to the high risk level. The drone control system 160 may position the drone 162 to capture known characteristics of the record 350 such as the gait profde 332 or the vehicle 338. In some implementations, the drone control system 160 may attempt to capture known characteristics (e.g., a mobile identifier 340) of the record 352 for an associate of the record 350. The activation component 266 may evaluate whether to activate a security measure based on a closest match that satisfies a threshold. For example, if the size profile 334 and the gait profile 332 match the record 350, the activation component 266 may activate a security measure (e.g., locking doors) corresponding to the threat level 320. In some implementations, the drone 162 may captures a characteristic (e.g., facial profile 330) that confirms a match to a different record 354, in which case the record 350 may be excluded. For example, if the suspected person is confirmed to match the record 354 by a strong match on the facial profile 330, the activation component 266 may activate a security measure (e.g., additional monitoring) based on the relatively low threat level 320 of record 354.

[0099] Turning to FIG. 4, an example method 400 operates a drone to respond to a suspected loss event. For example, method 400 may be performed by the drone control system 160 and / or one or more drones 162. The drone control system 160 and / or drone control application 260 may be executed on the computer device 240. In some implementations, the drone 162 includes a processor and memory for executing one or more of the operations described herein. Optional blocks are shown with dashed lines.

[0100] At block 410, the method 400 includes detecting a suspected loss condition at a premises. For example, the drone control system 160 and / or the event detection component 262 may detect a suspected loss condition at a premises 100. For example, the event detection component 262 detect unauthorized movement of a radio frequency identification tag associated with an item. In some implementations, for example, the block 410 may optionally include detecting movement of the tag toward an exit.

[0101] At block 415, the method 400 includes deploying a drone in response to the suspected loss condition. For example, the drone control system 160 and / or deployment component 264 may deploy a drone 162 in response to the suspected loss condition. For example, the drone may be one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi -pedal robot, or a track vehicle.

[0102] At block 420, the method 400 includes identifying a suspected person involved in the suspected loss condition at a first location within the premises. For example, the drone control system 160, the drone 162, and / or the identification component 270 may identify a suspected person 164 involved in the suspected loss condition at a first location within the premises 100. In some implementations, the identification component 270 may add or update a record 350 in the repeat offender database 150 for the suspected person 164. For example, if the suspected person 164 matches an existing record 350 in the repeat offender database 150, the identification component 270 may add additional characteristics to the existing record 350. If the suspected person 164 does not match an existing record, the identification component 270 may create a new record.

[0103] At block 425, the method 400 includes following the suspected person from the first location to a second location outside the premises. For example, the drone control system 160, the drone 162 and / or the tracking component 272 may cause the drone 162 to follow the suspected person 164 from the first location to a second location outside the premises.

[0104] At block 430, the method 400 may optionally include deploying a second drone to follow the suspected person outside of the premises. For example, the drone control system 160 and / or the deployment component 264 may deploy a second drone to follow the suspected person outside of the premises.

[0105] At block 435, the method 400 may optionally include positioning the drone with respect to the suspected person to frame a video. For example, the drone control system 160, the drone 162 and / or the capture component 274 may position the drone with respect to the suspected person to frame a video.

[0106] At block 440, the method 400 may optionally include capturing a video of the suspected person. For example, the drone control system 160, the drone 162 and / or the capture component 274 may capture a video of the suspected person.

[0107] At block 445, the method 400 may optionally include reading one or more wireless signals associated with the suspected person. For example, the drone controlsystem 160, the drone 162 and / or the capture component 274 may read one or more wireless signals associated with the suspected person. For example, the wireless signals may include an identifier of a mobile device carried by the suspected person or an identifier of an electronic tag associated with an item involved in the suspected loss condition.

[0108] At block 450, the method 400 may optionally include projecting an image near the suspected person. For example, the drone control system 160, the drone 162 the communication component 276 and / or the projector 284 may project an image near the suspected person.

[0109] At block 455, the method 400 may optionally include outputting an audible message near the suspected person. For example, the drone control system 160, the drone 162 the communication component 276 and / or the speaker 286 may output an audible message near the suspected person.

[0110] Turning to FIG. 5, an example method 500 operates a drone to monitor a suspected person to initiate a security measure prior to the suspected person entering a premises. For example, method 500 may be performed by the drone control system 160 and / or one or more drones 162. The drone control system 160 and / or drone control application 260 may be executed on the computer device 240. In some implementations, the method 500 may be performed in conjunction with the method 400. For instance, the method 500 may be performed after the method 400 in which a suspected person is added to a repeat offender database. In some implementations, the drone 162 includes a processor and memory for executing one or more of the operations described herein. Optional blocks are shown with dashed lines.[oni] At block 510, the method 500 includes detecting, by a drone deployed external to a premises, a first characteristic associated with a person that matches a record in a repeat offender database. For example, the drone control system 160 and / or the suspect detection component 263 may detect via the drone 162 deployed external to the premises 100, a first characteristic associated with a person 164 that matches a record 350 in a repeat offender database 150.

[0112] At block 520, the method 500 includes monitoring, by the drone in response to detecting the first characteristic, a second characteristic from the record in the repeat offender database. For example, the drone control system 160 and / or monitoring component 265 may monitor, via the drone 162 in response to detecting the first characteristic, a second characteristic from the record 350 in the repeat offenderdatabase 150. In some implementations, at sub-block 522, the block 520 may optionally include determining a set of available characteristics in the record. In some implementations, at sub-block 524, the block 520 may optionally include selecting a characteristic that the drone is capable of monitoring as the second characteristic. In some implementations, at sub-block 526, the block 520 may optionally include positioning the drone with respect to the person to monitor the second characteristic.

[0113] At block 530, the method 500 includes activating a security measure for the premises prior to the person entering the premises based on a risk score for the record in the repeat offender database. For example, the drone control system 160, and / or the activation component 266 may activate a security measure for the premises 100 prior to the person 164 entering the premises based on a risk score for the record 350 in the repeat offender database 150. In some implementations, at sub-block 532, the block 530 may optionally include selecting the security measure based on the threat score. In some implementations, at sub-block 534, the block 530 may optionally include automatically locking one or more doors that prevent the person from entering the premises. In some implementations, at sub-block 536, the block 530 may optionally include deploying a second drone to follow the person inside of the premises.

[0114] At block 540, the method 500 may optionally include adding a third characteristic detected by the drone to the repeat offender database in response to a confidence score satisfying a threshold. For example, the drone control system 160, may add a third characteristic detected by the drone to the repeat offender database 150 in response to a confidence score satisfying a threshold. Referring now to FIG. 6, illustrated is an example computer device 600 in accordance with an implementation, including additional component details as compared to FIG. 2. In one example, computer device 600 may include processor 48 for carrying out processing functions associated with one or more of components and functions described herein. Processor 48 can include a single or multiple set of processors or multi-core processors. Moreover, processor 48 can be implemented as an integrated processing system and / or a distributed processing system. In an implementation, for example, processor 48 may include CPU 242.

[0115] In an example, computer device 600 may include memory 50 for storing instructions executable by the processor 48 for carrying out the functions described herein. In an implementation, for example, memory 50 may include memory 244. The memory 50 may include instructions for executing the drone control application 260.

[0116] Further, computer device 600 may include a communications component 52 that provides for establishing and maintaining communications with one or more parties utilizing hardware, software, and services as described herein. Communications component 52 may carry communications between components on computer device 600, as well as between computer device 600 and external devices, such as devices located across a communications network and / or devices serially or locally connected to computer device 600. For example, communications component 52 may include one or more buses, and may further include transmit chain components and receive chain components associated with a transmitter and receiver, respectively, operable for interfacing with external devices.

[0117] Additionally, computer device 600 may include a data store 54, which can be any suitable combination of hardware and / or software, that provides for mass storage of information, databases, and programs employed in connection with implementations described herein. For example, data store 54 may be a data repository for operating system 252 and / or applications 254. The data store may include memory 244 and / or storage device 246.

[0118] Computer device 600 may also include a user interface component 56 operable to receive inputs from a user of computer device 600 and further operable to generate outputs for presentation to the user. User interface component 56 may include one or more input devices, including but not limited to a keyboard, a number pad, a mouse, a touch-sensitive display, a digitizer, a navigation key, a function key, a microphone, a voice recognition component, any other mechanism capable of receiving an input from a user, or any combination thereof. Further, user interface component 56 may include one or more output devices, including but not limited to a display, a speaker, a haptic feedback mechanism, a printer, any other mechanism capable of presenting an output to a user, or any combination thereof.

[0119] In an implementation, user interface component 56 may transmit and / or receive messages corresponding to the operation of operating system 252 and / or applications 254. In addition, processor 48 may execute operating system 252 and / or applications 254, and memory 50 or data store 54 may store them.

[0120] As used in this application, the terms “component,” “system” and the like are intended to include a computer-related entity, such as but not limited to hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to being, a process running on aprocessor, a processor, an object, an executable, a thread of execution, a program, and / or a computer. By way of illustration, both an application running on a computer device and the computer device can be a component. One or more components can reside within a process and / or thread of execution and a component may be localized on one computer and / or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored thereon. The components may communicate by way of local and / or remote processes such as in accordance with a signal having one or more data packets, such as data from one component interacting with another component in a local system, distributed system, and / or across a network such as the Internet with other systems by way of the signal.

[0121] Moreover, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless specified otherwise, or clear from the context, the phrase “X employs A or B” is intended to mean any of the natural inclusive permutations. That is, the phrase “X employs A or B” is satisfied by any of the following instances: X employs A; X employs B; or X employs both A and B. In addition, the articles “a” and “an” as used in this application and the appended claims should generally be construed to mean “one or more” unless specified otherwise or clear from the context to be directed to a singular form.

[0122] Additional example implementations are described in the following numbered clauses:

[0123] Clause 1. A system comprising: one or more memories, individually or in combination, storing computer-executable instructions; and one or more processors, individually or in combination, configured to execute the instructions to: detect a suspected loss condition at a premises; and deploy a drone in response to the suspected loss condition, wherein the drone is configured to: identify a suspected person involved in the suspected loss condition at a first location within the premises; and follow the suspected person from the first location to a second location outside the premises.

[0124] Clause 2. The system of clause 1, further comprising the drone, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multipedal robot, or a track vehicle.

[0125] Clause 3. The system of clause 1 or 2, wherein the drone is configured to capture a video of the suspected person.

[0126] Clause 4. The system of clause 3, wherein the drone is configured to position itself with respect to the suspected person to frame, in the video, one or more of: a face of the suspected person; a vehicle of the suspected person; one or more people associated with the suspected person; or a gait of the suspected person.

[0127] Clause 5. The system of any of clauses 1-4, wherein the drone is configured to read one or more wireless signals associated with the suspected person, wherein the one or more wireless signals associated with the suspected person include one or more of: an identifier of a mobile device carried by the suspected person; or an identifier of an electronic tag associated with an item involved in the suspected loss condition.

[0128] Clause 6. The system of any of clauses 1-5, wherein to detect the suspected loss condition at the premises, the one or more processors, individually or in combination, are configured to detect unauthorized movement of a radio frequency identification tag associated with an item.

[0129] Clause 7. The system of any of clauses 1-6, wherein the drone is configured to project an image near the suspected person.

[0130] Clause 8. The system of any of clauses 1-7, wherein the drone is configured to output an audible message near the suspected person.

[0131] Clause 9. The system of any of clauses 1-8, wherein the one or more processors, individually or in combination, are configured to deploy a second drone to follow the suspected person outside of the premises.

[0132] Clause 10. The system of any of clauses 1-9, wherein the one or more processors, individually or in combination, are configured to: detect, via a drone deployed external to a premises, a first characteristic associated with a person that matches a record in a repeat offender database; monitor, via the drone in response to detecting the first characteristic, a second characteristic from the record in the repeat offender database; and activate a security measure for the premises prior to the person entering the premises based on a risk score for the record in the repeat offender database.

[0133] Clause 11. The system of clause 10, wherein the first characteristic and the second characteristic are selected from: a mobile device identifier; a size of the person; a facial recognition of the person; a gait profile of the person; associated people; or a vehicle identifier.

[0134] Clause 12. The system of clause 10, wherein to monitor the second characteristic from the record in the repeat offender database, the one or moreprocessors, individually or in combination, are configured to: determine a set of available characteristics in the record; select a characteristic that the drone is capable of monitoring as the second characteristic; and position the drone with respect to the person to monitor the second characteristic.

[0135] Clause 13. The system of clause 10, wherein the risk score is based on a threat score for the record and a confidence score based on at least the first characteristic and the second characteristic.

[0136] Clause 14. The system of clause 13, wherein to activate the security measure the one or more processors, individually or in combination, are configured to select the security measure based on the threat score.

[0137] Clause 15. The system of clause 10, wherein to activate the security measure the one or more processors, individually or in combination, are configured to automatically lock one or more doors that prevent the person from entering the premises.

[0138] Clause 16. The system of clause 10, wherein the one or more processors, individually or in combination, are configured to add a third characteristic detected by the drone to the repeat offender database in response to a confidence score satisfying a threshold.

[0139] Clause 17. The system of clause 10, further comprising the drone, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multipedal robot, or a track vehicle.

[0140] Clause 18. The system of clause 10, wherein to activate the security measure the one or more processors, individually or in combination, are configured to deploy a second drone to follow the person inside of the premises.

[0141] Clause 19. A method comprising: detecting a suspected loss condition at a premises; and deploying a drone in response to the suspected loss condition, wherein the drone is configured to: identify a suspected person involved in the suspected loss condition at a first location within the premises; and follow the suspected person from the first location to a second location outside the premises.

[0142] Clause 20. The method of clause 19, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi-pedal robot, or a track vehicle.

[0143] Clause 21. The method of clause 19 or 20, wherein the drone is configured to capture a video of the suspected person.

[0144] Clause 22. The method of clause 21, wherein the drone is configured to position itself with respect to the suspected person to frame, in the video, one or more of: a face of the suspected person; a vehicle of the suspected person; one or more people associated with the suspected person; or a gait of the suspected person.

[0145] Clause 23. The method of any of clauses 19-22, wherein the drone is configured to read one or more wireless signals associated with the suspected person, wherein the one or more wireless signals associated with the suspected person include one or more of: an identifier of a mobile device carried by the suspected person; or an identifier of an electronic tag associated with an item involved in the suspected loss condition.

[0146] Clause 24. The method of any of clauses 19-23, wherein detecting the suspected loss condition at the premises comprises detecting unauthorized movement of a radio frequency identification tag associated with an item.

[0147] Clause 25. The method of any of clauses 19-24, wherein the drone is configured to project an image near the suspected person.

[0148] Clause 26. The method of any of clauses 19-25, wherein the drone is configured to output an audible message near the suspected person.

[0149] Clause 27. The method of any of clauses 19-26, further comprising deploying a second drone to follow the suspected person outside of the premises.

[0150] Clause 28. The method of any of clauses 19-22, further comprising: detecting, by a drone deployed external to a premises, a first characteristic associated with a person that matches a record in a repeat offender database; monitoring, by the drone in response to detecting the first characteristic, a second characteristic from the record in the repeat offender database; and activating a security measure for the premises prior to the person entering the premises based on a risk score for the record in the repeat offender database.

[0151] Clause 29. The method of clause 28, wherein the first characteristic and the second characteristic are selected from: a mobile device identifier; a size of the person; a facial recognition of the person; a gait profile of the person; associated people; or a vehicle identifier.

[0152] Clause 30. The method of clause 28, wherein monitoring the second characteristic from the record in the repeat offender database comprises: determining a set of available characteristics in the record; selecting a characteristic that the drone iscapable of monitoring as the second characteristic; and positioning the drone with respect to the person to monitor the second characteristic.

[0153] Clause 31. The method of clause 28, wherein the risk score is based on a threat score for the record and a confidence score based on at least the first characteristic and the second characteristic.

[0154] Clause 32. The method of clause 31, wherein activating the security measure comprises selecting the security measure based on the threat score.

[0155] Clause 33. The method of clause 28, wherein activating the security measure comprises automatically locking one or more doors that prevent the person from entering the premises.

[0156] Clause 34. The method of clause 28, further comprising adding a third characteristic detected by the drone to the repeat offender database in response to a confidence score satisfying a threshold.

[0157] Clause 35. The method of clause 28, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi-pedal robot, or a track vehicle.

[0158] Clause 36. The method of clause 28, wherein activating the security measure comprises deploying a second drone to follow the person inside of the premises.

[0159] Various implementations or features may have been presented in terms of systems that may include a number of devices, components, modules, and the like. A person skilled in the art should understand and appreciate that the various systems may include additional devices, components, modules, etc. and / or may not include all of the devices, components, modules etc. discussed in connection with the figures. A combination of these approaches may also be used.

[0160] The various illustrative logics, logical blocks, and actions of methods described in connection with the embodiments disclosed herein may be implemented or performed with a specially-programmed one of a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but, in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computer devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors inconjunction with a DSP core, or any other such configuration. Additionally, at least one processor may comprise one or more components operable to perform one or more of the steps and / or actions described above.

[0161] Further, the steps and / or actions of a method or procedure described in connection with the implementations disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD- ROM, or any other form of storage medium known in the art. An exemplary storage medium may be coupled to the processor, such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. Further, in some implementations, the processor and the storage medium may reside in an ASIC. Additionally, the ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal. Additionally, in some implementations, the steps and / or actions of a method or procedure may reside as one or any combination or set of codes and / or instructions on a machine readable medium and / or computer readable medium, which may be incorporated into a computer program product.

[0162] In one or more implementations, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media includes computer storage media. Non-transitory computer-readable media excludes transitory signals. A storage medium may be any available media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Disk and disc, as used herein, includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc where disks usually reproduce data magnetically, while discs usually reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0163] While implementations of the present disclosure have been described in connection with examples thereof, it will be understood by those skilled in the art that variations and modifications of the implementations described above may be made without departing from the scope hereof. Other implementations will be apparent to those skilled in the art from a consideration of the specification or from a practice in accordance with examples disclosed herein.

Claims

CLAIMSWHAT IS CLAIMED IS:

1. A system comprising: one or more memories, individually or in combination, storing computerexecutable instructions; and one or more processors, individually or in combination, configured to execute the instructions to: detect a suspected loss condition at a premises; and deploy a drone in response to the suspected loss condition, wherein the drone is configured to: identify a suspected person involved in the suspected loss condition at a first location within the premises; and follow the suspected person from the first location to a second location outside the premises.

2. The system of claim 1, further comprising the drone, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi-pedal robot, or a track vehicle.

3. The system of claim 1 , wherein the drone is configured to capture a video of the suspected person.

4. The system of claim 3, wherein the drone is configured to position itself with respect to the suspected person to frame, in the video, one or more of: a face of the suspected person; a vehicle of the suspected person; one or more people associated with the suspected person; or a gait of the suspected person.

5. The system of claim 1, wherein the drone is configured to read one or more wireless signals associated with the suspected person, wherein the one or more wireless signals associated with the suspected person include one or more of: an identifier of a mobile device carried by the suspected person; oran identifier of an electronic tag associated with an item involved in the suspected loss condition.

6. The system of claim 1, wherein to detect the suspected loss condition at the premises, the one or more processors, individually or in combination, are configured to detect unauthorized movement of a radio frequency identification tag associated with an item.

7. The system of claim 1, wherein the drone is configured to project an image near the suspected person.

8. The system of claim 1, wherein the drone is configured to output an audible message near the suspected person.

9. The system of claim 1, wherein the one or more processors, individually or in combination, are configured to deploy a second drone to follow the suspected person outside of the premises.

10. The system of claim 1, wherein the one or more processors, individually or in combination, are configured to: detect, via the drone deployed external to the premises, a first characteristic associated with a person that matches a record in a repeat offender database; monitor, via the drone in response to detecting the first characteristic, a second characteristic from the record in the repeat offender database; and activate a security measure for the premises prior to the person entering the premises based on a risk score for the record in the repeat offender database.

11. The system of claim 10, wherein the first characteristic and the second characteristic are selected from: a mobile device identifier; a size of the person; a facial recognition of the person; a gait profile of the person; associated people; ora vehicle identifier.

12. The system of claim 10, wherein to monitor the second characteristic from the record in the repeat offender database, the one or more processors, individually or in combination, are configured to: determine a set of available characteristics in the record; select a characteristic that the drone is capable of monitoring as the second characteristic; and position the drone with respect to the person to monitor the second characteristic.

13. The system of claim 10, wherein the risk score is based on a threat score for the record and a confidence score based on at least the first characteristic and the second characteristic.

14. The system of claim 13, wherein to activate the security measure the one or more processors, individually or in combination, are configured to select the security measure based on the threat score.

15. The system of claim 10, wherein to activate the security measure the one or more processors, individually or in combination, are configured to automatically lock one or more doors that prevent the person from entering the premises.

16. The system of claim 10, wherein the one or more processors, individually or in combination, are configured to add a third characteristic detected by the drone to the repeat offender database in response to a confidence score satisfying a threshold.

17. The system of claim 10, further comprising the drone, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi-pedal robot, or a track vehicle.

18. The system of claim 10, wherein to activate the security measure the one or more processors, individually or in combination, are configured to deploy a second drone to follow the person inside of the premises.

19. A method comprising: detecting a suspected loss condition at a premises; and deploying a drone in response to the suspected loss condition, wherein the drone is configured to: identify a suspected person involved in the suspected loss condition at a first location within the premises; and follow the suspected person from the first location to a second location outside the premises.

20. The method of claim 19, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi-pedal robot, or a track vehicle.

21. The method of claim 19, wherein the drone is configured to capture a video of the suspected person.

22. The method of claim 21, wherein the drone is configured to position itself with respect to the suspected person to frame, in the video, one or more of: a face of the suspected person; a vehicle of the suspected person; one or more people associated with the suspected person; or a gait of the suspected person.

23. The method of claim 19, wherein the drone is configured to read one or more wireless signals associated with the suspected person, wherein the one or more wireless signals associated with the suspected person include one or more of: an identifier of a mobile device carried by the suspected person; or an identifier of an electronic tag associated with an item involved in the suspected loss condition.

24. The method of claim 19, wherein detecting the suspected loss condition at the premises comprises detecting unauthorized movement of a radio frequency identification tag associated with an item.

25. The method of claim 19, wherein the drone is configured to project an image near the suspected person.

26. The method of claim 19, wherein the drone is configured to output an audible message near the suspected person.

27. The method of claim 19, further comprising deploying a second drone to follow the suspected person outside of the premises.

28. The method of claim 19, further comprising: detecting, by the drone deployed external to the premises, a first characteristic associated with a person that matches a record in a repeat offender database; monitoring, by the drone in response to detecting the first characteristic, a second characteristic from the record in the repeat offender database; and activating a security measure for the premises prior to the person entering the premises based on a risk score for the record in the repeat offender database.

29. The method of claim 28, wherein the first characteristic and the second characteristic are selected from: a mobile device identifier; a size of the person; a facial recognition of the person; a gait profile of the person; associated people; or a vehicle identifier.

30. The method of claim 28, wherein monitoring the second characteristic from the record in the repeat offender database comprises: determining a set of available characteristics in the record; selecting a characteristic that the drone is capable of monitoring as the second characteristic; and positioning the drone with respect to the person to monitor the second characteristic.

31. The method of claim 28, wherein the risk score is based on a threat score for the record and a confidence score based on at least the first characteristic and the second characteristic.

32. The method of claim 31, wherein activating the security measure comprises selecting the security measure based on the threat score.

33. The method of claim 28, wherein activating the security measure comprises automatically locking one or more doors that prevent the person from entering the premises.

34. The method of claim 28, further comprising adding a third characteristic detected by the drone to the repeat offender database in response to a confidence score satisfying a threshold.

35. The method of claim 28, wherein the drone is one of: an unmanned aerial vehicle; an autonomous wheeled vehicle, a multi-pedal robot, or a track vehicle.

36. The method of claim 28, wherein activating the security measure comprises deploying a second drone to follow the person inside of the premises.

Images