JP2009539182A - System and method for distributed monitoring of remote sites - Google Patents

Abstract

  Rules are applied to video surveillance data to detect events. Localization of the event is achieved by dividing the event into separate components, and in some embodiments, each of the components can be defined at different locations and by different users. .

Description

  The present invention relates to computer-based methods and systems for monitoring activity, and more particularly to a computer-assisted monitoring system capable of detecting events occurring at multiple sites.

CROSS REFERENCE TO RELATED PATENT APPLICATIONS This application claims the priority and benefit of US Serial Nos. 11 / 446,523 and 11 / 446,570, both filed June 2, 2006. These claims are hereby incorporated by reference in their entirety.

Background Information The current increased security awareness and lower cost of monitoring equipment have resulted in increased use of monitoring systems using technologies such as closed circuit television (CCTV). Such systems can reduce crime, prevent accidents, and generally improve security in a wide variety of environments. A series of cameras located at various locations around an area of interest (eg, warehouse, retail store, office building, airport, etc.) are typically included in a video surveillance system. The camera communicates the video feed (video material) back to the central viewing station (or stations), typically where security personnel are located. Various monitoring feeds (monitoring material) are displayed on a series of screens, and these monitoring feeds are monitored for suspicious activity.

  In addition to using CCTV systems at individual locations, using video surveillance and analysis systems to collect data on people's behavior across multiple locations (behavior) is of great importance (interest) There is. For example, a nationwide retail store chain may be interested in shopper behavior in its various stores. Data collected from a single site is useful, but only at the following times will the full value of that data be realized. That is, we compared data from various sites that provide a perspective on how best to deploy resources across multiple locations within or within a site to achieve a specific goal It's time.

  However, to be useful, data from one location should be comparable to data collected at other similar locations. That is, the same event (eg, “person paused in front of the exhibit”) should have some consistent meaning at each location. However, due to non-standard floor plans, various camera configurations, and other site differences, the occurrence of certain events can appear very different (from a surveillance system perspective) at each location. . Such discrepancies specify the event at the level of detail required to ensure that one person (eg, chief security officer or corporate marketing analyst) detects the event at multiple different locations. Make it difficult to do.

  One approach to dealing with non-uniform location problems is to have a global operator interact with the monitoring system at each individual site to define the events of interest. This approach has the advantage that events can be centrally controlled and managed, but time and resource constraints prevent scalability across multiple sites. Another approach requires that similar locations across all sites are the same in both floor plans and sensor placements. This approach allows a global operator to define the event of interest centrally and reproduce it across all locations, but requires that all locations be identical. Not realistic. The third approach leaves the responsibility for event provision to the hands of the local site operator. However, such an approach abandons any element of central control and significantly reduces data consistency across the site.

  Unfortunately, neither of these approaches is sufficient. Therefore, what is needed is a technique for defining and managing events centrally at a global level, while allowing for variations in location layout and camera configuration.

Overview According to the present invention, monitoring data (eg, video monitoring data, point-of-sale information management (“POS”) data, radio frequency identification (“RFID”) data, electronic merchandise monitoring (“EAS”) data, adjacent card data) Rules are applied to personal identification data such as and / or biometrics to detect the occurrence (or non-occurrence) of an event. To facilitate both central control and localization at the same time, event definitions are separated into multiple components, with one component defined globally and another component defined locally . A global component of an event can represent, for example, aspects of the event that are the same (or nearly the same) across all (or some large set) of locations. Local components represent aspects of events that can be customized for each location.

  For example, using the systems and techniques described below, event rules “templates” containing global specific information about events of interest (eg, theft, vandalism, purchases, etc.) and completed by remote site operators A central security authority can generate “placeholders” for localized event information that will be triggered. The operator at the remote site will typically have more knowledge about product placement, camera placement, floor plan, etc. The template is provided to the site and incorporated as part of the site monitoring system. The local system operator completes the template and approval is sent to the central authority. The acknowledgment indicates that the event is fully defined and is being used for ongoing monitoring.

  Accordingly, in a first aspect, the present invention provides a method for facilitating monitoring of a plurality of different sites. The method includes providing a set of rules that represent events of interest. The rule has multiple components, some of which are site-specific components, while other components are site independent. The site-independent components are defined globally and the rules are then distributed to multiple sites, thereby providing site-specific component definitions and monitoring of the sites using the rules. Making it easier.

  Site-specific components can be locations around the site, floor plan data, sensor identification data (eg, camera IDs, RFID sensor IDs, POS sensor IDs, and / or EAS sensor IDs), or any of them Can be specified. Site-independent components can specify actions that occur at the site, objects placed around the site, and / or people interacting with objects around the site.

  In some embodiments, an alert is received from the site indicating the occurrence of an event at the site. The alerts can be aggregated to facilitate statistical analysis of the alerts, such as, for example, determining the average number of alerts received from a site during a given period. A particular analysis can determine, for example, whether site-specific components of a rule are sub-optimal and / or provided inconsistently across sites. In some cases, changes to site-specific components suggested by the analysis can be delivered to sites where inconsistencies have been observed. A second alert can also be generated (either centrally or remotely) and communicated to a remote site, where the remote alert has one or more initial alerts. It can be a generated site, or it can be a different site. In some examples, the different sites can be identified based on an inferred relationship between the event and / or the site that received the alert. Site-specific components can also be sent to a central authority for approval and / or issuance (publication).

  In addition to (or instead of) receiving alerts, monitoring data can be received from various sites. In such cases, rules are applied to the monitoring data to detect the occurrence (or non-occurrence) of the event of interest, and thus can be aggregated and / or analyzed as described above. Possible alarms are generated.

  In another aspect, the present invention provides a system for monitoring a plurality of different sites including a rule definition module and a transmission module. The rule definition module facilitates the generation of rules that represent various events that may or may not occur at the site. The rules include site-specific components (eg, floor plan data, location, camera position information, etc.) and site-independent components (eg, actions that occur at the site, objects at the site, and objects at the monitoring site) And people who interact with it). A communication module communicates the rules to the monitoring site, where environment-specific location components can be defined.

  In some embodiments, using a web server to provide access to the rule-making module for remotely located clients, each associated with (and typically located with) a particular site. Can do. In some cases, the web server manages (controls) the access provided to remote clients, for example, restricts them so that the remote client modifies or configures site-specific components. You will only be able to access a subset of the elements. The transmission module can also receive data such as alerts indicating the occurrence of an event at a location (eg, from a monitored environment), as well as video, RFID data, EAS data, and POS data. Sensor data can be received. In some embodiments, the system may, for example, aggregate received data, compare the number of alarms received from a monitoring location, and receive alarms and / or monitoring for statistical analysis. An analysis module can also be included to determine the accuracy and consistency of environment-specific components by identifying inconsistencies in the data. Based on the identified inconsistencies, the rule can be modified (eg, using a rule definition module), and in some cases, the modification is redistributed to the remote site via the communication module be able to. The system may also include a data storage module for storing video surveillance data, rules, results of analysis performed by the analysis module, as well as other application specific data.

  In another aspect, the present invention provides a method for monitoring a site. The method includes providing a standard site layout that specifies an element or elements that are common to a number of sites. Events are assigned to the element regardless of the actual layout of the site, resulting in a standard site layout with annotations. The annotated layout is then communicated to a user who is familiar with the site to which the layout was sent, so that the user can then download a standard site layout (eg, downloadable such as an AJAX applet). Can be modified (using an applet). Thereby, the site layout matches the actual site layout and can be used to monitor the site.

  The element can specify a location around the site, such as floor plan data. Events assigned to standard floor plans can be site specific (eg, sensor identification data such as camera IDs, RFID sensor IDs, POS sensor IDs, and / or EAS sensor IDs), and / Or may be site-independent, such as location (exit, passage, etc.) or interaction between a person and an element (eg, a customer stops at a product display).

  In some embodiments, the modified layout may be used in a monitoring system (eg, at one or more of the sites) as a basis for generating an alert based on the occurrence of an event. Is possible. The alarm can be analyzed to determine, for example, the accuracy of events and / or floor plans.

  In another aspect, the present invention provides a system for monitoring a site that includes a user interface and a modification module. The user interface includes a standard site layout window frame in which site-independent elements are associated with the standard site layout and a window frame in which the actual site-specific layout is presented to the user. The modification module facilitates associating site-specific elements of the actual site layout with site-independent elements.

  In some embodiments, the modification module includes an asynchronous java script applet. The system may also include a web server for providing the applet to the user and for processing data requests from the applet using, for example, XML. A data storage module can also be used to execute data requests implemented by the modification module and sent via the web server.

  In the drawings, like reference characters generally refer to the same parts throughout the different views. Furthermore, the drawings are not necessarily to scale, emphasis instead being placed upon generally illustrating the principles of the invention.

1 is a block diagram of a monitoring system that captures data from multiple sensor networks according to one embodiment of the invention. FIG. 1 is a block diagram of one embodiment of a monitoring system having both centralization and remote processing functions according to one embodiment of the present invention. FIG. FIG. 3 is an example of various components used to define an event within a monitoring system according to one embodiment of the invention. 3 is a flowchart illustrating a method for realizing a monitoring system according to an embodiment of the present invention. 6 is a flowchart illustrating additional steps of a method for implementing a monitoring system according to an embodiment of the present invention. 6 is a flowchart illustrating additional steps of a method for implementing a monitoring system according to an embodiment of the present invention. FIG. 3 is a screen capture of a user interface for realizing a monitoring system according to an embodiment of the present invention. FIG. 3 is a display diagram of a user interface for defining a floor plan template for a monitoring system according to an embodiment of the present invention. FIG. 4 is a screen capture of a user interface for defining location components of events within a monitoring system according to one embodiment of the present invention. FIG. 6 is a screen capture of a user interface for defining events in a monitoring system according to an embodiment of the present invention. FIG. 6 is a screen capture of a user interface for modifying an event in a monitoring system according to an embodiment of the present invention. FIG. 4 is a display diagram of a user interface for causing a site-specific component to be caused by an event in the monitoring system according to an embodiment of the present invention. FIG. 4 is a display diagram of a user interface for customizing a site-specific floor plan using a floor plan template in a monitoring system according to an embodiment of the present invention.

DETAILED DESCRIPTION Implemented in connection with tracking customers and products within a retail store, and with regard to detecting theft and evaluating (measuring) various promotions and operations of multiple stores Although described herein as being useful in some cases, the systems and techniques described below are monitored, such as airports, casinos, schools, amusement parks, entertainment venues, and office buildings. It can be similarly provided for a wide range of purposes for any environment of the condition.

  FIG. 1 illustrates an integrated video surveillance and sensor network system 100 according to various embodiments of the present invention. The system 100 captures monitoring data from any number of monitoring devices within one or more monitoring sites. Thus, the data is for analysis at a single central location and / or at any number of intermediate data processing locations and / or (at each monitoring device, at a local processor, or both). It is available for processing locally. In some embodiments, the processing and analysis techniques described below can be allocated between remote, intermediate, and central sites according to bandwidth, processing power, and other parameters. Data from the monitoring device can be processed according to one or more rules to detect the occurrence (or even non-occurrence) of an event or multiple events at the monitoring site. The system generally comprises an intelligent video surveillance system 105 and optionally one or more external sensor networks 110. The intelligent video monitoring system 105 includes a video processing module 115 and an alarm / search processing module 120. The video processing module 115 analyzes the video stream and generates compressed video and video metadata as output. In some embodiments, the alert / search processing module 120 comprises a tracking module 130, an alert module 135, and a delivery module 140 that scans the video metadata for patterns that match a predetermined set of rules to match the patterns. Is found, an alert (or a search result in the case of pre-recorded metadata) can be generated and then the alert can be communicated to one or more output devices 145. Yes (described in more detail below). Examples of metadata used by the alert module when processing rules include object IDs, object type (eg, human, product, etc.), date / time stamp, current camera location, previous camera location, direction data Product cost, product shrinkage, and others.

  Commonly owned, co-pending US Patent Application Serial No. 10 / 706,850, “Method And System For Tracking And Behavioral Monitoring Of Multiple Objects Moving Through Multiple Fields-Of-View” includes intelligent video An example of a monitoring system 105 is described, the entire disclosure of which is incorporated herein by reference. In one embodiment, “Object Tracking and Alerts” filed on May 30, 2006, commonly owned, owned US Patent Application Serial No. 11 / 443,500, Point-of-sale (“POS”) systems, radio frequency identification (“RFID”) systems, and / or electronic merchandise monitoring, as described in this disclosure, which is incorporated herein by reference in its entirety. The alarm / retrieval processing module 120 is augmented by additional inputs for receiving data from the external sensor network 110 using various forms of tracking and data capture, such as a (“EAS”) system. Yes.

  The video surveillance system 105 includes a plurality of input sensors 125 that capture data indicative of interactions between people and things in the monitored environment. Sensor 125 generates a camera (eg, optical sensor, infrared detector, still camera, analog video camera, digital video camera, or image data of sufficient quality to support the methods described below. And any non-video based sensors (eg, RFID base stations, POS scanners, and inventory management systems). Sensors also include smoke, fire and carbon monoxide detectors, door and window access detectors, glass breakage detectors, motion detectors, audio detectors, infrared detectors, computer network monitors, audio identification devices, video cameras , Still cameras, microphones, and / or fingerprints, faces, retinas, or other biometric devices. In some examples, the sensors can include conventional emergency buttons, global positioning system (GPS) positioning devices, other geographic positioning devices, medical indicators, and vehicle information systems. Sensors can also be integrated into other existing information systems, such as inventory management systems, accounting systems, or the like.

  In an example in which an additional external sensor network 110 is incorporated with the video surveillance system 105, the external sensor network 110 collects signals representing sensor outputs and via one or more standard data transmission techniques. This is sent to the alarm / search processing module 120 of the video monitoring system 105. The signal can be transmitted over a LAN and / or WAN (eg T1, T3, 56 kb, X.25), broadband connection (ISDN, frame relay, ATM), wireless link (802.11, Bluetooth, etc.), etc. . In some embodiments, the video signal can be encrypted using, for example, trusted key pair encryption. Various sensor systems can use Ethernet or wireless networks, direct serial or parallel connections, USB, Firewire, Bluetooth, or various communication paths such as proprietary interfaces Can be transmitted. The system 100 can be configured as a “star network” where each sensor 125 is individually connected to the alarm / search module 120, or in some cases the sensor network 110 can be It can have a more general topology, including switches, routers, and other components commonly found in computer networks. In some embodiments, the sensor 125 is capable of two-way communication, and therefore from the video surveillance system 105 (such as to activate, sound an alarm, operate, change settings, etc.). A signal can be received.

  In some embodiments, the system 100 includes a video storage module 150 and a rules / metadata storage module 155. The video storage module 150 stores the video captured from the video monitoring system 105. The video storage module 150 includes VCRs, DVRs, RAID arrays, USB hard drives, optical disk recorders, flash storage devices, image analyzers, general-purpose computers, video enhancement devices, interlace removers (deinterlacers), scalers, and / or Other video or data processing and storage elements for storing and / or processing video may be included. National Television System Committee (NTSC), Phase Inversion Line (PAL), and Sequential Color Memory (SECAM), uncompressed digital signals using DVI or HDMI connections, and / or common codec formats (eg, MPEG, Video signals can be captured and stored in a variety of analog and / or digital formats, including compressed digital signals based on MPEG2, MPEG4, or H.264) as examples only. .

  The rule / metadata storage module 150 stores metadata and rules captured from the video monitoring system 105 and the external sensor network 110. The metadata is compared to the rules to determine if an alert should be triggered. The rule / metadata storage module 155 can be implemented on a server class computer that includes application instructions for storing alert rules and providing the alert rules to the alert / retrieval processing module 120. Examples of database applications that can be used to implement the video storage module 150 and / or the rules / metadata storage module 155 include a MySQL database server by MySQL AB, Uppsala, Sweden, or Berkeley, California. A PostgreSQL database server by the PostgreSQL Global Development Group, or ORACLE Corp. of Redwood Shores, California. The ORACLE database server provided by is included. In some embodiments, the video storage module 150 and the rules / metadata storage module 155 can be implemented on a single server using, for example, multiple partitions and / or instances. As a result, desired system performance can be obtained.

  Various external sensor networks 110 can provide data to the system 100. For example, a POS network includes a number of stations (eg, cash registers, scanners, etc.) connected to a network, and when activated, the sensors in the station can detect customer transaction information (product, price, customer ID). Etc.), as well as the state of money withdrawal (eg, open or closed) to the network. Similarly, an EAS network typically includes a number of pedestals located near a retail outlet. The pedestal detects the presence of an activated EAS tag placed on an expensive (or in some cases all) product. When the presence of a tag is detected, the pedestal communicates information over the network to a central location. Many commercial buildings also use security systems that detect the opening and closing of doors, and “cards” that require employees to pass or present an authentication card when entering or leaving the facility. A “through” system is used. In accordance with the present invention, some or all of these sensor-based surveillance systems 110 are integrated with the video surveillance system 105 to improve its functionality and accuracy. Of course, the above list of sensor types is not exhaustive and merely provides examples of the types of sensor networks 110 that can be accommodated.

  In one non-limiting example, the sensor network 110 includes an RFID subsystem. The RFID subsystem itself interacts with repeaters (transponders) located on objects being tracked by the monitoring system 100 (also referred to as “base stations” or “stations”). Includes a transmitter. The station transmits RF energy intermittently (eg, every nth millisecond, where n is some selected integer) within an effective radius of the station. When a repeater enters this effective radius, its RF energy “wakes up” the repeater, which then interacts with it and transmits an identification signal to the station. The signal typically includes various information about the object to which the repeater is attached, such as SKU code, source code, quantity code, and the like. This data can be augmented with information from the transmitter (eg, transmitter ID and date / time stamp) and saved as a unique record. By placing multiple transmitters around an area (e.g., across a store or warehouse), using the coordinates of the transmitters and the time at which they interact with the repeater, RFID An RFID subsystem can be used to determine the location and path of the object carrying the tag.

  In some embodiments, the alarm generated by the alarm / search processing module 120 is a smart terminal or dumb terminal, a network computer, a wireless device (eg, portable PDAs), a mobile phone, an information device, or the like. A workstation, minicomputer, mainframe computer, or other computing device that can be operated as a general purpose computer, or used alone to function as an output device 145 in the system 100 It can be communicated to an output device 145 such as a dedicated hardware device. In one example, a security officer is provided with a wireless output device 145 having text, messaging, and video capabilities when patroling the surveillance environment. When an alert is generated, a message is communicated to the output device 145 to direct the person in charge to a particular location. In some embodiments, the video can be included in the message and provide a patrol officer with a visual confirmation of the person or object of interest.

  In some embodiments, the output device 145 can also include geographic information service (GIS) data. In such embodiments, maps and / or floor plans (either actual photographs or graphical representations thereof) are combined with image and textual information representing the environment and objects within the environment. For example, security personnel working in a large store can be provided with a wireless handheld device (such as a SAMSUNG SCHi730 mobile phone), which can be provided with a floor plan and / or Or still images and / or video graphics including parking areas near the store can be provided. Using GPS coordinates acquired by similar devices (or, in some cases, RFID base stations located throughout the store), the location of various exhibits, personnel, vendors, or groups It can be determined and displayed as a map of the store. In this way, features that are common to all sites, but that are located as much as possible in different locations, can be mapped for each site.

  As the system 100 analyzes the movement of customers and other objects, the alert / search processing module 120 uses the metadata received from the video surveillance system 115 and the external sensor network 110 to satisfy one or more rules. And if so, generate an alarm. As an example, an object ID associated with a customer and a product ID associated with a product of interest may be manually associated and / or automatic (eg, based on repeated detections in two adjacent objects). It can be linked using techniques. If it is determined that the product and customer are located in common (either repeatedly, continuously, or at some defined interval), the customer is placed in their shopping cart. An alarm can be generated indicating that the product has been placed in A subsequent indication that the product was detected at the RFID station at the store exit, and a lack of indication that the product was scanned at the POS station may indicate a shoplifting event. The alert can then be communicated to security personnel. With the GIS device enabled, the security personnel can see the product and customer locations on the store floor plan.

  In some embodiments, additional data can be added to the display, such as crowd density or coloring representing the preferred route, further facilitating the rapid movement of security personnel to a particular location. it can. Color enhancement can also be added to indicate how fast the object is moving or the degree of threat that the object poses to the monitored environment. In some cases, update data (updates) can be communicated to the display to provide a real-time (or near real-time) display of monitored events and objects.

  FIG. 2 illustrates an exemplary embodiment 200 of the present invention. In example 200, multiple video surveillance and sensor network systems 100 are deployed in a distributed manner to facilitate monitoring multiple sites. As shown, the distributed video surveillance and sensor network system 100 includes at least one central site 205 and a plurality of remote sites 210, 210 ′, 210 ″ (generally 210) that communicate over the network 215. With. As shown, the system comprises three remote sites, but this is merely for illustrative purposes, and in practice any number of sites 210 can exist. Each remote site may include one or more components 220, 220 ′ of video monitoring and sensor network system 100, such as local client software 225 and / or one or more sensor networks 230 for monitoring the remote site. 220 ″ (generally 220). In some examples, a complete embodiment of intelligent video surveillance system 105 may exist at each (or several) of remote sites 210. For example, one remote site (eg, warehouse, store located in a metropolitan area) can be large enough to guarantee a complete implementation of the system, while other implementations In the form, typically smaller sites can be restricted to sensor devices that communicate captured data to the central site 205. In some embodiments, multiple remote sites 210 may send video and / or sensor network data to some number (typically greater than 1) for processing, analysis, and / or storage. And smaller than the number of remote sites).

  Local client software 225 can facilitate remote connections to servers at central site 205. In such embodiments, the local client software 225 can include a web browser, client software, or both. The web browser allows a user at the remote site 210 to request a web page, or other downloadable programs (eg, from the central site 205 and / or other remote sites 210) along with the web page request. Or an applet or a document can be requested. An example of a web page is a data file containing information, graphics, audio, text, and / or video that can be executed or interpreted by a computer. The data file can be displayed, executed, played, processed, streamed and / or stored, and can include links or pointers to other web pages. In one embodiment, a user of local client software 225 manually requests a web page from central site 205. Alternatively, the local client software 225 can make the request automatically using a web browser. Examples of commercially available web browser software include Internet Explorer provided by Microsoft Corporation, Netscape Navigator provided by AOL / Time Warner, or FIREFOX provided by Mozilla Foundation. .

  The local client software 225 may also include one or more applications that allow a user to manage the components of the sensor network 230 and / or the rules for monitoring that particular site 210. . The application can be implemented in various forms, for example, in the form of a Java applet downloaded to a client and executed with a web browser, or the application can be implemented in Java or Visual Basic. Or in the form of a stand-alone application, implemented in a multi-platform language such as C, or in code executable by a native processor. In one embodiment, when executed on a client at remote site 210, an application opens a network connection to a server at central site 205 on communication network 215 and communicates through that connection to that server. Do. In one particular example, the application can be implemented as an information screen within a separate application, eg, using asynchronous Java script and XML (“AJAX”). As a result, many of the operations activated by the user are processed at the remote site. In such a case, data can be exchanged with the central site 205 behind the scene, and any web page being viewed by the user at the remote site is reloaded every time a change is made. Does not need to be done, thus improving application interactivity, speed, and usability.

  For example, remote site 210 includes the MICROSOFT WINDOWS family of operating systems from Microsoft Corporation in Redmond, Washington, the MACINTOSH operating system from Apple Computer in Cupertino, California, and SUN North Carolina, SUN MICROSYSTEMS from SUN A personal computer capable of running an operating system such as various variants of Unix, such as GNU / Linux (and others) by Durham's RED HAT, INC Locale on It is possible to run the software 225. Local software 225 is also a smart terminal or dumb terminal, network computer, wireless device, mobile phone, information device, workstation, minicomputer, mainframe computer, general-purpose computer, or general purpose computer or monitoring system It can also run on hardware such as other computing devices that are operated as dedicated hardware devices used alone to function as clients within.

  The central site 205 interacts (interacts) with the system at each of the remote sites 210. In one embodiment, a portion of video surveillance and sensor network system 100, such as intelligent video surveillance system 105, is implemented on server 240 at central site 205. In such an example, server 240 is preferably implemented on one or more server class computers. The server class computer has sufficient memory, data storage, and processing power to run a server class operating system (eg, SUN Solaris, GNU / Linux, and MICROSOFT WINDOWS family operating system). To do. Depending on the capabilities of the device, the number of sites, and the amount of data being received and analyzed, system hardware and software may be used, except for the system hardware and software described herein. it can. For example, the server 240 can be a server farm or a logical group of one or more servers, such as a server network, or can be part of it. As another example, there can be multiple servers that can be associated with or connected to each other, or multiple servers can operate independently, however, with shared data. In a further embodiment, as is typical in large systems, application software can be implemented on components, whether different components are on different server computers or on the same server. , Or some combination thereof. In some embodiments, the server 240 can be implemented and operated by a service office or hosting service. The certain service department or hosting service represents various, sometimes irrelevant (desiring to outsource such services) companies.

  The communication network 215 connects the remote implementation to the server 240 using the transfer module 245 at the central site 205. Non-limiting examples of applications that can perform the functions of the delivery module include APACHE Web Server and WINDOWS INTERNET INFORMATION SERVER. The communication can occur via any medium and protocol as described above with respect to FIG. Preferably, the network 215 is capable of propagating TCP / IP protocol communications, and is responsible for HTTP / HTTPS requests made by local software and / or servers and connections between the local software 225 and the server 240. It can be transmitted on such a TCP / IP network. However, the type of network is not limited and any suitable network can be used. Non-limiting examples of networks that can function as or as part of the communications network 215 include wireless or wired Ethernet based intranets, local or wide area networks (LAN or WAN), and / or A global communication network (known as the Internet) that supports a number of different communication media and protocols.

  In embodiments where some or all of the processing and analysis is performed at the central site 205, the server 240 also provides for the definition, storage, and analysis of data and rules related to the monitoring of the remote site 210. Various application modules can be included. For example, the rules module 250 may define rules for events of interest (which may occur at a remote site) and the rules (generally or at a particular site), as described in more detail below. To facilitate the provision of floor plans to be attributed to the site (in any of the above).

  Server 240 may also include a central storage module 255, such as a database system. The central storage module 255 stores data received from the remote site 205, rules regarding events of interest, user permissions, industrial data, and the like in one or more databases. The database typically provides data to other modules residing on the server 240 and local software 225 at the remote site 205. For example, the database can provide information to the analysis module 260, which compares the defined rules with the video data to determine whether a particular event has occurred. In some embodiments, the analysis module performs a review of historical data to identify characteristics in the data, such as frequent instances of a particular event at a site when compared to other sites. Try to do. The central storage module 255 can also include a separate database for video, non-video sensor data, rule components, historical analysis, user permissions, and the like. Examples of database servers that can be configured to perform these and other similar functions include those described in connection with the storage module of FIG.

  Server 240 may also operate as a mass memory device for storing application instructions and data for communicating with remote site 210 and for processing its monitoring data. More specifically, the server 240 provides event detection and monitoring applications according to the present invention to obtain monitoring data from various devices at the remote site 210 and to manipulate the data at the central site 205. Can be configured to store. The event detection and monitoring application includes instructions executable by a computer, such that when the instructions are executed by the server 240 and / or local software 225, the monitoring will be described in more detail below. Acquire, analyze, and communicate data. Using a drive mechanism associated with any computer readable medium, such as a floppy drive, a CD-ROM drive, a DVD-ROM drive, or a network drive, the event detection and monitoring application may use the computer readable medium. Can be stored in the server 240 and loaded into the memory of the server 240.

  In many embodiments, the remote site 210 can be uniform in function and / or design. However, in many instances, one or more of the sites 210 will be different from the others. For example, a department store chain can implement a system in accordance with the present invention over some or all of its warehouses, distribution centers, and retail stores. Thereby, the floor plan, activity, and management schedule for various sites will be different. In some examples, a site may be very similar (eg, a similarly designed storefront), but may be specific to the neighborhood where the store is located and / or to a particular store Benefit from different monitoring strategies due to environmental differences, such as promotional events. In such an example, defining a global rule set that represents various aspects of the event of interest at each location without significantly affecting accuracy or overburdening the staff at each site It is difficult.

  FIG. 3 shows the configuration of a multi-component event. The configuration balances the need for central rule definition with the need for scalable embodiments, depending on the desirability of localized input and customization at the remote site. In general, the configuration of the present invention combines multiple components. Some of the multiple components that make up event 305 are global in nature (ie, features are not unique to any particular site that has site-specific components). Therefore, the occurrence (or non-occurrence) of the event 305 can be detected based on the detection of each component as defined in the event. For example, one component of an event can be a location 310, such as a point-of-sale counter, an exit, a corridor, an entrance, or other physically identifiable location. The components of event 305 also include an object 315, such as a particular product in a retail store, and an action 320, such as selection and / or purchase of object 315 or movement of a person around the site. Can be included.

  Events can be implemented as rules that are used to examine the occurrence or non-occurrence of events at one or more sites. One possible form for rules uses Boolean logic. As an example, when using an illegal employee return event, the rule would be “if ((returned in POS #XXX) and (not (object #YYY exists in camera display #ZZZ))) Can be expressed as Here, “XXX” indicates a unique ID number assigned to each POS station, “YYY” indicates a specific product, and “ZZZ” is assigned to a camera having a field of view corresponding to the POS station. It refers to a unique ID number. While the provisions of the rules and thus the association between the region ID and the POS station ID can be manually formulated by the user (with knowledge of the specific POS station and camera location) of the system at that site, the site Product information can be defined globally by users who lack specific knowledge but know that the particular item is frequently stolen or returned incorrectly.

  In general, alarm rules use Boolean logic (eg, AND, OR, and NOT operators) that can be detected on a given sensor network to identify an event and its components. Combine together. For example, the POS event may include “return processing performed”, “cash withdrawal opened”, “product ZZZ purchased”, and the like. The video system event may include “object exists”, “object is moving”, “number of objects> N”, and the like. Security system events may include “card # 123456 passed”, “door open”, “operation detected”, and so on.

  Events can be combined with Boolean logic to generate an alert expression that can be arbitrarily complex. A rule can consist of one or more alert expressions. An alert is generated if the entire expression evaluates to “true”. For example, consider an alarm that detects whether two people have left a store when an electronic merchandise surveillance (EAS) event is detected. The constituent elements of the event are “tag detected” and “number of objects> 2.” If both are true, the event has occurred and an alarm is triggered. Therefore, the compound expression is “(tag detected in EAS # 123) and (number of objects in area # 456> 2)”. As described above, a unique ID number is used to associate that particular EAS pedestal with a region of interest on the appropriate camera.

  As another example, a single credential (commonly referred to as “piggybacking”) is used to trigger an alarm based on detecting two people entering a restricted-access door can do. The alert rule is similar to the EAS alert rule described above. That is, “if ((door is opened in door # 834)) and (number of objects in area # 532> 2)) then alarm”. Other alerts can be based on the movement of objects such as hazardous materials, cars, and merchandise. The other alert determines whether the object is moving into a restricted area, moving very fast, or moving at a time when activity should not be detected.

  As well as detecting employee return fraud, it is often useful to know when a POS office cash withdrawal is open and no customers are present. Such events frequently indicate employee theft. As an example of a more complex rule, detection of this event can be combined with employee return fraud rules, so that one rule can detect both cases. That is, “If (((Return processing was performed in POS #XXX) or or cash withdrawal was opened in POS #XXX)) and (not (object exists in area #YYY)) then alarm” .

  Each component together provides an event, such as a product that has been selected by the customer and brought to the cash register. Such events can be defined theoretically, i.e. any particular register, the monitoring device 325 used to monitor the register, or the operating area 330 of the device (e.g. , Or the field of view of the camera or the operating radius of the RFID sensor). The event is not completely accurate until such information is added to the event. Therefore, the ability to deliver individual event component provisions to personnel who are specially familiar with the physical attributes of the individual sites allows the overall purpose of the event to remain constant between sites. While possible, it allows the necessary customization of events to address various physical characteristics of the site.

  In many cases, each of the remote sites will share certain characteristics (eg, they all have passages, doors, restrooms, exhibits, etc.), but the characteristics of that particular configuration are different. It will be. As an example, a convenience store chain may have a self-service food area, a freezing case, and a toilet in each store, but the physical layout between these areas is different due to different floor plans. The relationship will be different. More specifically, a store's refrigeration case may be along the back wall, and its cashier counter may be located along the same wall as the exit, In this store, the refrigeration case is in the central passage of the store, and the cashier counter is on the opposite side of the exit.

  To further facilitate the implementation of a defined event, such as for a particular store, a general site template (or series of templates) representing the “standard form” of the site floor plan from each remote site Can be prescribed. For example, a standard floor plan can define any number of general attributes and physical characteristics (eg, walls, exits, passages, rooms, etc.) at a site. Standard floor plans are common between sites, as described in more detail below, and in some cases, events are associated with one or more elements of the floor plan. In some embodiments, for example, if the user has some knowledge of a particular set of site layouts, the standard floor plan includes general characteristics and site-specific elements. Can be included.

  FIGS. 4-6 illustrate various embodiments of techniques for implementing a rules-based monitoring system across multiple different sites. The process can generally be divided into three distinct phases. That is, in the definition phase (generally shown in FIG. 4), the customization and monitoring phase (generally shown in FIG. 5), and the alarm and analysis phase (generally shown in FIG. 6). is there. During the prescribing phase, global attributes of the event are defined and a general site floor plan can be created at the central site. During the customization and monitoring phase, events and / or floor plans can be tailored to individual sites and used to monitor activity at the sites. During the alert and analysis phase, alert and sensor data is received at the central site and analyzed to identify trends and anomalies in the data.

  In describing the various tasks of the technique, the roles of the two users are referred to throughout the text below. First of all, the “central user” should be responsible for performing tasks originating from the central site, which are generally global in nature, ie, some of the remote sites. It can be applied to such a set (or all in some cases). Second, “remote users” should be responsible for tasks originating from the remote site, which are generally specific to a certain one (or some small group) of remote sites. . Typically, such tasks are left to the remote user. This is because the central user lacks site-specific knowledge to perform the task (eg, assigning a particular camera to an event) or the amount of tasks spans a large number of users. This is because the amount of work distribution is more efficient.

  Referring to FIG. 4, the central user of the system can use one or more sites that can be used as a starting point for site independent components (site independent components) and site specific floor plans in the event. Perform various tasks that define general floor plans. More specifically, the central user defines the event configuration by identifying the various components of the event (step 405). As mentioned above, the components can be site independent or site specific. Examples of event-independent event components include actions (eg, product selection, movement, purchase, etc.) and objects (eg, people, products, cars, money, etc.). Examples of site-specific components include surveillance, such as cameras, point-of-sale offices, RFID transmitters, adjacent card readers, and other devices located around the site for the purpose of receiving surveillance data A sensor is included.

  Components such as location can be both site-independent and site-specific. For example, a central user may have a location in general nature (ie, for example, an exit, point-of-sale counter, a restroom, a parking lot, and / or a product-specific aisle or exhibit), It can be defined if it is known to exist at each remote site (or some number of remote sites). These locations can be customized by the remote user by converting the abstract location defined at the central site to the actual location at the remote site.

  The various components of the defined event allow the central user to specify information for some or all of the global components (step 410). For example, the central user can specify that the event is based on an action (eg, selection) attributed to two objects (eg, a customer and a specific product). In some embodiments, an event can include a combination of actions, objects, and locations, and a non-occurrence of each. Each component can have one or more thresholds associated with each component, such as date / time parameters and counts, and in some cases these parameters can be assigned to a central user. Or by a remote user or both. The parameters can also be reset manually and / or automatically based on meeting a threshold and / or the occurrence or non-occurrence of an event. By causing time-based parameters to be attributed to the event, the threshold of the event can be adjusted in a manner that allows the event to be accurately detected while minimizing false positives. For example, an event directed to shoplifting detection includes three operational components such as product selection, exit, and no sale, and two product components such as a person and a particular item of the product, Two location components can be included: a point-of-sale counter and an exit. Once defined, the event can be delivered to the remote site for further customization and implementation (step 415).

  In some embodiments, the central user also defines one or more standard floor plans that can be used as templates for remote locations (step 420). In some cases, one standard floor plan can be used for all remote sites. However, in many cases, multiple standard floor plans can be designed as templates for a subset of remote sites that share multiple features. For example, a large retail chain has a large number of different brands such as numerous warehouses and distribution centers, stores targeting teenagers, stores targeting infant parents, and stores targeting professionals. You may have a store. In such a case, the central user can define a standard floor plan for each type of site. In some examples, a standard floor plan for one type of site (eg, a store for teens) and a standard floor plan for other sites, such as a store for professionals. Can be used as a template for (with possible minor modifications). The number of different standard floor plans that can be created is virtually unlimited, but in general, the degree of similarity between sites and the availability of the central user designing the floor plan It will be determined by the degree. The standard floor plan can also be annotated with one or more events (step 425) and delivered to a remote site (step 430). Thus, the remote user is provided with a starting set of events and a general floor plan, the remote user can construct a site specific floor plan from the general floor plan, and the site Event specifications can be completed by adding specific components.

  Each of the event configurations, events, floor plan templates, and combinations thereof may be stored, for example, in the central storage module 255 of the server 240 at the central site.

  Referring to FIG. 5, the remote user receives the event and / or floor plan (step 505) and customizes the event and / or floor plan using the local software and system described herein. To meet the individual needs of each remote site, or possibly a remote site group. The remote user can define site-specific components of events initiated by the central user, for example, by adding or modifying location components specific to a particular site (step 510). For example, a remote user can assign one or more monitoring sensors to a location. Thus, the event “select product from beverage display (beverage display)” is the location of the object in the display, the camera having the field of view including the display, the RFID sensor having the operating radius including the display, and / or the display. Or it may be associated with other sensors used to track movement. In an embodiment where the camera (or other sensor) field of view is further subdivided into multiple sub-regions, the remote user can select the floor plan and sub-region areas using an interactive graphical interface. By doing so, both the camera ID and the sub-region ID can be assigned to the event.

  In some embodiments, remotely defined events and / or components that make up the events can be reused at individual sites and by a central user. This allows the central user to use the remote user's knowledge of the site in building subsequent events and floor plan templates. For example, the central user can define a location component, such as “Build a shelf (end cap)” for inclusion on the retail floor plan, which is defined by the remote user. Based on a given location, it has certain parameters (height, duration, sensor ID number) associated with it.

  The remote user can also set parameters associated with the event. For example, a store may remain at a different time than other stores, or may have a specific time that requires additional security, so the time parameter governing the event is It can be different from store to store. As another example, an acceptable time span between two events (e.g., a shopper is selecting an item and is leaving the store) has a larger floor area than a smaller store. May need to be larger in a store with

  In an embodiment where a standard floor plan is received at a remote site, the remote user can customize the floor plan to meet the needs of a particular site (step 515). For example, a central user can provide a general layout with four aisles, two point-of-sale locations and one exit. However, if the remote site has six aisles, three point-of-sale locations, and two exits, the remote user will have the floor plan more accurately represent the actual layout of the site. As you can see, you can add the necessary elements. In addition, the central user arranges the elements in a general manner, regardless of the relationship between the elements and / or surrounding walls. Again, the remote user can manipulate the floor plan (eg, using the local software 225 in the above and further detailed description below) so that the floor plan is the actual map. It will reflect the site (or make it very similar).

  In some examples, the central user may have defined the event, and such associations are common across many sites, such as associating a customer's selection of a merchandise item with a particular aisle. The event may be related to an element of the standard floor plan based on the judgment of the central user. However, if such an association is not accurate (eg, the product has not been transported to a particular store or it is left behind a counter), the remote user Can discard the association, redefine the event, associate it with a different element of the floor plan, or associate it with any combination of the foregoing. In one example, the remote user can delete a centrally defined event or event component if it does not match the remote site. Providing remote users with the building blocks of an event-driven monitoring system that maintains some consistency across many sites, and allows events to be customized at the site level By doing so, the system balances the need for data commonality with site variability. As a result, the central site receives data that can be compared from different sites.

  Once the event and / or floor plan is customized for the site, the event is realized in the monitoring system (step 250). In some embodiments, the implementation includes saving customized events and / or floor plans to a central storage module at the server. In other embodiments where the monitoring system (or part thereof) is implemented at a remote site, the local storage 525 is used to monitor the site for events and floor plans and activities related to the event (step 530). Application code used by the system for the purpose.

  While the system is monitoring the site (or even later), information can be communicated to the central site (either programmatically, manually, or both). For example, in an embodiment where the alert / search processing module (120 in FIG. 1) is located at a remote site, in addition to generating an alert based on the occurrence of an event and dispatching the alert to local security personnel The alert can also be communicated to a central site for analysis and for comparison across multiple sites (step 535). In other embodiments, video data is sent to a central site in real time for event processing and alerting, or periodically to provide central storage and analysis of associated metadata across video and site. It can also be communicated (step 540). In some cases, the video data can be sent in batch mode (eg, once at night) during off-peak hours to avoid congestion and overload of data processing resources. Similarly, sensor data from other sensors (RFID, POS, etc.) can be communicated to a central site for similar purposes (step 545).

  Referring to FIG. 6, alarm, video, and / or sensor data is received at the central site (steps 605, 610, and 615) and stored at the central site (eg, in central storage module 255). And can be processed. In some embodiments, the data is aggregated (step 620) and analyzed (step 625). The alerts can be aggregated and analyzed according to time, site (s), and / or objects specified in the event that triggered the alert. For example, if an employee at a central site wants to compare shoplifting events related to a particular product (eg, razor, baby milk, etc.) across multiple sites, based on the event with these products All alerts can be selected and grouped by site. In some examples, the video and / or sensor data captured during the event can be further analyzed (step 630) to determine whether the event was a false positive or to correct the event. It can be ascertained whether other actions or objects to be considered at times were present during the event. The analysis can be performed, for example, using a central analysis module 260 that resides on the server 240.

  Based on the analysis, outliers (outliers) can be identified that indicate that one or more events are inappropriately defined (step 635). For illustrative purposes, if an event is delivered to multiple sites, the average number of alerts received from each store may indicate a “typical” event rate for that type of site. However, receiving a significantly higher or lower number of events (eg, a standard deviation greater than 2 from the average) from a particular site means that the event is improperly defined at that site or that site It can be shown that the other parameters are actually different from the site it is being compared to. For example, location-specific components in the event may be inaccurate (for example, the wrong path was caused by the product, or the wrong camera was assigned to the area) and the sensor may not function There may have been a remote user sabotaged the system to hide employee-based theft. In such cases, the central user can propose a correction for the event, or in some cases, the central user can make the correction himself (step 640) and the event to the affected site. Can be redistributed (step 650).

  Additional alerts can also be generated using the inferred relationship between the site, location, event, and objects within the site, and the alert can be delivered to the site. For example, an alert received from two different sites at an interval comparable to the propagation time between the two sites indicates that the same (or related) item in the product has been stolen, and the same person has both theft Can be shown to be involved. Once such a connection is identified, the central site communicates a second alert (eg, including text, video, and / or both) to the site within a radius from the site where the item was stolen. Can alert you to the site to be aware of the possibility of theft. Identification of the remote site can be based on manual selection of the site or, in some cases, can be performed automatically based on historical data stored at the central site. In the example where the relationship between sites is delivered to the site, the second alert can be generated at the first remote site, whether it is geography, product line, or other historical data. Can be transmitted to the site (s) determined to be “related” to the first site.

  In the example where both alerts and some or all of the sensor data are received at the central site, additional rules can be applied to the sensor data. For example, additional rules may be essential (eg, determining patterns or trends in the data) and / or confirming (eg, duplicate copies of rules are delivered to the remote site to provide an appropriate number of alerts. Confirming that the rules are returning) can be more complex. Sensor data can also be combined with actual alarm data (both accurate and inaccurate) and used as input to the training algorithm. In the training algorithm, the system can effectively “learn” to more accurately identify events of interest.

  In addition to the usage associated with security events, the data can also be used for marketing and operational purposes. For example, events can be defined to monitor sales activities during a sale, new product launches, customer traffic, or periods of interest. Aggregate alerts based on the occurrence of such events and compare the overall customer experience across multiple stores and at different times to promote, price, and other product-related events Can be determined.

  Referring to FIG. 7, an example application screen includes a user interface 700 that is driven by a menu to implement the systems and techniques described above. The interface 700 includes four main functions: template definition 705, location definition 710, event definition 715, and event / location display 720. A template definition function 705 facilitates defining and modifying a standard floor plan that can be used as a starting point for site-specific layouts. A location definition function 710 facilitates defining a general location where one or more actions occur and objects interact. Location specificities can range from the most general (generic) (eg, doors) to special locations such as loading dock # 3 in warehouse # 2. As described above and as described in more detail below in connection with FIG. 10, the event definition function 715 allows a user to define an event as a combination of one or more event components, and also attributes or Parameters can be associated with the event. The event / location display 720 allows the user to review defined locations and events in the system and the site to which the user is assigned.

  Referring to FIG. 8, an example of the application screen includes a template design user interface 800 for creating a standard floor layout diagram and a template. The user interface includes a site template 805, a template parameter selection area 810, and a template operation area 815. The template 805 is implemented as an interactive interface that allows the user to select, edit, add, delete, and move elements of the floor plan. In some embodiments, the elements are represented as application objects having attributes such as size and height, so that the user can relate to other objects (eg, in units, pixels, etc.) and In absolute items (for example, inches, feet, etc.), the relative size of the object can be specified. Template 805 may respond to “drag and drop” user / screen interactions based on keystrokes and / or commands entered using a pointing device such as a mouse or optical pen. it can. In embodiments where the user interface 800 is provided to the user via a browser application, the object can be represented as a flash-based window or an object in an AJAX applet. This means that most of the user-initiated commands for editing and moving the template object are processed on the client machine, and the client machine is the minimum to the server and from the server. Data transmission is required.

  Template parameter area 810 provides fields for entering and displaying parameters associated with the template. More specifically, the user selects the template type (eg, warehouse, retail, second floor, suburb, general, etc.), the date the template was created, and the site (s) to which the template is assigned. Can be specified. The template action area 815 provides operable objects (such as hyperlinks, control buttons, combo boxes, and the like). If the operable object is selected by the user, for example, assign the template to a particular site (or group of sites), publish the template (eg to a remote user), and Copy and start creating a new template.

  The user interface 800 also includes a library of template elements that can be used to create events, attribute elements to templates, or both. Specifically, the user interface 800 can include an object library 820, a location library 825, an action library 830, and an event library 840. Each library provides a list of each element available to the user, either for combining into an event (as described above) and / or to a position in the template. Each template library further provides the ability to add elements to the library as needed.

  The user can annotate the template with events and / or event components from the library by selecting the component and by dragging the component to a location on the template 805. For example, a user may wish to create a template having two fixed walls 845, a passage 850, a cashier counter 855, and an exhibit 860. In many cases, the floor plan represented in the template does not actually represent any particular site, but as a starting point for customization (as described further below in connection with FIGS. 12 and 13). Can be used by remote users.

  In some embodiments, the user interface 800 can also include a sensor library (not shown) that provides a list of available sensors in various sensor networks and video surveillance systems, so that the user can The location of generic (generic) sensors (eg, video cameras) and / or specific sensors (eg, camera # 321) can be added to the template. In the example where the template is defined by a central user, the template can be stored at the central site and “published” to the remote user upon completion.

  Referring to FIG. 9, an example application screen can be used to define locations in a location library and to annotate floor plans and / or create events. A location definition user interface 900 is included. User interface 900 includes fields 905 and 910. The user can enter a full name (eg, blue jeans table in front of the store) and a short name (blue jeans table) in fields 905 and 910, respectively. Location type text box 915 provides the user with a field that specifies the type of location that is defined (eg, table, door, counter, restroom, multi-storey parking, etc.). The description field 920 allows the user to enter a longer text description of the location. The text description may include, for example, location coordinates, location implementation instructions, and other related features at the location. Contact field 925 captures the attribute of the user creating the location, such as an email address, user name, employee number, or title. For example, depending on the user creating the location, the architectural embodiment of the system, or other system-based parameters, the submit button 930 may send the location and its attributes to the central storage module, Save to the remote storage module or both.

  Referring to FIG. 10, an example application screen includes an event definition user interface 1000 for defining events in the system (and for modifying once defined). As described above, composing an event from one or more event components, such as actions, locations, and objects, and parameters that further describe how and when the event is realized. it can. Typically, the predefined event user interface 1000 is used by a central user to provide site independent components of events, such as time parameters, general location, behavior, and the like. However, in some embodiments, a remote user can be given access to a predefined event function to create a new site-specific event. In some cases, a central administrator can grant or deny access to such functionality on a per user basis. The user interface 1000 includes an event name field 1005 for capturing aliases for events and for identifying (possibly unique) events within the data storage module (s). The location field 1010 provides a list of available locations that can be associated with the event. The parameter field 1015 provides the user with the ability to assign a date and / or time range for the event. For example, an event directed to detecting that a shopper stops at an exhibit and selects a product can be limited to the date and time the store is open.

  The action selection items 1020 and 1025 facilitate the definition of action-based components in the event. In a retail setting, for example, a shopper's actions around a particular exhibit, such as stopping at an exhibit, picking up an item, and placing it in a cart, are of interest. There is a possibility. However, accurately determining whether such an event has occurred may require time-based parameters to be attributed to certain actions. Specifically, an exhibit that is long enough (for example, longer than a few seconds) for a shopper to view the item using the “Stop Time” parameter to determine if the user has stopped at the exhibit. You can detect if you actually paused. Similarly, a long rest period tied to inactivity (eg, picking up a product) makes the exhibit attractive to shoppers, but the product is not of interest or improperly valued. There is a possibility that it is attached.

  Such an action will display the number of shoppers who pass by ignoring the exhibits (for example, shoppers who have no dead time, touched the product, but walked up to the exhibit). Comparison with the number of shoppers attracted to the item (e.g., shoppers who touched the item with a dwell time of more than a few seconds) can help determine the effectiveness of the exhibit. Additionally, these statistics can be compared to total sales based on, for example, POS data, and compared to the total number of shoppers entering the store. Detecting and counting a particular shopper's behavior when they occur at a particular location and comparing similar events across different different sites can make site-specific differences Effectively “standardize” events by focusing on actions that can be removed and directly attributed to shopper interactions with products.

  Referring to FIG. 11, an example application screen includes an event editing user interface 1100 for modifying an event and assigning site-specific elements to the event. In some embodiments, data previously entered (eg, by a central user) and displayed on the user interface 1100 to a remote user is read-only, while in some cases Now, certain elements (eg, name and time-based parameters) can be read-only and other data elements can be edited. In each case, the user interface 1100 also includes an assigned camera selection box 1105 and an assigned sensor selection box 1110. In an example where a remote user receives an instruction to implement an event at the user's site (or group of sites), the user makes a selection from available camera and / or sensor identifiers at the user's particular site. Can do. Allowing a remote user to review an event and select an appropriate sensor to detect the event improves, for example, the chance that a proper camera will record the event.

  Referring to FIG. 12, an example application screen includes a template editing user interface 1200 that allows a remote user to customize a store floor plan template provided by a central user. In addition to the functions and features of the template design user interface 800, the template editing user interface 1200 allows a user (either central or remote) to modify the template. As a result, the template better represents a specific site. The object library can include various video cameras 1210 and sensors 1215 that can be selected and placed at various locations for the floor plan (possibly identified by a unique ID). For example, a user can know that a particular camera is attached to a particular wall and is directed to a passageway, and therefore the user will place a camera at that location. Similarly, an RFID sensor or other similar EAS device can be placed at the store exit. In some examples, the template can include elements added by the central user (walls, passages, exhibits, etc.) that exist at the remote site but are not properly positioned. In such a case, the remote user can select the elements and change their placement with respect to the site floor plan. For example, a passage 1220 arranged perpendicular to a particular wall in the original template can be moved. As a result, the passage 1220 is parallel to the wall. Similarly, the product display 1220 can be moved. Thereby, the product display 1220 remains at the end of the newly arranged passage. The point-of-sale location 1430 (eg, a cashier counter) can also be moved to its appropriate location based on the actual floor plan of the site. In some cases, additional elements such as additional walls 1440 can be added to complete the floor plan. Once the site specific changes to the floor plan are complete, the floor plan is saved (in remote storage, central storage, or both) and used as a basis for monitoring the site. In some cases, the change is sent back to the central user for approval prior to implementation and / or for use as a future template.

  Referring to FIG. 13, an example application screen includes a floor plan mapping user interface 1300 for mapping elements of a standard floor plan to an actual floor plan at a remote site. Similar to the template editing user interface 1200, the floor plan mapping user interface 1300 allows a user to construct a site specific floor plan for embodiments within the monitoring system described above. However, the floor plan mapping user interface 1300 provides a visual representation of both the template 805 and the existing site floor plan 1305 so that the user can annotate and use the template with the site floor. The layout drawing 1305 can be operated. In some embodiments, an electronic representation of a floor plan for a remote site may be made available from another source, such as building-related drawings, building layouts, blueprints, and the like. And the user may wish to use these drawings as a starting point for site specific floor plans. For example, the user can indicate the location of the video camera and / or sensor 1310 on the site floor plan 1305, can select items from the template 805, and their true position is the site floor plan 1305. You can indicate above. Specifically, elements such as aisle 1315, POS device 1320, and merchandise display 1325 can be selected on template 805, dragged onto site floor plan 1305, and accurate location Can be arranged. In some examples, elements such as the inlet 1330 can be added to the floor plan 1305. In some cases, prior to allowing the user to implement a site floor plan for use in monitoring the site, the system will remove all items from template 805. The user is requested to “place” on the floor plan 1305. As a result, a complete and accurate site floor plan is incorporated into the system for use in detecting events of interest at the site without requiring the central user to have detailed knowledge of each remote site. Made available to each other to ensure that a certain minimum number of events are realized at each site.

  In addition to mapping standard floor plan elements to actual floor plan elements, actual floor plan elements can be mapped to standard floor plan elements, and therefore certain events are assigned. Elements of the standard floor plan can be directed to the central user. Such an approach not only uses standardized standard floor plans, but also uses data captured based on site-specific parameters to further facilitate site-to-site comparisons. For example, event data can be plotted against a standard floor plan to compare the total number of customers between multiple (eg, three or more) stores with different actual floor plans. As a result, the central user identifies the occurrence of events or products with exceptionally high reduction rates across multiple sites without having to first consider the floor plans of the different sites. be able to.

  For embodiments where the method is provided as one or more software programs, the program may be a number of high-level languages such as FORTRAN, PASCAL, JAVA, C, C ++, C #, BASIC, various script languages, and And / or in any one of HTML. Data can be transferred between various applications and storage modules using client / server techniques such as ODBC and direct data access, and via web services, using XML and AJAX technologies. Additionally, the software can be implemented in assembly language directed to a microprocessor residing on the target computer. For example, if the software is configured to run on an IBM PC or PC compatible machine, the software can be implemented in the Intel 80x86 assembly language. The software on products including (but not limited to) floppy disks, hard disks, optical disks, magnetic tapes, PROMs, EPROMs, EEPROMs, field programmable gate arrays, or CD-ROMs Can also be realized.

  Variations, modifications, and other embodiments of what is described herein will occur to those of ordinary skill in the art without departing from the principles and scope of the invention as claimed in the claims. Will. Accordingly, the invention is to be defined not by the preceding illustrative description but instead by the principles and scope of the following claims.

Claims (57)

A method for facilitating monitoring of different sites,
Providing a rule set representing at least one event of interest comprising at least one site-specific component and at least one site-independent component;
Defining the at least one site-independent component; and
Distributing the rule set to the different sites, thereby facilitating defining the at least one site-specific component at the different sites and monitoring according to the rules at each site Including the method.   The method of claim 1, wherein each of the site specific components comprises specifying at least one location in at least one of the plurality of different sites.   The method of claim 1, wherein each of the site independent components comprises specifying at least one action.   The method of claim 1, wherein each of the site independent components comprises specifying at least one object.   The method of claim 4, wherein each of the site-independent components comprises specifying a person that interacts with the at least one object.   The method of claim 1, wherein each of the site specific components comprises floor plan data.   The method of claim 1, wherein each of the site-specific components comprises sensor identification data.   The method according to claim 7, wherein the sensor identification data includes one or more of a video surveillance camera ID, an RFID sensor ID, an electronic merchandise surveillance sensor ID, and an adjacent card sensor ID.   The method of claim 1, further comprising receiving one or more alerts from the plurality of different sites, the alerts comprising an indication of one or more occurrences of the event of interest at each site. the method of.   The method of claim 9, further comprising aggregating the received alerts, thereby facilitating statistical analysis thereof.   The method of claim 10, wherein the aggregating comprises determining an average number of alerts received from the subset of the plurality of different sites during a predetermined time period.   The method of claim 9, further comprising analyzing the received alert to determine whether one or more of the site-specific components are suboptimal.   10. The method further comprising analyzing the alert to detect inconsistencies between the site specific components due to each of one or more of the plurality of different sites. The method described in 1.   14. The method of claim 13, further comprising modifying at least one of the site-specific components of the rule and delivering the modified rule to a site that has been found to be inconsistent. The method described.   The method of claim 9, further comprising communicating a second alert to the site based on the one or more received alerts.   The method of claim 15, wherein the received alert based on the second alert comprises being received from a site other than the site to which the second alert was communicated.   The site to which the second alert was communicated is determined based on an inferred relationship between the site to which the second alert was communicated and the site from which the alert was received The method of claim 16. Define the rules in terms of site-specific components,
Receiving monitoring data from the at least one site; and
One or more of the rules are applied to the monitoring data, thereby detecting the occurrence of one or more of the events of interest for the at least one of the sites. The method of claim 1, further comprising:   The method of claim 18, further comprising generating an alert for the at least one of the plurality of different sites based on the occurrence of one or more of the events of interest. .   20. The method of claim 19, further comprising aggregating the alerts, thereby facilitating statistical analysis of the alerts.   21. The method of claim 20, wherein the aggregating comprises determining an average number of alerts based on events that occurred in the plurality of different site subsets during a predetermined time period.   21. The method of claim 20, further comprising analyzing the aggregated alert to determine whether one or more of the site-specific components are suboptimal.   21. The method further comprising analyzing the alert to detect inconsistencies between the site specific components due to each of one or more of the plurality of different sites. The method described in 1.   The method of claim 1, further comprising defining the at least one site-specific component at the different sites associated.   25. The method of claim 24, further comprising communicating the at least one site specific component to a central site for approval. A system for facilitating monitoring of different sites,
A rule definition module for defining a rule set, each of which represents one or more events of interest, one or more site-specific components and one or more A rule-defining module, the rule set comprising:
A communication module for communicating one or more of the rules to one or more different sites, thereby defining the one or more site-specific components at the plurality of different sites And a transmission module for facilitating the system.   27. The system of claim 26, further comprising a web server for providing remote clients at the site access to the rule definition module.   28. The system of claim 27, wherein the web server is configured to restrict access provided to remote clients to define the site specific components.   27. The system of claim 26, wherein the communication module is configured to receive one or more alerts from the site, each alert indicating one or more occurrences of the event of interest.   27. The system of claim 26, further comprising an analysis module for aggregating the received alerts, thereby facilitating statistical analysis thereof.   32. The system of claim 30, wherein the analysis module is further configured to analyze the aggregated alert to determine whether one or more of the site-specific components are suboptimal. .   31. The analysis module of claim 30, wherein the analysis module further analyzes the aggregated alert to detect inconsistencies between the site specific components due to the one or more different sites. System.   35. The system of claim 32, wherein the rule definition module is further configured to modify the rule based on the detected inconsistency.   36. The system of claim 32, wherein the transmission module is further configured to communicate the modified rule to the remote site.   27. The system of claim 26, further comprising a data storage module for storing the rules.   36. The system of claim 35, wherein the data storage module further stores monitoring data received from the plurality of different sites. A method for monitoring different sites,
Providing a rule set representing at least one event of interest comprising at least one site-specific component and at least one site-independent component;
Defining the at least one site-independent component;
Delivering the rule set to the plurality of different sites;
Defining at least one site-specific component in one of the sites; and
Monitoring the one of the sites according to the rules. A product incorporating a computer readable program portion for monitoring activity at different sites,
Providing a rule set representing at least one event of interest comprising at least one site-specific component and at least one site-independent component;
Defining the at least one site-independent component; and
Distributing the rule set to the different sites, thereby facilitating defining the at least one site-specific component at the different sites and monitoring according to the rules at each site An article of manufacture comprising computer readable instructions for A method for monitoring a site,
Providing a standard site layout that specifies at least one common element located in multiple sites, each of the sites having an actual site layout;
Create an annotated standard site layout by assigning one or more events to one or more of the common elements independently of the actual site layout;
Facilitating modification of the annotated layout, matching the annotated layout to each of the actual site layouts; and
Monitoring each site according to a corresponding modified annotated layout of each site.   40. The method of claim 39, wherein the at least one element comprises a location at or within each of the plurality of sites.   40. The method of claim 39, wherein the events each comprise a site independent component and a site specific component.   42. The method of claim 41, wherein the site-independent component comprises specifying an interaction between a person and the at least one element.   42. The method of claim 41, wherein the site specific component comprises sensor identification data.   44. The method of claim 43, wherein the sensor identification data comprises one or more of a video surveillance camera ID, an RFID sensor ID, an electronic merchandise surveillance sensor ID, and an adjacent card sensor ID.   40. The method of claim 39, wherein the monitoring step comprises generating an alarm according to the occurrence of an event.   46. The method of claim 45, further comprising receiving at least one alert from at least one of the sites.   48. The method of claim 46, further comprising analyzing the at least one alert.   40. The method of claim 39, further comprising providing a downloadable applet to the at least one user to facilitate processing of the modification to the annotated standard layout.   49. The method of claim 48, wherein the downloadable applet comprises an asynchronous Java script applet.   50. The method of claim 49, wherein the applet comprises communicating with a remote data source using XML.   One of: deleting an element of the annotated standard site layout, changing a location associated with the element of the annotated standard site layout, and adding an element to the annotated standard site layout 40. The method of claim 39, wherein the modification comprises a modification. A system for monitoring a site,
A user interface,
A site layout template window frame for displaying a standard site layout including at least one site-independent element;
A user interface comprising a site specific window frame for displaying the actual site layout of the monitored site;
A system comprising a modification module for facilitating association of site-specific elements of the actual site layout with at least one site-independent element.   53. The system of claim 52, wherein the modification module includes an asynchronous Java script applet.   53. The system of claim 52, further comprising a web server for providing the applet to a user and for processing data requests from the applet.   55. The system of claim 54, further comprising a data storage module that communicates with the web server to fulfill a data request sent to the web server via the modification module. A system for monitoring a site, the method comprising:
Means for providing a standard site layout designating at least one common element located in a plurality of sites, each of the sites having an actual site layout;
Means for creating an annotated standard site layout by assigning one or more events to one or more of the common elements independent of the actual site layout;
Means for facilitating modification of the annotated layout to match the annotated layout to each of the actual site layouts;
And means for monitoring each site according to a corresponding modified annotated layout for each site. A product incorporating a computer-readable program portion for monitoring a site,
Providing a standard site layout that specifies at least one common element located in multiple sites, each of the sites having an actual site layout;
Create an annotated standard site layout by assigning one or more events to one or more of the common elements independently of the actual site layout;
Facilitating modification of the annotated layout, matching the annotated layout to each of the actual site layouts; and
A product comprising computer readable instructions for monitoring each site according to a corresponding modified annotated layout for each site.

Images