Loading...
Please wait, while we are loading the content...
Similar Documents
Scalable Framework for Monitoring Machine-to-machine (m2m) Devices
| Content Provider | The Lens |
|---|---|
| Abstract | A device receives information associated with machine-to-machine (M2M) devices connected to a host server device via a network. The information associated with the M2M devices include one or more of device information associated with components of the M2M devices, application information generated by the M2M devices, or network information associated with interactions of the M2M devices, with the network, when the M2M devices provide the application information to the host server device via the network. The device performs an analysis of the information associated with the M2M devices via one or more analytics techniques, and generates analysis information based on the analysis of the information associated with the M2M devices. The device provides the analysis information for display by the host server device. |
| Related Links | https://www.lens.org/images/patent/164-831-785-448-133/pdf/US_2015_A1_20150271033_164-831-785-448-133.pdf |
| Language | English |
| Publisher Date | 2017-10-31 |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Patent |
| Jurisdiction | United States of America |
| Date Applied | 2014-03-20 |
| Applicant | Verizon Patent & Licensing Inc |
| Application No. | 201414220300 |
| Claim | A method, comprising: receiving, by a device, information associated with a first set of machine-to-machine (M2M) devices connected to a host server device via a network, the device being different from the host server device, and the information associated with the first set of M2M devices including one or more of: device information associated with components of the first set of M2M devices, or application information generated by the first set of M2M devices; determining, by the device, normal behavior patterns, associated with the first set of M2M devices, over time; performing, by the device, a first analysis of the information associated with the first set of M2M devices via one or more analytics techniques, the first analysis, of the information associated with the first set of M2M devices, including: a comparison of the information associated with the first set of M2M devices and the normal behavior patterns, and anomaly detection to identify one or more of an item, an event, or an observation that does not conform to the normal behavior patterns based on the comparison, and the first analysis, of the information associated with the first set of M2M devices, being performed in at least one of: near real time, real time, or batch time; generating, by the device, analysis information based on the first analysis of the information associated with the first set of M2M devices, the analysis information including a comparison of the first analysis, of the information associated with the first set of M2M devices, and a second analysis of information associated with a second set of M2M devices, the first set of M2M devices being different from the second set of M2M devices; generating, by the device, a dashboard user interface that includes the analysis information and anomaly information; and providing, by the device and for display, the dashboard user interface to the host server device. The method of claim 1 , further comprising: providing one or more notifications associated with the analysis information to one or more other devices associated with the host server device. The method of claim 2 , where the one or more notifications include information associated with one or more M2M devices, of the first set of M2M devices, identified as being anomalous based on the first analysis of the information associated with the first set of M2M devices. The method of claim 1 , where the one or more analytics techniques include one or more of: an anomaly detection technique to identify one or more anomalous M2M devices, of the first set of M2M devices, based on the information associated with the first set of M2M devices, a trending technique to identify one or more trends for the first set of M2M devices based on the information associated with the first set of M2M devices, a prediction technique to predict one or more behaviors of the first set of M2M devices based on the information associated with the first set of M2M devices, or a segmentation technique to group one or more M2M devices, of the first set of M2M devices, into groups, based on the information associated with the first set of M2M devices. The method of claim 1 , where the analysis information includes one or more of: information associated with one or more anomalies identified in the device information or the application information, information associated with one or more trends identified in the device information or the application information, information associated with one or more comparisons of the device information or the application information, associated with the first set of M2M devices, and device information or application information associated with other M2M devices, or information associated with one or more predictions determined based on the device information or the application information. The method of claim 1 , further comprising: customizing the dashboard user interface for a particular user by including analysis information and anomaly information for one or more M2M devices, of the first set of M2M devices, associated with the particular user. The method of claim 1 , where the analysis information includes one or more of: information associated with a data usage level of one or more of the M2M devices of the first set of M2M devices, information associated with a total session number for one or more of the M2M devices of the first set of M2M devices, or information associated with a number of bad disks being utilized by one or more of the M2M devices of the first set of M2M devices. A device, comprising: one or more processors, at least partially implemented in hardware, to: receive information associated with a first set of machine-to-machine (M2M) devices connected to a host server device via a network, the device being different from the host server device, and the information associated with the first set of M2M devices including one or more of: device information associated with components of the first set of M2M devices, or application information generated by the first set of M2M devices; determine normal behavior patterns, associated with the first set of M2M devices, over time; perform a first analysis of the information associated with the first set of M2M devices via one or more analytics techniques, the first analysis, of the information associated with the first set of M2M devices, including: a comparison of the information associated with the first set of M2M devices and the normal behavior patterns, and anomaly detection to identify one or more of an item, an event, or an observation that does not conform to the normal behavior patterns based on the comparison, and the first analysis, of the information associated with the first set of M2M devices, being performed in at least one of: near real time, real time, or batch time; generate analysis information based on the first analysis of the information associated with the first set of M2M devices, the analysis information including a comparison of the first analysis, of the information associated with the first set of M2M devices, and a second analysis of information associated with a second set of M2M devices, the first set of M2M devices being different from the second set of M2M devices; generate a dashboard user interface that includes the analysis information and anomaly information; store the analysis information; and provide, for display, the dashboard user interface to the host server device. The device of claim 8 , where the one or more processors are further to: provide at least one notification associated with the analysis information to at least one other device, associated with the host server device, via an email message, a text message, or a voicemail message. The device of claim 9 , where the at least one notification includes information associated with one or more M2M devices, of the first set of M2M devices, identified as being anomalous based on the first analysis of the information associated with the first set of M2M devices. The device of claim 8 , where the one or more analytics techniques include one or more of: an anomaly detection technique to identify one or more anomalous M2M devices, of the first set of M2M devices, based on the information associated with the first set of M2M devices, a trending technique to identify one or more trends for the first set of M2M devices based on the information associated with the first set of M2M devices, a prediction technique to predict one or more behaviors of the first set of M2M devices based on the information associated with the plurality first set of M2M devices, or a segmentation technique to group one or more M2M devices, of the first set of M2M devices, into groups, based on the information associated with the first set of M2M devices. The device of claim 8 , where the analysis information includes one or more of: information associated with one or more anomalies identified in the device information or the application information, information associated with one or more trends identified in the device information or the application information, information associated with one or more comparisons of the device information or the application information, associated with the first set of M2M devices, and device information or application information associated with other M2M devices, or information associated with one or more predictions determined based on the device information or the application information. The device of claim 8 , where the one or more processors are further to: customize the dashboard user interface for a particular entity, the customized dashboard user interface including: the analysis information, and anomaly information for the first set of M2M devices associated with the particular entity. The device of claim 8 , where the analysis information includes one or more of: information associated with a data usage level of one or more of the first set of M2M devices, information associated with a total session number for one or more of the first set of M2M devices, or information associated with a number of bad disks being utilized by one or more of the first set of M2M devices. A computer-readable medium for storing instructions, the instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the one or more processors to: receive information associated with a first set of machine-to-machine (M2M) devices connected to a host server device via a network, the device being different from the host server device, and the information associated with the first set of M2M devices including one or more of: device information associated with hardware components of the first set of M2M devices, or application information generated by the first set of M2M devices; determine one or more normal behavior patterns, associated with the first set of M2M devices, over time; perform a first analysis of the information associated with the first set of M2M devices via one or more analytics techniques, the first analysis, of the information associated with the first set of M2M devices, including: a comparison of the information associated with the first set of M2M devices and the one or more normal behavior patterns, and anomaly detection to identify one or more of an item, an event, or an observation that does not conform to the one or more normal behavior patterns based on the comparison, and the first analysis, of the information associated with the first set of M2M devices, being performed in at least one of: near real time, real time, or batch time; generate analysis information based on the first analysis of the information associated with the first set of M2M devices, the analysis information including a comparison of the first analysis, of the information associated with the first set of M2M devices, and a second analysis of information associated with a second set of M2M devices, the first set of M2M devices being different from the second set of M2M devices; generate a dashboard user interface that includes the analysis information and anomaly information; and provide, for display, the dashboard user interface to the host server device. The computer-readable medium of claim 15 , where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to: provide one or more notifications associated with the analysis information to one or more other devices associated with the host server device. The computer-readable medium of claim 16 , where the one or more notifications include: information associated with one or more M2M devices, of the first set of M2M devices, identified as being anomalous based on the first analysis of the information associated with the first set of M2M devices. The computer-readable medium of claim 15 , where the one or more analytics techniques include one or more of: an anomaly detection technique to identify one or more anomalous M2M devices, of the first set of M2M devices, based on the information associated with the first set of M2M devices, a trending technique to identify one or more trends for the first set of M2M devices based on the information associated with the first set of M2M devices, a prediction technique to predict one or more behaviors of the first set of M2M devices based on the information associated with the first set of M2M devices, or a segmentation technique to group one or more M2M devices, of the first set of M2M devices, into groups, based on the information associated with the first set of M2M devices. The computer-readable medium of claim 15 , where the analysis information includes one or more of: information associated with one or more anomalies identified in the device information or the application information, information associated with one or more trends identified in the device information or the application information, information associated with one or more comparisons of the device information or the application information, associated with the first set of M2M devices, and device information or application information associated with other M2M devices, or information associated with one or more predictions determined based on the device information or the application information. The computer-readable medium of claim 15 , where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to: determine a particular usage pattern or a particular connectivity pattern of a particular M2M device of the first set of M2M devices; compare the information associated with the first set of M2M devices and the particular usage pattern or the particular connectivity pattern; and determine that the particular M2M device is anomalous based on comparing the information associated with the first set of M2M devices and the particular usage pattern or the particular connectivity pattern. |
| CPC Classification | TRANSMISSION OF DIGITAL INFORMATION; e.g. TELEGRAPHIC COMMUNICATION |
| Examiner | Lan-dai T Truong |
| Extended Family | 164-831-785-448-133 145-527-587-393-025 |
| Patent ID | 9806902 |
| Inventor/Author | Srivastava Ashok N Pamarthy Kalyan Das Santanu Chen Yunzhu Le An Sun Xuepeng |
| IPC | G06F15/173 H04L12/28 |
| Status | Active |
| Owner | Verizon Patent and Licensing Inc |
| Simple Family | 164-831-785-448-133 145-527-587-393-025 |
| CPC (with Group) | H04L12/2825 |
| Issuing Authority | United States Patent and Trademark Office (USPTO) |
| Kind | Patent/New European patent specification (amended specification after opposition procedure) |
