Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
This office action is in response to the application filed on 03/24/2025. Claims 1-14, 19-20 are pending in this application. Claims 1,19 are independent claims.
Election/Restrictions
Applicant's election with traverse of Species I and Sub-species k in the reply filed on 07/23/2006 is acknowledged. The traversal is on the ground(s) that Species III is the system counterpart to the method Species I and there is no serious burden on the Examiner to search these claims together. This is found persuasive because the examiner does agree that Species I and Species III are related so Species I and III will be modified into a single Species.
Applicant further traverse on the ground(s) that there is no serious burden on the Examiner to search various Sub-species (a-k) together. This is also found persuasive because the Examiner agrees that with additional variation of searches can cover the Sub-species so Sub-Species (a-k) will be modified into a single Sub-species.
Claims 1-14 and 19-20 are examined in this office action.
The restriction is made FINAL.
Claim Objections
Claim 8 objected to because of the following informalities: Claim 8 recites “(I) directly interacting” should read “(i) directly interacting”. Appropriate correction is required.
Claim 8 objected to because of the following informalities: Claim 8 recites “the traffic information data types” should read “the traffic information data type” to match the singular term introduced in claim 7. Appropriate correction is required.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-5, 7, 9-10, 12-13 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lutu et al. (NPL: 27 July 2020, arXiv:2007.13708v1 [cs.NI] - “Where Things Roam – Uncovering Cellular IoT/M2M Connectivity ).
Regarding claim 1, Lutu teaches a method for processing multiple types of inputs to remotely determine mobile device type (Pg. 7, 4.3. M2M Device Classification, Col. 2, lines 8-11:” To do so we require to split the devices into three classes: smart (for smartphones), feat (for feature phones), and m2m (for IoT/M2M devices)” e.g., Lutu teaches sorting every device on the operator’s network into a device type using only network data. That is processing multiple inputs to remotely determine mobile device type.), comprising:
receiving, in conjunction with a radio access network (RAN) associated with a packet core (Fig 4 – Radio Access Network; Pg. 6, [4.1], MNO dataset, Col. 2, lines 3-12: “Such a network can be simplified to consist of three main domains:” (i) the cellular device (in our case, the smart meter, (ii) the Radio Access Network (RAN) and (iii) the Core Network (CN). Our passive measurement approach relies on commercial solutions integrated within the MNO’s infrastructure. The red pins in Fig. 4 mark the network elements that we monitor, namely the Mobility Management Entity (MME), the Message Sequence Chart (MSC) and the Serving GRPS Support Node (SGSN).” e.g., Lutu’s data comes from an operator network make up of a RAN and a core network, and the MME and SGSN it monitors are packet-core elements. The data is therefore received I conjunction with a RAN associated with a packet core) ,
to which a remote mobile device is currently and/or was previously attached (Pg. 6, 4.1 MNO dataset, Col. 2, lines 12-13: “We collect control plane data on the total population of devices connected to the MNO’s radio network. “ e.g., The data covers every device connected to connected to the operator’s radio network. Each device is a remote mobile device currently attached to the RAN),
at least two types of data sets associated with the remote mobile device (Pg. 7, 4.1 Radio Interfaces., Col. 1, lines 1-4 :”Radio interfaces. We process logs reporting on activities on IuCS, IuPS, A, and Gb radio interfaces. Those carry events generated by the devices connecting to the radio sectors, and requesting resources for either data or voice communications.”; Pg. 7, 4.1, Service usage, Col. 1, lines 1-5:”We use Call Detail Records (CRDs) and eXtended Detail Records (xDRs) to provide aggregate service usage for calls and data. Each record reports the anonymized user ID, MCC, and MNC codes for both device SIM and visited country, timestamp, duration, and bytes consumed.” E.g., the radio interface event logs and the CDR/xDR usage records are two different types of datasets. Both are tied to the same device through its anonymized user ID.)
in which each of the data sets received comprises a respective type of information operative to provide at least one respective type of clue regarding a type of mobile device best describing said remote mobile device(Pg.7, 4.1, Radio interfaces, Col. 1, lines 5-7 : “Each event carries the anonymized user D, SIM MCC and MNC, Type Allocation Code, the sector ID handling the communication, timestamp, event type, event result code. “; Pg. 7, 4.1, Device properties, Col. 1, lines 2-4 “This catalog maps the device TAC to a set of device properties such as device manufacturer, brand and model name, operating system, and radio bands supported.”; Pg.8 , Col. 1, lines 22-24:” APNs string can be a significant aid for strengthening the confidence of the classification as they hint the vertical used by a device.” E.g., The TAC in each radio event maps to the device’s manufacturer, model and operating system, and the APN strings in the data records hint at the device’s vertical. They are therefore supplying their own kind of clue about the device type.)
processing, using at least one data processing technique, the at least two types of data sets, thereby generating an output data set (Pg. 7, 4.1, Daily devices-catalog, Col. 1, lines 1-3: “We combine the three data sources to create a daily list of active devices and associated properties and traffic characteristics. “; Pg. 7, 4.1, Daily devices-catalog, Col. 1, lines 4-8:“Each record in the generated catalog reports a device ID, total number of events, calls, bytes seen, SIM MCC/MNC, list of visited MCC-MNC, list of APN strings, device manufacturer, device model, device Operating System (OS)” e.g., combining the three sources into one record per device is processing the datasets with a data processing technique. The result catalog is the output dataset.);
and determining, using at least said output data set, the type of mobile device best describing said remote mobile device (Pg. 8, 4.3, Col. 1, lines 39-43 :” Finally, we classify the devices combining both APNs and device properties. We start marking as m2m all devices using the validated APNs. Then, we extend the m2m class to all devices having the same properties of the devices using the validated APNs.” E.g., Lutu teaches assigning each device in the catalog to the smart, feat or m2m class from the combined APN and device property data. i.e., determining the device type from the output dataset.);
whereby, as a direct result of said processing, the determination is more accurate and/or more consistent than any similar determination using only one of the at least two types of data sets as an input (Examiner notes the whereby clause states a result and carry no weight ( MPEP 2111.04); Pg. 8, 4.3, Col. 2, lines 12-17: “Differently from (18), using APNs is useful to increase the classification confidence, and reduce the amount of manual investigations. However, when used in isolation, APNs are not enough as we find about 21% of the devices in the dataset not having any APN. This justifies our multi-steps classification process (keywords→APNs→device properties).” E.g., Lutu teaches combining data because APNs alone are not enough).
Regarding claim 2, Lutu teaches wherein the mobile device type comprises at least one of: (i) smartphones, (ii) tablets, (iii) feature phones, (iv) Internet of Things (IoT) devices, (v) personal computers and/or laptops, (vi) notebooks, (vii) wearables, and (viii) any other portable and/or non-portable electronic device capable of wireless communication and network connectivity to the RAN and/or packet core (Pg. 7, 4.3. M2M Device Classification, Col. 2, lines 8-11 :” To do so we require to split the devices into three classes: smart (for smartphones), feat (for feature phones), and m2m (for IoT/M2M devices)” ).
Regarding claim 3, Lutu teaches The method of claim 1, wherein said determining of the type of mobile device best describing said remote mobile device comprises identifying at least one manufacturer associated with the remote mobile device (Pg. 7, Device properties, Col. 1, lines 2-4 :“This catalog maps the device TAC to a set of device properties such as device manufacturer, brand and model name, operating system, and radio bands supported.”; Pg.7, Daily devices-catalog, Col. 1, lines 4-8 :”Each record in the generated catalog reports a device ID, total number of events, calls, bytes seen, SIM MCC/MNC, list of visited MCC-MNC, list of APN strings, device manufacturer, device model, device Operating System (OS).”; Pg. 9, Col. 1, lines 10-13:” To further validate our inference, we use the GSMA (GSMA) TAC data catalog to identify the manufacturers of these devices.“ e.g., Each catalog record reports the device manufacturer looked up from the TAC. Lutu’s determination therefore identifies the manufacturer.).
Regarding claim 4, Lutu teaches wherein said determining of the type of mobile device best describing said remote mobile device comprises identifying a specific model to which the remote mobile device belongs(Pg. 7, Device properties, Col. 1, lines 2-4 :“This catalog maps the device TAC to a set of device properties such as device manufacturer, brand and model name, operating system, and radio bands supported.”; Pg. 7, Daily devices-catalog, Col. 1, lines 4-8:”Each record in the generated catalog reports a device ID, total number of events, calls, bytes seen, SIM MCC/MNC, list of visited MCC-MNC, list of APN strings, device manufacturer, device model, device Operating System (OS).” E.g., each catalog record also reports the device model looked up from the TAC. Lutu’s determination therefore identifies the specific model).
Regarding claim 5, Lutu teaches wherein the at least two types of data sets comprise at least one of: (i) traffic information collected from the Radio Access Network (RAN) and the packet core, (ii) control information collected from the Radio Access Network (RAN) and the packet core (Pg. 6, 4.1 MNO dataset, Col. 2, lines 6-13:” Our passive measurement approach relies on commercial solutions integrated within the MNO’s infrastructure. The red pins in Fig. 4 mark the network elements that we monitor, namely the Mobility Management Entity (MME), the Message Sequence Chart (MSC) and the Serving GPRS Support Node (SGSN). We collect control plane data on the total population of devices connected to the MNO’s radio network.“; Pg. 7, 4.1:”Radio interfaces., Col. 1, lines 1-4:” We process logs reporting on activities on IuCS, IuPS, A, and Gb radio interfaces. Those carry events generated by the devices connecting to the radio sectors, and requesting resources for either data or voice communications.” E.g., The radio interface logs are control plane data captured at the MME, MSC and SGSN and on the interfaces between the radio network and the core. They are control information collected from the RAN and the packet core.),
(iii) device identifiers, (iv) network protocol usage patterns, (v) location data, (vi) sensor data, (vii) battery usage patterns, (viii) communication patterns, and (ix) application usage statistics (Pg. 7, Radio interfaces, Col. 1, lines 5-7: “Each event carries the anonymized user D, SIM MCC and MNC, Type Allocation Code, the sector ID handling the communication, timestamp, event type, event result code.“ e.g., each event contains the device’s anonymized user ID and its TAC. They are device identifiers).
Regarding claim 7, Lutu teaches wherein one of the types of data sets is associated with a traffic information data type comprising at least one of the following types of data related to communication activities of mobile devices: (i) packet payloads, (ii) IP addresses, (iii) ports (), (iv) data volume statistics, (v) application-specific data patterns, and (vi) any other information related to content and/or characteristics of data transmissions over a network (Pg. 7, 4.1, Col. 1, lines 1-5: “Service usage. We use Call Detail Records (CRDs) and eXtended Detail Records (xDRs) to provide aggregate service usage for calls and data. Each record reports the anonymized user ID, MCC, and MNC codes for both device SIM and visited country, timestamp, duration, and bytes consumed.” E.g., bytes consumed in each usage record are data volume statistics; Pg. 7, Service usage, Col. 1, lines 5-7:” Data records also report APN strings, which usually encode information about the specific service/business they relate to” e.g., Specific service is application specific data patterns.).
Regarding claim 9, Lutu teaches wherein one of the types of data sets is associated with a control information data type comprising at least one of the following types of data related to management and/or control of mobile network operations: (i) radio resource control (RRC) messages, (ii) mobility management messages, (iii) quality of service (QoS) parameters, (iv) handover signaling, and (v) any other signaling messages (Pg. 11, 7.1 “background traffic”) and/or metadata used for network management and/or device authentication and/or resource allocation ( Pg. 11, 7.1, SMIP Device Activity, Col. 2, lines 1-4:” We measure SMIP signaling activity looking at the patterns of Attach, Routing Area Update, and Detach signaling procedures that we capture from the passive monitoring of MSC and MME elements (see Figure 4)” e.g., Attach, Routing Area Update, and Detach signaling procedures are mobility management procedures.; Pg. 7, Radio interfaces., Col. 1, lines 1-4 :” We process logs reporting on activities on IuCS, IuPS, A, and Gb radio interfaces. Those carry events generated by the devices connecting to the radio sectors, and requesting resources for either data or voice communications.” E.g., requesting resources for data or voice are signaling messages used for resource allocation.).
Regarding claim 10, Lutu teaches wherein in conjunction with said receiving, the control information data types are obtained from internal sources within the RAN and/or the packet core of mobile network infrastructure ( Pg. 6, 4.1 MNO dataset, Col. 2, lines 3-12: “Such a network can be simplified to consist of three main domains:” (i) the cellular device (in our case, the smart meter, (ii) the Radio Access Network (RAN) and (iii) the Core Network (CN). Our passive measurement approach relies on commercial solutions integrated within the MNO’s infrastructure. The red pins in Fig. 4 mark the network elements that we monitor, namely the Mobility Management Entity (MME), the Message Sequence Chart (MSC) and the Serving GPRS Support Node (SGSN).” E.g., MME, MSC and SGSN are internal resources within packet core.), in which the method further comprising:
establishing communication with the RAN associated with the packet core (Fig. 4; Pg. 7, Col. 1, lines 1-4:”Radio interfaces. We process logs reporting on activities on IuCS, IuPS, A, and Gb radio interfaces. Those carry events generated by the devices connecting to the radio sectors, and requesting resources for either data or voice communications.” e.g., Fig. 6 shows the monitored A, Gb, Iu-CS, Iu-PS and SI interfaces between the RAN and the core network, monitoring those interfaces is established communication with the RAN associated with the packet core);
accessing internal sources within the RAN and/or packet core to obtain traffic control-related data types (Pg. 11, 7.1 SMIP Device Activity, Col. 2, lines 1-4:” We measure SMIP signaling activity looking at the patterns of Attach, Routing Area Update, and Detach signaling procedures that we capture from the passive monitoring of MSC and MME elements (see Figure 4)” e.g., Capturing signaling at the MSC and MME which is understood to be reading of traffic control related data types) ;
and collecting traffic information from communication activities of the mobile device through the established communication with the RAN (Pg. 7, 4.1, Col. 1, lines 1-4:”Radio interfaces. We process logs reporting on activities on IuCS, IuPS, A, and Gb radio interfaces. Those carry events generated by the devices connecting to the radio sectors, and requesting resources for either data or voice communications.” E.g., the radio interface events record devices requesting resources for data communications. i.e., traffic information collected through the monitor network).
Regarding claim 12, Lutu teaches wherein the processing of data set types related to control/traffic and data sets related to device identity comprises correlating the usage patterns and/or network behaviors derived from control and/or traffic data with unique identifiers associated with each device (Pg. 7, Daily devices-catalog, Col. 1, lines 4-8.” Each record in the generated catalog reports a device ID, total number of events, calls, bytes seen, SIM MCC/MNC, list of visited MCC-MNC, list of APN strings, device manufacturer, device model, device Operating System (OS)”; Pg. 7, Daily devices-catalog, Col. 1, lines 11-14:” Finally, we compute mobility metrics for each device. Specifically, from radio logs, we compute the time spent on each individual sector to which a device connected.”; Pg. 8, Col. 1, lines 39-44 :” Finally, we classify the devices combining both APNs and device properties. We start marking as m2m all devices using the validated APNs. Then, we extend the m2m class to all devices having the same properties of the devices using the validated APNs.” E.g., Each catalog record ties the device’s traffic data (bytes, APNs ) and its radio log mobility metric to one device ID, and the classification combines those values with the TAC derived properties. Therefore, correlating behaviors derived from control and traffic data with a unique device identifier. ),
thereby enhancing accuracy of distinguishing between device types based on their distinctive behavioral characteristics and/or device attributes (Examiner notes the whereby clause states a result and carry no weight ( MPEP 2111.04); Pg. 8, Col. 2, lines 12-17 “Differently from (18), using APNs is useful to increase the classification confidence, and reduce the amount of manual investigations. However, when used in isolation, APNs are not enough as we find about 21% of the devices in the dataset not having any APN. This justifies our multi-steps classification process (keywords→APNs→device properties).” E.g., Lutu teaches combining data increases classification confidence ).
Regarding claim 13, Lutu teaches The method of claim 1, wherein the processing of the at least two types of data sets using at least one data processing technique involves employing algorithms comprising at least one of: (i) machine learning algorithms, (ii) statistical analysis methods, (iii) pattern recognition techniques, and (iv) data fusion approaches (Pg. 7, Daily devices-catalog, Col. 1, lines 1-3: “We combine the three data sources to create a daily list of active devices and associated properties and traffic characteristics.“ e.g., combining the three data sources into per device catalog is data fusion approach).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Lutu et al (NPL: 27 July 2020, arXiv:2007.13708v1 [cs.NI] - “Where Things Roam – Uncovering Cellular IoT/M2M Connectivity) in view of Casati (US 20220351762 A1)
Regarding claim 6, Lutu teaches The method of claim 1, wherein one of the types of data sets is associated with a device identity/identifiers data type (Pg.7, 4.1, Radio interfaces, Col. 1, lines 5-7 : “Each event carries the anonymized user D, SIM MCC and MNC, Type Allocation Code, the sector ID handling the communication, timestamp, event type, event result code. “) comprising at least one of the following unique identifiers (Lutu, Pg. 7, n.2 “The first 8 digits of the device IMEI, which are statically allocated to the device vendors.” ) :
Lutu teaches uses only the TAC portion of the IMEI which is shared by all devices of a model. It does not use a unique identifier such as a full IMEI or IMSI.
Casati teaches wherein one of the types of data sets is associated with a device identity/identifiers data type comprising at least one of the following unique identifiers w(i) international mobile equipment identity (IMEI) numbers, (ii) international mobile subscriber Identity (IMSI) numbers, (iii) media access control (MAC) addresses, and (iv) any other persistent and globally unique identifiers used for device identification in mobile networks (Pg. 9, [0076]: lines 1-7:” After the RACS-capable network receives the registration request from the user equipment, the RACS-capable network, for example by using means such as the processor 12, obtains an international mobile equipment identity (IMEI) or permanent equipment identifier (PEI) of the user equipment and extracting a type allocation code (TAC) from the IMEI or the PEI as shown in block 610.” E.g., obtaining the device full IMEI when the device registers through the RAN. )
Lutu and Casati are considered analogous to the claimed invention because they are both direct to remote device identification and classification. Therefore, It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the teaching of Casasti to capture IMEI information in order to distinguish individual devices that share a TAC to identify the specific device.
Claim 8, 11, 14, 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Lutu et al (NPL: 27 July 2020, arXiv:2007.13708v1 [cs.NI] - “Where Things Roam – Uncovering Cellular IoT/M2M Connectivity ) in view of Kohout et al. (US 10749770 B2)
Regarding claim 8, Lutu teaches The method of claim 7 (see claim 7 rejection above),
Lutu teaches wherein in conjunction with said receiving, obtaining the traffic information data types comprises at least one of: (I) directly interacting with the mobile device through network communication protocols, (ii) application programming interfacing (APIs) (Lutu, Pg. 7, 4.1, Service usage, Col. 1, lines 1-5:”We use Call Detail Records (CRDs) and eXtended Detail Records (xDRs) to provide aggregate service usage for calls and data. Each record reports the anonymized user ID, MCC, and MNC codes for both device SIM and visited country, timestamp, duration, and bytes consumed.” E.g., Per device usage records are traffic information obtained in conjunction with the receiving),
Lutu does not expressly teach and (iii) utilizing other communication channels operative to collect traffic-related information, including at least one of packet payloads, IP addresses, ports, data volume statistics, and application-specific data patterns, without requiring internal access to the RAN or packet core infrastructure.
Kohout teaches and (iii) utilizing other communication channels operative to collect traffic-related information, including at least one of packet payloads, IP addresses, ports, data volume statistics, and application-specific data patterns, without requiring internal access to the RAN or packet core infrastructure ( Kohout, Col. 7, 60-66:“The system works in a passive way and can consume relatively lightweight traces of network traffic, such as IPFIX records, NetFlow records, web proxy logs, or the like. In particular, the system is able to infer the device type of a device on the network based on its observed traffic, without requiring the system to scan the device or the device to provide any additional self-identification data.” E.g., traffic information from NetFlow, IPFIX and proxy log records are communication channels without direct interaction with the device; Col. 7, 13-17:” For example, router CE-2 may capture the source address and/or port of host node 10, the destination address and/or port of server 154, the protocol(s) used by packet 302, the hostname of server 154, and/or other header information by analyzing the header of a packet 302.“ e.g., hostname and port are IP address and ports,; Fig. 1B, Col. 7, 6-9:“For example, as shown, consider the case of edge router CE-2 through which the traffic between node 10 and server 154 flows.” E.g., data captured at an edge router with no access to radio or core network);
Lutu and Kohout are considered analogous to the claimed invention because they are both direct toward remote device classification. Therefore, It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the teaching of Kohout to capture traffic information outside the core network in order to classify devices from lightweight, passively collected traffic records.
Regarding claim 11, Lutu teaches The method of claim 1, wherein the processing of the data set types related to control and data sets related to traffic involves analyzing a correlation between control information comprising mobility management messages and/or quality of service parameters (Lutu, Pg. 11, 7.1, SMIP Device Activity, Col. 2, lines 1-4:” We measure SMIP signaling activity looking at the patterns of Attach, Routing Area Update, and Detach signaling procedures that we capture from the passive monitoring of MSC and MME elements (see Figure 4)” e.g., Lutu captures mobility management signaling ( Attach, Routing Area Update, Detach) as its control information.),
and traffic information comprising packet payloads and/or IP addresses (Lutu, Pg. 7, 4.1, Service usage, Col. 1, lines 1-5:”We use Call Detail Records (CRDs) and eXtended Detail Records (xDRs) to provide aggregate service usage for calls and data. Each record reports the anonymized user ID, MCC, and MNC codes for both device SIM and visited country, timestamp, duration, and bytes consumed.” Lutu’s traffic information is bytes and APN strings, not payloads or IP addresses.),
to differentiate between device types based on their distinctive usage patterns and/or network behaviors ( Lutu, Pg. 12 7.2, lines 5-10:”In Figure 12 our analysis shows that connected cars are very similar to normal inbound roaming smartphones, with high mobility patterns (left) large volume of signaling traffic (center) and data traffic (right). At the same time, smart energy meters are stationary IoT devices demonstrate a completely different behavior”. E.g., Lutu teaches differentiating connected cars apart form smart meters by comparing their signaling, mobility and data-traffic patterns together i.e., analyzing control and traffic information jointly to differentiate device types by their behavior.)
Lutu does not teach traffic information include packet payloads or IP addresses.
Kohout teaches traffic information include packet payloads or IP addresses (Kohout, col. 8, lines 49-54:” Example features from the traffic telemetry data may include, but are not limited to, the contacted server hostname, the server IP, the server IP+server port, ApplicationID (as parsed by firewalls), User-Agent string (for web access logs), process hash, etc. that was used by the monitored device.”; Kohout, Col. 7, 13-17:” For example, router CE-2 may capture the source address and/or port of host node 10, the destination address and/or port of server 154, the protocol(s) used by packet 302, the hostname of server 154, and/or other header information by analyzing the header of a packet 302.”; Kohout, Col. 7, 30-32:” For example, router CE-2 or another device may perform deep packet inspection (DPI) on one or more of packets 302, to assess the contents of the packet.” E.g., Kohout collects IP addresses, host name and contents of the packets i.e., payloads.).
Lutu and Kohout are considered analogous to the claimed invention because they are both direct toward remote device classification. Therefore, It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the teaching of Kohout to include IP-address feature in Lutu’s traffic data in order to distinguish device types by the endpoints they contact as Kohout explains in Col. 7, lines 28-32: “In some aspect, the device identification may be based on the frequencies of the observed traffic features, such as visit domains, applications used by the device, etc.”.
Regarding claim 14, Lutu teaches the method of claim 1 but does not teach wherein the processing of the data sets received utilizes a machine learning model trained on previously acquired data sets, wherein the machine learning model is associated with at least one of: (i) supervised learning, (ii) unsupervised learning, or (iii) reinforcement learning.
Kohout teaches wherein the processing of the data sets received utilizes a machine learning model trained on previously acquired data sets, wherein the machine learning model is associated with at least one of: (i) supervised learning, (ii) unsupervised learning, or (iii) reinforcement learning (Kohout, Col. 6, lines 9-14:” In various embodiments, traffic analysis process 248 may employ one or more supervised, unsupervised, or semi-supervised machine learning models. Generally, supervised learning entails the use of a training set of data, as noted above, that is used to train the model to apply labels to the input data.”).
Lutu and Kohout are considered analogous to the claimed invention because they are both direct toward remote device classification. Therefore, It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the teaching of Kohout to process Lutu’s combination data sets with a trained machine learning model in order to make the system more efficient by utilizing trained machine learning model to classify devices automatically.
Regarding claim 19, Lutu teaches A system operative to process multiple types of inputs to remotely determine mobile device type, comprising (Pg. 7, 4.3. M2M Device Classification, Col. 2, lines 8-11:” To do so we require to split the devices into three classes: smart (for smartphones), feat (for feature phones), and m2m (for IoT/M2M devices)”):
a receiver sub-system configured to receive, in conjunction with a radio access network (RAN) associated with a packet core (Pg. 6, 4.1 MNO dataset, Col. 2, lines 6-13:“Our passive measurement approach relies on commercial solutions integrated within the MNO’s infrastructure. The red pins in Fig. 4 mark the network elements that we monitor, namely the Mobility Management Entity (MME), the Message Sequence Chart (MSC) and the Serving GRPS Support Node (SGSN).”),
to which a remote mobile device is currently and/or was previously attached (Pg. 6, 4.1 MNO dataset, Col. 2, lines 12-13: “We collect control plane data on the total population of devices connected to the MNO’s radio network. “),
at least two types of data sets associated with the remote mobile device (Pg. 7, 4.1 Radio Interfaces., Col. 1, lines 1-4 :”Radio interfaces. We process logs reporting on activities on IuCS, IuPS, A, and Gb radio interfaces. Those carry events generated by the devices connecting to the radio sectors, and requesting resources for either data or voice communications.”; Pg. 7, 4.1, Service usage, Col. 1, lines 1-5:”We use Call Detail Records (CRDs) and eXtended Detail Records (xDRs) to provide aggregate service usage for calls and data. Each record reports the anonymized user ID, MCC, and MNC codes for both device SIM and visited country, timestamp, duration, and bytes consumed.” E.g., The radio interface event logs and the CDR/xDR usage records are two different types of data sets tied to the same device),
wherein each of the data sets received comprises a respective type of information operative to provide at least one respective type of clue regarding a type of mobile device best describing said remote mobile device (Lutu, Pg. 7, 4.1, Device properties, Col. 1, lines 2-4 “This catalog maps the device TAC to a set of device properties such as device manufacturer, brand and model name, operating system, and radio bands supported.”; Lutu, Pg.8 , Col. 1, lines 22-24:” APNs string can be a significant aid for strengthening the confidence of the classification as they hint the vertical used by a device.” E.g., the TAC maps to the device’s manufacturer, model and OS, and the APN strings hint at the device’s vertical. Each data set supplies its own kind of clue about the device type.);
thereby generating an output data set (Lutu, Pg. 7, 4.1, Daily devices-catalog, Col. 1, lines 1-3: “We combine the three data sources to create a daily list of active devices and associated properties and traffic characteristics.“);
and a determination component configured to determine, using at least said output data set, the type of mobile device best describing said remote mobile device (Lutu, [4.3], pg. 8, Col. 1, lines 39-43 :” Finally, we classify the devices combining both APNs and device properties. We start marking as m2m all devices using the validated APNs. Then, we extend the m2m class to all devices having the same properties of the devices using the validated APNs”; Kohout, Col. 8, lines 17-23:” Illustratively, the techniques described herein may be performed by hardware, software, and/or firmware, such as in accordance with the traffic analysis process 248, which may include computer executable instructions executed by the processor 220 (or independent processor of interfaces 210) to perform functions relating to the techniques described herein.”);
whereby, as a direct result of said processing, the determination is more accurate and/or more consistent than any similar determination using only one of the at least two types of data sets as an input (Examiner notes the whereby clause states a result and carry no weight ( MPEP 2111.04); 4.3, Pg. 8, Col. 2, lines 12-17: “Differently from (18), using APNs is useful to increase the classification confidence, and reduce the amount of manual investigations. However, when used in isolation, APNs are not enough as we find about 21% of the devices in the dataset not having any APN. This justifies our multi-steps classification process (keywords→APNs→device properties).”).
Lutu does not teach a computer comprising a memory module operative to store machine-readable code and related data in conjunction with operating a machine learning model configured to process the at least two types of data sets;
Kohout teaches a computer comprising a memory module operative to store machine-readable code and related data ( Kohout, Fig. 2; Col. 5, lines 6-9:” Device 200 comprises one or more network interfaces 210, one or more processors 220, and a memory 240 interconnected by a system bus 250, and is powered by a power supply 260.”; Kohout, Col. 5, lines 19-23:” The memory 240 comprises a plurality of storage locations that are addressable by the processor(s) 220 and the network interfaces 210 for storing software programs and data structures associated with the embodiments described herein.”) in conjunction with operating a machine learning model configured to process the at least two types of data sets (Kohout, Col. 5, lines 46-48:” In general, traffic analysis process 248 may execute one or more machine learning-based classifiers to classify a device in a network, based on its corresponding network traffic.” E.g., Lutu teaches using rules, not model. Kohout teaches traffic analysis process runs machine learning classifiers on network data to classify devices.),
Lutu and Kohout are considered analogous to the claimed invention because they are both direct toward remote device classification. Therefore, It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the teaching of Kohout to run Lutu’s classification on a processor and memory executing a machine learning classifier in order to classify devices automatically at operator scale.
Regarding claim 20, Lutu in view of Kohout teaches The system of claim 19, wherein the receiver sub-system, the computer comprising the memory module, and the determination component are implemented in one or more of the following environments: (i) a local server, wherein the components are housed on a dedicated machine within the same network as the mobile devices, (ii) a cloud-based server, wherein the components are hosted on a virtual server in a remote data center and accessed over the internet, (iii) a hybrid server, wherein some components are hosted locally and others are hosted in the cloud, and (iv) a distributed server, wherein the components are spread across multiple machines or locations for load balancing or redundancy purposes (Lutu, Pg. 6, 4.1 MNO dataset, Col. 2, lines 6-13:” Our passive measurement approach relies on commercial solutions integrated within the MNO’s infrastructure. The red pins in Fig. 4 mark the network elements that we monitor, namely the Mobility Management Entity (MME), the Message Sequence Chart (MSC) and the Serving GPRS Support Node (SGSN).”; Kohout, Fig. 2, Col. 4, lines 63- Col. 5, lines 1: “FIG. 2 is a schematic block diagram of an example node/device 200 that may be used with one or more embodiments described herein, e.g., as any of the computing devices shown in FIGS. 1A-1B, particularly the PE routers 120, CE routers 110, nodes/device 10-20, servers 152-154 (e.g., a network controller located in a data center, etc.)”).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 11304243 B2 discloses identifying UE device type from Classmark signaling captured by a network probe.
US 20220400487 A1 discloses a wireless base station receives user equipment capability information including device type.
US 20170230832 A1 discloses a monitoring platform on the cellular network ‘s GTP tunnel to extract IMSI and in conjunction with session IP address to apply device security profile.
US 20220191761 A1 discloses determining a RAN network device’s manufacturer and model from a MAC address or IMEI information in IP packet header.
WO 2005008386 discloses a server identifies a mobile device’s manufacturer and model from registration message carrying the IMEI, IMSI, terminal profile and location.
US 20210185528 A1 discloses method for identifying terminal device and communication apparatus.
US 11510050 B2 discloses determining technological capability of device having unknown technological capability and which are associated with a telecommunication network.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to THUAN H NGUYEN whose telephone number is (571)270-0332. The examiner can normally be reached 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Wesley Kim can be reached at 5712727867. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/THUAN HUU NGUYEN/Examiner, Art Unit 2648
/WESLEY L KIM/Supervisory Patent Examiner, Art Unit 2648