DETAILED ACTION
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 .
This communication is in response to the application filed on 11/06/2024.
Claims 1-6, and 8-14 are pending and are rejected. Claim 7 is objected.
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. FI20236293, filed on 11/23/2023.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/06/24 and 03/09/25 were filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Objections
Claims 1, 3-8, 10, and 13-14 are objected to because of informalities in claim format and clarity. These claims contain bullet symbols, dashes, and non-standard indentation to delineate claim limitations For example, claim 1 recites step preceded by hyphens and circular bullet symbols rather than proper claim indentation and punctuation. The use of such symbols is improper claim format under 37 CFR 1.75 and MPEP 608.01(m). Claim 3 further contains duplicate wording and unclear structure in the limitation “designated target service designated in a training service request”. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 2 recites “the service determination model is a trained model comprising
at least one Compact Convolutional Transformer”. However, the service determination model in claim 1 is a trained model comprising at least one machine learning sequence-to-sequence prediction model. It is unclear whether claim 2 intends to specify that the at least one Compact Convolutional Transformer is specific embodiment of the at least one machine learning sequence-to-sequence prediction model mentioned in claim 1.
Claim 4 recites “determine the plurality of service used at the node during the period of interest”. There is insufficient antecedent basis for this limitation in the claim.
Claim 13 recites “the at least one memory and computer program code configured to, with the at least one processor, cause the apparatus to:”. This language is awkward and unclear as to the structural relationship between the memory, processor, and instructions. Applicant is required to amend the claim to clearly recite that the memory stores instruction, and the instruction, when executed by the processor, cause the apparatus to perform the recited functions.
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.
Claims 1-2 and 4-14 are rejected under 35 U.S.C. 103 as being unpatentable over Madanapalli (WO 2023087069 A1) in view of Doken (US 20240048989 A1).
Regarding claim 1, Madanapalli teaches a method comprising:
- Selecting a period of interest within a collecting period, wherein the collecting period comprises a plurality of sub-periods, wherein the period of interest consisting of at least one of said sub-periods (page 8, lines 24-28, the network traffic classification process accepts two input parameters, referred to herein as interval and PLB, respectively. The input parameter PLB is a list of packet length boundaries that define the boundaries of the packet length bins, and the input parameter interval defines the fixed duration of each timeslot; col. 9, lines 10-13, the choice of interval and PLB determines the granularity and size of the resulting arrays. For example, a user may choose to have a relatively small interval, say 100ms, and have 3 packet length boundaries, or a large interval, say 1 sec, and have 15 packet length boundaries);
- Determining a plurality of services used at a node of a communication network, during the period of interest, by implementing a service determination model on a plurality of inputs, the plurality of inputs comprising (pages 11-12, Thus the cell upPacketLength[i,j] (downPacketLength[i,j]) stores the average packet length of upstream (downstream) packets that arrived in timeslot j and whose packet lengths were in the packet length bin i. These arrays provide time-series average packet length measurements across the packet length bins, and have been found to be useful to identify specific applications (or, equivalently, specific providers) (e.g., Netflix, Disney, etc) within a particular application type (e.g., video), because although the overall traffic shape remains very similar between different applications/providers, the packet lengths differ. Application Type Classification (/.e., to identify the type of an application (e.g., Video vs. Conference vs. Download, etc.)), and (b) Application Provider Classification (/.e., to identify the specific application (or, equivalently, the provider of the application/service) (e.g., Netflix vs YouTube, or Zoom vs Microsoft Teams, etc.))):
a downstream traffic volume received by the node during the period of interest and an upstream traffic volume sent by the node during the period of interest; p downstream traffic volumes received by the node during each of p sub-periods preceding the period of interest and p upstream traffic volumes sent by the node during said each of p sub-periods preceding the period of interest (page 8, line 29 to page 9, line 10, if the packet is an upload packet, the cell (i,j) of the upPackets array is incremented by 1, and the cell (i,j) of the upBytes array is incremented by the payload length (Len) of the packet (in bytes). Thus, after timeslot j has passed, cell (i,j) of the upPackets array stores the count (/.e., the number) of all packets that arrived in timeslot j with lengths between PLB[i-l] and PLB[i], and cell (i,j) of the upBytes array stores the total number of bytes of payload data contained in those same packets. Conversely, if the packet is a download packet, then the cells (i,j) of the downPackets and downBytes arrays is incremented in the same manner. The choice of interval and PLB determines the granularity and size of the resulting arrays. For example, a user may choose to have a relatively small interval, say 100ms, and have 3 packet length boundaries, or a large interval, say 1 sec, and have 15 packet length boundaries (in steps of lOOBytes). Such choices can be made depending on both the NTC task and the available compute/memory resources);
the service determination model being a trained model comprising at least one machine learning sequence-to-sequence prediction model (page 11, lines 16-19, a machine learning ("ML") model is trained to classify a network traffic flow into one of these five classes. The ML model training data contains flows from different applications/providers of each application type in order to make it diverse and not limited to provider-specific patterns),
wherein the service determination model has been trained to determine a plurality of target services used at the node during a training period of interest (page 13, lines 5-9, every record of the training data is a three tuple < timeseries, Type, Provider >. The timeseries arrays were recorded for 30 seconds at an interval of o.5sec and with 3 packet length bins (PLB = [0,1250,1500]). The data was filtered, pre-processed and labelled appropriately per task, as described below, before feeding it to the ML models. For the application type classification task, only the top 5-10 applications/providers of each class were used, and only the type was used as the final label).
Madanapalli does not explicitly teach wherein p is a positive integer number;
Doken teaches wherein p is a positive integer number ([0005] The values measured may include the total number of bits downloaded in time interval T (downstream tonnage), the total number of bits uploaded in time interval T (upstream tonnage), peak (instantaneous) downstream bandwidth in time interval T, peak (instantaneous) upstream bandwidth in time interval T, downstream wide area network (WAN) link utilization (proportion of time that the downstream WAN link is activated during time interval T));
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention made to include in the Madanapalli disclosure, the downstream, upstream, and the period of time are not negative number, as taught by Doken. One would be motivated to do so to calculates the difference between the values for the two most recent time periods.
Regarding claim 2, Madanapalli and Doken teach method according to claim 1 wherein Madanapalli further teaches the service determination model is a trained model comprising at least one Compact Convolutional Transformer (page 3, lines 1-4, the time series data sets includes applying an artificial neural network deep learning model to the time series data sets of each network traffic flow to classify the network flow into one of the plurality of predetermined network traffic classes).
Regarding claim 4, Madanapalli and Doken teach method according to claim 1 wherein Madanapalli further teaches:
determining the plurality of services used at the node comprises determining a main service; the main service being a service generating a highest traffic among a plurality of services useable at the node (page 8, lines 3-11, Surprisingly, the inventors have determined that these four time series data sets, even when generated for only the first ~10 seconds of each new traffic flow, can be used to accurately classify the network flow into one of a plurality of predetermined network traffic classes);
wherein the plurality of target service comprises a main target service used at the node
during the training period of interest (page 11, lines 16-18, The ML model training data contains flows from different applications/providers of each application type in order to make it diverse and not limited to provider-specific patterns).
Regarding claim 5, Madanapalli and Doken teach method according to claim 1 wherein Madanapalli further teaches:
determining the plurality of services used at the node further comprises outputting an indication of traffic volume generated by each service of the plurality of services, the service determination model being trained to determine the traffic volume generated by each target service of the plurality of target services used at the node during the training period of interest (page 7, lines 3-7, The external interfaces include a network interface connector (NIC) 112 which connects the apparatus 100 to a communications network such as the Internet or to a network switch, and may include universal serial bus (USB) interfaces, at least one of which may be connected to a keyboard and a pointing device such as a mouse, and a display adapter, which may be connected to a display device).
Regarding claim 6, Madanapalli and Doken teach method according to claim 1 wherein Madanapalli further teaches the plurality of inputs further comprises:
f downstream traffic volumes received by the node during each of f sub-periods following the period of interest and f upstream traffic volumes sent by the node during said each of f sub-periods following the period of interest (page 8, lines 15-19, the time series data sets are implemented as four twodimensional ("2-D") arrays referred to herein as upPackets, downPackets, upBytes and downBytes, respectively representing counts of packets transmitted in upstream and downstream directions, and corresponding cumulative byte counts of those same packets in upstream and downstream directions);
Madanapalli does not explicitly teach f is a positive integer number
Doken teaches
wherein f is a positive integer number ([0005] The values measured may include the total number of bits downloaded in time interval T (downstream tonnage), the total number of bits uploaded in time interval T (upstream tonnage), peak (instantaneous) downstream bandwidth in time interval T, peak (instantaneous) upstream bandwidth in time interval T, downstream wide area network (WAN) link utilization (proportion of time that the downstream WAN link is activated during time interval T)).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention made to include in the Madanapalli disclosure, the downstream, upstream, and the period of time are not negative number, as taught by Doken. One would be motivated to do so to calculates the difference between the values for the two most recent time periods.
Regarding claim 7, Madanapalli and Doken teach method according to claim 1 wherein the service determination model has been trained to determine the plurality of target services used at the node, for a plurality of training periods of interest, based on a plurality of training inputs;
wherein, for a first of two parts of the plurality of training periods of interest, the plurality of training inputs comprises:
p training downstream traffic volumes received by the node during each of p training sub-periods preceding the training periods of interest of the first part of the plurality of training periods of interest and p upstream traffic volumes sent by the node during said each of p training sub-periods preceding the training periods of interest of the first part of the plurality of training periods of interest;
f training downstream traffic volumes received by the node during each of f training sub-periods following the training periods of interest of the first part of the plurality of training periods of interest and f upstream traffic volumes sent by the node during said each of p training sub-periods following the training periods of interest of the first part of the plurality of training periods of interest;
wherein, for a second of the two parts of the plurality of training period of interest, the plurality of training inputs only comprises:
training downstream traffic volume and training upstream traffic volume received and sent during the number p of training sub-periods, each one of the p training sub-periods preceding the training periods of interest of the second part of the plurality of training periods of interest;
wherein the period of interest is equal in length to the training period of interest.
Regarding claim 8, Madanapalli and Doken teach method according to claim 1, Madanapalli further teaches:
Iterating the selecting and the determining from a first to a last sub-period of the collecting period according to a chronological order (page 8, the time series data sets are generated using counters to capture the traffic shape/behavioural profile of each network flow).
Regarding claim 9, Madanapalli and Doken teach method according to claim 8 wherein Madanapalli further teaches each one of the sub-periods is part of only one period of interest (page 9, The two (upstream and downstream) video flows on top of the Figure show periodic activity - there are media requests going in the upstream direction with payload length between 0 and 1250, and correspondingly media segments are being sent by the server using full-MTU packets that fall into the packet length bin).
Regarding claim 10, Madanapalli and Doken teach method according to claim 9 wherein Madanapalli further teaches:
the collecting comprises a number of sub-periods superior to p, the first sub-period comprised in a selected period of interest among the collecting period is a sub-period directly following, according to a chronological order, the p-th sub-period of the collecting period (page 10, the network traffic classification apparatus includes a high-speed P4 programmable switch, such as an Intel® Tofino®-based switch. Each network traffic flow is identified by generating its flow_key and matching to an entry in a lookup table of the switch, and sets of 4 registers store upstream and downstream byte counts and packet counts).
Regarding claim 11, Madanapalli and Doken teach method according to claim 1 wherein Madanapalli further teaches the downstream traffic volume and the upstream traffic volume received and sent during the plurality of sub-periods of the collecting period are measured, for each sub-period, by one or more downstream counters and one or more upstream counters; a downstream counter measuring a downstream traffic received at the node during a measuring time, a upstream counter measuring a upstream traffic sent from the node during the measuring time (page 8, lines 10-14, the time series data sets are generated using counters to capture the traffic shape/behavioural profile of each network flow. Importantly, the data captured does not include header/payload contents of packets, and consequently is protocol-agnostic and does not rely on clear-text indicators such as SNI (server name indication)).
Regarding claim 12, Madanapalli and Doken teach method according to claim 1, Madanapalli further teaches:
Analyzing and/or reporting of the activity of one or a plurality of nodes of the communication network based on at least one determined service during the determination step, Troubleshooting one or a plurality of nodes of the communication network based on at least one determined service during the determination step, managing one or a plurality of nodes of the communication network based on at least one determined service during the determination step, and/or optimizing a service used at one or a plurality of nodes of the communication network based on at least one determined service during the determination step (page 18, lines 1-8, the CNN 604 updates the encoder weights to improve the extraction of features using visual filters, whereas in the case of the TE-LSTM, the LSTM 606 updates the encoder weights to improve the extraction of time-series features. Irrespective of the underlying model architecture, the transformer encoder is capable of enhancing the input to suit the operation of the underlying model 604, 606, with the result that the combined/composite models (TE + the underlying 'vanilla' model) learn and perform better than the underlying vanilla models 604, 606 alone, across the range of NTC tasks).
Regarding claim 13, Madanapalli teaches apparatus comprising:
at least one processor; and at least one memory including a computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the apparatus to:
- Select a period of interest among a collecting period, wherein the collecting period comprises a plurality of sub-periods, wherein the period of interest comprising at least one sub-period (page 8, lines 24-28, the network traffic classification process accepts two input parameters, referred to herein as interval and PLB, respectively. The input parameter PLB is a list of packet length boundaries that define the boundaries of the packet length bins, and the input parameter interval defines the fixed duration of each timeslot; col. 9, lines 10-13, the choice of interval and PLB determines the granularity and size of the resulting arrays. For example, a user may choose to have a relatively small interval, say 100ms, and have 3 packet length boundaries, or a large interval, say 1 sec, and have 15 packet length boundaries);
- Determine a plurality of services used at a node of a communication network, during the period of interest, by implementing a service determination model on a plurality of inputs, the plurality of inputs comprising: downstream traffic volume and upstream traffic volume received and sent during the at least one sub-period of the period of interest (pages 11-12, Thus the cell upPacketLength[i,j] (downPacketLength[i,j]) stores the average packet length of upstream (downstream) packets that arrived in timeslot j and whose packet lengths were in the packet length bin i. These arrays provide time-series average packet length measurements across the packet length bins, and have been found to be useful to identify specific applications (or, equivalently, specific providers) (e.g., Netflix, Disney, etc) within a particular application type (e.g., video), because although the overall traffic shape remains very similar between different applications/providers, the packet lengths differ. Application Type Classification (/.e., to identify the type of an application (e.g., Video vs. Conference vs. Download, etc.)), and (b) Application Provider Classification (/.e., to identify the specific application (or, equivalently, the provider of the application/service) (e.g., Netflix vs YouTube, or Zoom vs Microsoft Teams, etc.)));
downstream traffic volume and upstream traffic volume received and sent during a number p of sub-periods, each one of the p sub-periods preceding the period of interest (page 8, line 29 to page 9, line 10, if the packet is an upload packet, the cell (i,j) of the upPackets array is incremented by 1, and the cell (i,j) of the upBytes array is incremented by the payload length (Len) of the packet (in bytes). Thus, after timeslot j has passed, cell (i,j) of the upPackets array stores the count (/.e., the number) of all packets that arrived in timeslot j with lengths between PLB[i-l] and PLB[i], and cell (i,j) of the upBytes array stores the total number of bytes of payload data contained in those same packets. Conversely, if the packet is a download packet, then the cells (i,j) of the downPackets and downBytes arrays is incremented in the same manner. The choice of interval and PLB determines the granularity and size of the resulting arrays. For example, a user may choose to have a relatively small interval, say 100ms, and have 3 packet length boundaries, or a large interval, say 1 sec, and have 15 packet length boundaries (in steps of lOOBytes). Such choices can be made depending on both the NTC task and the available compute/memory resources);
the service determination model being a trained model based on at least one ML sequence-to-sequence prediction model, wherein the service determination model has been trained to determine the plurality of service used at the node during the period of interest (page 11, lines 16-19, a machine learning ("ML") model is trained to classify a network traffic flow into one of these five classes. The ML model training data contains flows from different applications/providers of each application type in order to make it diverse and not limited to provider-specific patterns; page 13, lines 5-9, every record of the training data is a three tuple < timeseries, Type, Provider >. The timeseries arrays were recorded for 30 seconds at an interval of o.5sec and with 3 packet length bins (PLB = [0,1250,1500]). The data was filtered, pre-processed and labelled appropriately per task, as described below, before feeding it to the ML models. For the application type classification task, only the top 5-10 applications/providers of each class were used, and only the type was used as the final label).
Madanapalli does not explicitly teach wherein p is a positive integer number;
Doken teaches wherein p is a positive integer number ([0005] The values measured may include the total number of bits downloaded in time interval T (downstream tonnage), the total number of bits uploaded in time interval T (upstream tonnage), peak (instantaneous) downstream bandwidth in time interval T, peak (instantaneous) upstream bandwidth in time interval T, downstream wide area network (WAN) link utilization (proportion of time that the downstream WAN link is activated during time interval T));
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention made to include in the Madanapalli disclosure, the downstream, upstream, and the period of time are not negative number, as taught by Doken. One would be motivated to do so to calculates the difference between the values for the two most recent time periods.
Regarding claim 14, Madanapalli teaches a non-transitory computer readable medium storing a computer program
comprising instructions for causing an apparatus to perform:
- Selecting the period of interest within a collecting period, wherein the collecting period comprises a plurality of sub-periods, wherein the period of interest consisting of at least one of said sub-periods (page 8, lines 24-28, the network traffic classification process accepts two input parameters, referred to herein as interval and PLB, respectively. The input parameter PLB is a list of packet length boundaries that define the boundaries of the packet length bins, and the input parameter interval defines the fixed duration of each timeslot; col. 9, lines 10-13, the choice of interval and PLB determines the granularity and size of the resulting arrays. For example, a user may choose to have a relatively small interval, say 100ms, and have 3 packet length boundaries, or a large interval, say 1 sec, and have 15 packet length boundaries);
- Determining a plurality of services used at the node, during the period of interest, by implementing a service determination model on a plurality of inputs, the plurality of inputs comprising (pages 11-12, Thus the cell upPacketLength[i,j] (downPacketLength[i,j]) stores the average packet length of upstream (downstream) packets that arrived in timeslot j and whose packet lengths were in the packet length bin i. These arrays provide time-series average packet length measurements across the packet length bins, and have been found to be useful to identify specific applications (or, equivalently, specific providers) (e.g., Netflix, Disney, etc) within a particular application type (e.g., video), because although the overall traffic shape remains very similar between different applications/providers, the packet lengths differ. Application Type Classification (/.e., to identify the type of an application (e.g., Video vs. Conference vs. Download, etc.)), and (b) Application Provider Classification (/.e., to identify the specific application (or, equivalently, the provider of the application/service) (e.g., Netflix vs YouTube, or Zoom vs Microsoft Teams, etc.))):
a downstream traffic volume received by the node during the period of interest and an upstream traffic volume sent by the node during the period of interest; p downstream traffic volumes received by the node during each of p sub-periods preceding the period of interest and p upstream traffic volumes sent by the node during said each of p sub-periods preceding the period of interest (page 8, line 29 to page 9, line 10, if the packet is an upload packet, the cell (i,j) of the upPackets array is incremented by 1, and the cell (i,j) of the upBytes array is incremented by the payload length (Len) of the packet (in bytes). Thus, after timeslot j has passed, cell (i,j) of the upPackets array stores the count (/.e., the number) of all packets that arrived in timeslot j with lengths between PLB[i-l] and PLB[i], and cell (i,j) of the upBytes array stores the total number of bytes of payload data contained in those same packets. Conversely, if the packet is a download packet, then the cells (i,j) of the downPackets and downBytes arrays is incremented in the same manner. The choice of interval and PLB determines the granularity and size of the resulting arrays. For example, a user may choose to have a relatively small interval, say 100ms, and have 3 packet length boundaries, or a large interval, say 1 sec, and have 15 packet length boundaries (in steps of lOOBytes). Such choices can be made depending on both the NTC task and the available compute/memory resources);
the service determination model being a trained model comprising at least one machine learning sequence-to-sequence prediction model (page 11, lines 16-19, a machine learning ("ML") model is trained to classify a network traffic flow into one of these five classes. The ML model training data contains flows from different applications/providers of each application type in order to make it diverse and not limited to provider-specific patterns), wherein the service determination model has been trained to determine a plurality of target services used at the node during a training period of interest (page 13, lines 5-9, every record of the training data is a three tuple < timeseries, Type, Provider >. The timeseries arrays were recorded for 30 seconds at an interval of o.5sec and with 3 packet length bins (PLB = [0,1250,1500]). The data was filtered, pre-processed and labelled appropriately per task, as described below, before feeding it to the ML models. For the application type classification task, only the top 5-10 applications/providers of each class were used, and only the type was used as the final label).
Madanapalli does not explicitly teach wherein p is a positive integer number;
Doken teaches wherein p is a positive integer number ([0005] The values measured may include the total number of bits downloaded in time interval T (downstream tonnage), the total number of bits uploaded in time interval T (upstream tonnage), peak (instantaneous) downstream bandwidth in time interval T, peak (instantaneous) upstream bandwidth in time interval T, downstream wide area network (WAN) link utilization (proportion of time that the downstream WAN link is activated during time interval T));
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention made to include in the Madanapalli disclosure, the downstream, upstream, and the period of time are not negative number, as taught by Doken. One would be motivated to do so to calculates the difference between the values for the two most recent time periods.
Claims 3 is rejected under 35 U.S.C. 103 as being unpatentable over Madanapalli (WO 2023087069 A1) in view of Doken (US 20240048989 A1) and further in view of Sirov (US 20230164043 A1).
Regarding claim 3, Madanapalli and Doken teach method according to claim 1, Madanapalli does not explicitly teach wherein:
the plurality of inputs further comprises a service request designating a service useable at the node, and
determining the plurality of services used at the node comprises outputting an indication of use of the service designated in the service request;
wherein the plurality of target services comprises designated target service designated in a training service request.
Sirov teaches
the plurality of inputs further comprises a service request designating a service useable at the node ([0046] a system is further disclosed for application-level classification of a data traffic session over a data communications network. The system comprises at least a receiver configured to receive a plurality of data packets of the data traffic session), and
determining the plurality of services used at the node comprises outputting an indication of use of the service designated in the service request ([0079] the instructions of machine learning module may cause system to receive training data, process it, and output one or more training datasets, each comprising a plurality of annotated data samples, based on one or more annotation schemes);
wherein the plurality of target services comprises designated target service designated in a training service request ([0074] Information received at data traffic monitor 208 may be processed and transmitted to data traffic analysis module 206a and/or to other components of system).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the claimed invention made to include in the Madanapalli disclosure, output training data set, as taught by Sirov. One would be motivated to do so to for training a machine learning model on a training dataset comprising the sets of features for each of the data flows, and labels indicating an identity of a particular one of the application or internet services associated with each of the data flows, to obtain a trained machine learning classifier.
Allowable Subject Matter
Claim 7 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims and overcome the objection/rejection as noted above. The prior art does not explicitly teach the limitations below when combined with the limitations in the independent claims 1, 13, and 14.
wherein the service determination model has been trained to determine the plurality of target services used at the node, for a plurality of training periods of interest, based on a plurality of training inputs;
wherein, for a first of two parts of the plurality of training periods of interest, the plurality of training inputs comprises:
p training downstream traffic volumes received by the node during each of p training sub-periods preceding the training periods of interest of the first part of the plurality of training periods of interest and p upstream traffic volumes sent by the node during said each of p training sub-periods preceding the training periods of interest of the first part of the plurality of training periods of interest;
f training downstream traffic volumes received by the node during each of f training sub-periods following the training periods of interest of the first part of the plurality of training periods of interest and f upstream traffic volumes sent by the node during said each of p training sub-periods following the training periods of interest of the first part of the plurality of training periods of interest;
wherein, for a second of the two parts of the plurality of training period of interest, the plurality of training inputs only comprises:
training downstream traffic volume and training upstream traffic volume received and sent during the number p of training sub-periods, each one of the p training sub-periods preceding the training periods of interest of the second part of the plurality of training periods of interest;
wherein the period of interest is equal in length to the training period of interest.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Frayman (US 20180124085 A1) and Dicato (US 20150007250 A1).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANH NGUYEN whose telephone number is (571)270-0657. The examiner can normally be reached M-F.
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, Umar Cheema can be reached at 5712703037. 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.
/ANH NGUYEN/Primary Examiner, Art Unit 2458