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 .
Response to Amendment
Prior to examination, claims 1-20 have been canceled.
The amendment filed on June 5, 2026, has been entered. Claim 21-40 remain pending in the application. Objections to the title, specification and abstract are formally withdrawn.
Priority
This application claims priority to Chinese Application No. CN202110900384.2 filed August 06, 2021.
Response to Arguments
Applicant's arguments filed June 5, 2026 have been fully considered but they are not persuasive.
Applicant argues that Monterio does not teach “performing, by a second network device, inference using an artificial intelligence (AI) model to obtain a first inference result; and sending, by the second network device”
The Examiner respectfully disagrees.
The Examiner respectfully asserts that Monterio teaches “performing, by a second network device, inference using an artificial intelligence (AI) model to obtain a first inference result; and sending, by the second network device”, in particular paragraphs 12 and 14 (see italicized portions of paragraphs cited below)
Monterio teaches:
[0012] One known approach and assumptions in the latest Third Generation Partnership Project (3GPP) study item on Al/ML, i.e. Rel-16, are based on prediction models at the network side, and these models are trained based on information reported from the UEs. These assumptions rely on the network predicting quantities of interest, such as mobility patterns, received signal strength/quality, e.g., Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), to make timely and intelligent decisions. It is a focus on application of Al/ML on the network side. Predictions of parameters such as RSRP, RSRQ, call drop, mobility patterns of the UEs, target cell in a handover are examples of use cases where Al/ML has been utilized in the network side for further optimization.
[0013] 3GPP has started to discuss Al/ML use cases in Rel-17. Operators see traditional human-machine interaction as slow, error-prone, expensive, and it is cumbersome to handle these challenges. Al comprising ML algorithms provide a powerful tool to help operators to improve the network management and the user experience by analyzing the data collected and autonomously processed that may yield further insights. Application of Al in 5G networks has gained tremendous attention in both academia and industry.
[0014] Therein, it is assumed that most of the Al algorithms may be up to the network implementation. The focus will be on signaling support for training and the execution involved in Al schemes, the data required by the Al algorithms, e.g., potentially reported by the UE or collected from different parts of the network, and outputs generated by the algorithms to be delivered to other network nodes or Network Functions (NFs) in Radio Access Network (RAN), Core Network (CN), or Operation and Maintenance (OAM)/CHM. Potential use cases and examples that are mentioned comprise energy saving, traffic steering, mobility optimization, load balancing, physical layer configuration optimization, etc.
While Examiner acknowledges that Monterio teaches on UE centric AI/ML prediction models, Examiner notes that Monterio also has support for network centric Al/ML prediction models.
Further, in the Non-Final Rejection dated March 6, 2026, Examiner noted pertinent prior art that teaches the elements claimed, i.e. Paredes (US 20230140473 A1) which teaches using artificial intelligence (AI) for communication networks to collect location information, the collected location information associated with movement of at least one user equipment within a network; communicating an indication of the prediction based on the collected information.
Claim Rejections - 35 USC § 103
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 21-40 are rejected under 35 U.S.C. 103 as being unpatentable over Mythri HUNUKUMBURE (US 20170311216 A1 and Hunukumbure hereinafter) in view of Monteiro (US 20240251258 A1 and Monteiro hereinafter).
Regarding Claim 21, Hunukumbure discloses a communication method comprising:
a first message to a first network device corresponding to a first target cell (“Then, (4. “Handover Request”) the Source eNB (i.e. second network device) issues a handover request (i.e. a first message) to the Target eNB (i.e. first network device), passing necessary information to prepare the handover at the target side“,[0005] Fig 7, step 4),
wherein the first target cell is a predicted serving cell accessible by a terminal device (“Suppose that a connected-mode UE is connected to a Source eNB providing a serving cell, and can receive at least reference signals from a neighbour cell (i.e. target cell) provided by a Target eNB).“,[0005]),
Hunukumbure doesn’t explicitly teach
performing, by a second network device, inference using an artificial intelligence (AI) model to obtain a first inference result; and sending, by the second network device,
the first message indicates a first inference result, the first inference result comprises first predicted information and the first predicted information comprises:
future movement information of the terminal device
future service information of the terminal device
or future movement track information of the terminal device
However, in a similar endeavor Monterio teaches
performing, by a second network device, inference using an artificial intelligence (AI) model to obtain a first inference result (“are based on prediction models at the network side, and these models are trained based on information reported from the UEs. These assumptions rely on the network predicting quantities of interest, such as mobility patterns, received signal strength/quality, e.g., Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), to make timely and intelligent decisions. It is a focus on application of Al/ML on the network side. Predictions of parameters such as RSRP, RSRQ, call drop, mobility patterns of the UEs, target cell in a handover are examples of use cases where Al/ML has been utilized in the network side for further optimization.”[0012]); and
sending, by the second network device (“Therein, it is assumed that most of the Al algorithms may be up to the network implementation. The focus will be on signaling support for training and the execution involved in Al schemes, the data required by the Al algorithms, e.g., potentially reported by the UE or collected from different parts of the network, and outputs generated by the algorithms to be delivered to other network nodes or Network Functions (NFs) in Radio Access Network (RAN), Core Network (CN)”[0014]),
the first message indicates a first inference result, the first inference result comprises first predicted information (“The Handover Request message comprises the MPM (Mobility Prediction Model) the UE 105 currently uses, settings, error information of the MPM, accuracy information of the MPM etc (i.e. inference results of predicted information)“,[0224]) and the first predicted information comprises:
future movement information of the terminal device (“Procedures of mobility prediction are input from the applications to the performance matrices. Evaluating results from prediction outputs (i.e. future predictions) such as moving direction 308 (i.e. future movement information), transition probability 309, future location 310 (i.e. future movement information), user trajectory 311 and the next cell ID 312 are provided to the performance matrices“,[0010], Fig 1),
future service information of the terminal device (“Procedures of mobility prediction are input from the applications to the performance matrices. Evaluating results from prediction outputs (i.e. future predictions) such as moving direction 308, transition probability 309, future location 310, user trajectory 311 and the next cell ID 312 (i.e. future service information) are provided to the performance matrices“,[0010], Fig 1) and ("an index or identifier of a next cell the UE 105 is predicted to move to or enter the coverage of, where the identifier or index may be, e.g., physical cell identity (PCI) and/or Cell Identity as indicated in a System Information Block; ii) the beam or Synchronization Sequence Block (SSB) index or identifier, e.g., that is expected to best serve a UE 105 in the future;"[0133]),
future movement track information of the terminal device (“Procedures of mobility prediction are input from the applications to the performance matrices. Evaluating results from prediction outputs (i.e. future predictions) such as moving direction 308 (i.e. future movement track information)… future location 310, user trajectory 311 (i.e. future movement track information) and the next cell ID 312 are provided to the performance matrices“,[0010], Fig 1).
Therefore, it would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to combine the method of Hunukumbure with the method suggested by Monterio. The motivation would be to enhance users' experience through services related to the users' specific location, see Monterio at [0008].
Regarding Claims 28 and 35, Hunukumbure-Monterio suggests all the limitations of claim 21 in device form rather than method form. Further Hunukumbure discloses an apparatus ([0119] ” FIG. 6 is a block diagram illustrating an example of an eNB 10, 11, 12 or 13 (i.e. network device) to which the present invention may be applied. The eNB includes transmitter/receiver unit(s) 904 connected to at least one antenna 902 (together defining a communication unit) and a controller 906 (i.e. processor)…the various functions described above may be embodied in the form of a computer program stored in the storage medium 908.”). Therefore, the rejection of claim 21 applies equally as well to the limitations of claim 28 and 35.
Regarding Claims 22 and 29, Hunukumbure-Monteiro teaches all the limitations of claims 21 and 28 as discussed above. Further Hunukumbure teaches
further comprising determining the first target cell based on the first inference result (“Step 3 “HO decision” is for Source eNB to make a decision (i.e. determining) based on measurement report (i.e. inference result) and RRM information to hand over the UE. Then, (4. “Handover Request”) the Source eNB issues a handover request to the Target eNB (i.e. target cell),“, [0005] Fig 7, steps 3 and 4).
Regarding Claims 23, 30 and 38, Hunukumbure-Monteiro teaches all the limitations of claims 21, 28 and 35 as discussed above. Further Hunukumbure teaches
wherein the future movement information of the terminal device comprises second predicted information, the second predicted information comprising:
camping time information of the terminal device in the future cell ("the profiling process enables the central controller to identify some patterns of commuter behaviour…From such patterns, the central controller can establish the bi-directional commuter movement (some getting out and some getting in) at most of the bus stops/stations at busy times (i.e. future camping time information).",[0084]),
information about whether the terminal device exits a connected state in the future cell(“In a bus for example, all of the users leaving the bus at a particular stop will normally leave (i.e. exit connection) by the same exit door (i.e. the first base station which is a moving cell on the bus) and then come into contact with the neighbour cell. Up to this point, they will be served by the moving cell (i.e. the bus example in reference). It is this measurement (at the exit point) that matters, which will be almost the same every time, even if individual users then disperse and later join different cells. This measurement can be provided to the controller or the destination cell in advance to speed up the handover.“,[0106]),
or prediction accuracy of the future movement information of the terminal device ("wherein the central controller is arranged to receive data concerning the users from at least the first base station, gather profile data of the users based on the data received, make predictions about which users are likely to enter and leave the vehicle at the stop, and based on the predictions, to provide guidance to the first and second base stations for performing handovers of the users."[0037]).
Hunukumbure doesn’t explicitly teach
information about a future cell of the terminal device;
a manner of accessing the future cell by the terminal device.
In a similar field of endeavor Monteiro teaches
information about a future cell of the terminal device (“If the MPM returns as output, for example: i) an index or identifier of a next cell the UE 105 is predicted to move to or enter the coverage of (i.e. future cell information), where the identifier or index may be, e.g., physical cell identity (PCI) and/or Cell Identity as indicated in a System Information Block;“,[0135]);
a manner of accessing the future cell by the terminal device (“ii) the beam or Synchronization Sequence Block (SSB) (i.e. how the UE accesses a future cell) index or identifier, e.g., that is expected to best serve a UE 105 in the future“,[0135]).
Therefore, it would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to combine the method of Hunukumbure with the method suggested by Monteiro. The motivation would be so that the UE may transmit or report to the target network node, e.g. after the handover, mobility, reconfiguration with sync, the information related to the MPM (i.e. Mobility Prediction Model). see Monteiro at [0136].
Regarding Claims 24, 31 and 39, Hunukumbure-Monteiro teaches all the limitations of claims 21, 28 and 35 as discussed above. Further Hunukumbure teaches
wherein the future service information of the terminal device comprises third predicted information, the third predicted information comprising: a future service type of the terminal device (" Some of these users will furthermore be active users, in other words, will use their mobile devices for data or voice services (predicted service type) inside the public transport vehicle and/or while waiting at a stop or station;"[0074] and “the central controller is arranged to predict whether the user is likely to continue to require wireless access to the service after leaving or entering the vehicle“,[0027] and "Users U are waiting at each bus stop and, like the users on the bus B, will be using their mobile devices in general and receiving services via the bus stop eNBs 12."[0067] and Fig. 1),
a quality of service (QoS) requirement of a future service (“A network oriented solution is proposed, which has a holistic view of the multiple destination cells based on previously reported values to determine what level of capacity will be freed and what level of QoS can be provided.“,[0047]),
a traffic volume of the future service (“In S16 the moving eNB provides (if necessary) the signal strength measurements to the central controller 20. Meanwhile, the fixed eNB(s) at bus stop BS2 informs the central controller of the number of passengers waiting at the bus stop. (For present purposes, “likely passengers” means users of the wireless communication network (i.e. traffic volume) waiting at the bus stop (i.e. future service): other users having no active mobile device are of no interest).“,[0092], Fig.4, element S16 and "If the serving (moving) cell finds that the measurements are delayed or there are a larger number of potential handovers (i.e. traffic volume)"[0104]),
or time information of the future service (“profiles can also be associated with the UEs' individual RFIDs in addition to the ID(s) allocated by the mobile network. The mapping between the two types of ID can be based on users' behaviour information, such as when the user's UE connects and disconnects (i.e. time information) with the in-vehicle eNB“[0078]. Further "the profiling process enables the central controller to identify some patterns of commuter behaviour…From such patterns, the central controller can establish the bi-directional commuter movement (some getting out and some getting in) at most of the bus stops/stations at busy times.",[0084]).
Regarding Claims 25, 32 and 40 Hunukumbure-Monteiro teaches all the limitations of claim 21, 28 and 35 as discussed above. Further Hunukumbure teaches
receiving feedback information from the first network device ("Then (6. “Handover Request Ack.”) the Target eNB 11 (i.e. first network device) prepares the HO and sends the handover request Ack. (feedback information) to the Source eNB...“,[0005] Fig. 7, step 6),
wherein the feedback information comprises indication information of: actual camping time information of the terminal device in the first target cell (“profiles can also be associated with the UEs' individual RFIDs in addition to the ID(s) allocated by the mobile network. The mapping between the two types of ID can be based on users' behaviour information, such as when the user's UE connects and disconnects (i.e. actual camping time information) with the in-vehicle eNB“,[0078] Fig. 3),
information about whether the terminal device actually exits a connected state in the first target cell (“The mapping between the two types of ID can be based on users' behaviour information such as when the user's UE connects and disconnects (i.e. exits) with the in-vehicle eNB, when the user gets on and gets off the bus (i.e. exits)“,[0078] and "detach (i.e. exits/disconnects) from old cell to synchronize to new cell", Fig. 7 under step 7),
a second inference result (“Step 3 “HO decision” is for Source eNB to make a decision (i.e. determining) based on measurement report (i.e. inference result) and RRM information to hand over the UE.”[0005], Fig 7, steps 3 and 4),
or a second target cell (“all of the users leaving the bus at a particular stop will normally leave by the same exit door and then come into contact with the neighbour cell (i.e. second target cell).“,[0106]).
Regarding Claims 26 and 33, Hunukumbure in view of Monteiro, Hunukumbure-Monteiro hereinafter, teaches all the limitations of claims 25 and 33 as discussed above.
Hunukumbure doesn’t explicitly teach
optimizing or updating a parameter of a model for determining the first inference result based on the feedback information
In a similar endeavor Monteiro teaches
optimizing or updating a parameter of a model for determining the first inference result based on the feedback information ("The target gNodeB 101 sends a Handover Request Acknowledgement message (feedback information) to the source gNodeB 101. The Handover Request Acknowledgement message comprises a re-configured (i.e. optimizing/updating) MPM (i.e. mobility prediction model), e.g., new MPM or new settings (i.e. parameters of a model). The source gNodeB 101 sends a RRC Reconfiguration message to the UE 105. The RRC Reconfiguration message comprises the re-configured MPM, e.g. the new MPM or the new settings(i.e. parameter)."[0226-0227] Fig. 13, element 1307).
Therefore, it would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to combine the method of Hunukumbure with the method suggested by Monteiro. The motivation would be so the UE 105 may perform some clean up actions related to the previous MPM configuration such as deleting and/or releasing entries predicted according to the previous model, state variables, reset timers, etc. see Monteiro at [0220].
Regarding Claims 27 and 34, Hunukumbure-Monteiro teaches all the limitations of claim 21 and 28 as discussed above.
Hunukumbure doesn’t explicitly teach
wherein the first inference result comprises a mobility-related inference result of a primary cell of the terminal device or a mobility-related inference result of a secondary node of the terminal device
In a similar endeavor Monteiro teaches
wherein the first inference result comprises a mobility-related inference result of a primary cell of the terminal device ("The UE 105 performs mobility predictions (i.e. inference result) using an MPM. Before step 201 is performed, the UE 105 is configured with the MPM, e.g., a first MPM, a current MPM"[0070] Fig. 13, element 1300 and 1305) or a mobility-related inference result of a secondary node of the terminal device ("The network node 101 determines that MPM re-configuration should be performed. The decision may be taken based on the report from step 202. The network node 101 creates MPM re-configuration information (i.e. inference result) as part of step 203, e.g., instructions that MPM re-configuration should be performed, information about the re-configuration etc."[0072] Fig. 3).
Therefore, it would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to combine the method of Hunukumbure with the method suggested by Monteiro. The motivation would be so the UE 105 receives a MPM configuration from the network node 101 and uses this model to perform mobility predictions e.g. predicted RSRP, prediction RSRQ, predicted SINR, next cell or beam, SSB, Channel State Information-Reference Signal (CSI-RS), predict whether the UE 105 is moving to or entering the coverage of, etc. see Monteiro at [0083].
Regarding Claim 36, Hunukumbure-Monteiro teaches all the limitations of claim 35 as discussed above. Further Hunukumbure teaches
wherein the first message requests the apparatus to allocate a resource corresponding to a first target cell to the terminal device (“Then, (4. “Handover Request”) the Source eNB issues a handover request (i.e. a first message) to the Target eNB (i.e. the apparatus), passing necessary information to prepare the handover (i.e. resource allocation) at the target side“,[0005] Fig 7, step 4), and
the first target cell is a predicted serving cell accessible by the terminal device (“Suppose that a connected-mode UE is connected to a Source eNB providing a serving cell, and can receive at least reference signals from a neighbour cell (i.e. target cell) provided by a Target eNB).“,[0005]).
Regarding Claim 37, Hunukumbure-Monteiro teaches all the limitations of claim 35 as discussed above. Further Hunukumbure teaches
wherein, when executed, the instructions cause the apparatus to perform operations comprising: allocating the resource of the first target cell to the terminal device in response to the first message (Then (6. “Handover Request Ack.”) the Target eNB 11 (i.e. first network device) prepares the HO (i.e. resource allocation)…); and
sending indication information of the resource that is of the first target cell and that is allocated to the terminal device ("…and sends the handover request Ack. (i.e. indication of feedback information) to the Source eNB...“,[0005] Fig. 7, steps 6 and 10).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Iyonda L. Lewis whose telephone number is (571)272-4440. The examiner can normally be reached Monday - Friday 8:00am - 4:00pm.
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, Alison Slater can be reached at (571) 270-0375. 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.
/IYONDA L LEWIS/Patent Examiner, Art Unit 2647
Iyonda.Lewis@USPTO.gov
/Alison Slater/Supervisory Patent Examiner, Art Unit 2647
Prosecution Insights