DETAILED ACTION
Response to Remark
This communication is considered fully responsive to the amendment filed on 07/08/26.
Independent claims have been amended.
Claim Rejections - 35 USC § 103
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 of this title, 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 1-3, 5, 6, 8, 10, 12, 13, 15, 17, 20, 23, 25, 32, 38, and 40 are rejected under 35 U.S.C. 103 as being unpatentable over Feki et al. (US 2021/0289406, “Feki”) in view of Futaki (US 2013/0237266, “Futaki”).
Regarding claim 1, Feki discloses a method implemented in a network node of a communication network, the method comprising:
- obtaining communication device context information related to a current status of a communication device (See 301 Fig.3 and 901 Fig.9, obtain a plurality of handover parameter values; See ¶.49, the terminal device may continuously measure the signal quality of the serving base station; See ¶.54, the speed of the terminal device, i.e. the physical quantity of speed that the terminal device is physically moving at; See ¶.56, the considered context corresponding to a given profile of terminal devices in the considered cell or group of cells; See Fig.8, RSRP, cell ID, beam ID; See ¶.93, a serving cell ID, a serving beam ID, and/or one or more measured RSRP values during a time interval per terminal device), and network context information related to a current status of the communication network (See ¶.49, measure the signal quality of the serving base station and neighboring base stations, and report these measurements to the base stations. Handover parameters such as hysteresis margin, time-to-trigger, TTT; See ¶.51, the hysteresis margin may define the entry condition to initiate the handover, when the RSRP measure of a neighbor cell is above the RSRP of the serving cell plus a threshold represented by A3 offset and hysteresis margin; See Fig.2, neighbor cell signal);
- inputting the communication device context information and the network context information to a machine-learning model (See Fig.7-8, inputting cell id, RSRP, beam ID and TTT & Hys into RNN model to be trained; See ¶.4, machine learning model;
PNG
media_image1.png
255
605
media_image1.png
Greyscale
), wherein the machine-learning model outputs a score for at least one candidate handover parameter value based on the communication device context information and the network context information (See 904 Fig.9 and ¶.94, determine a first set of optimal handover parameter values for the plurality of terminal devices; See 905 Fig.9, the first set of optimal handover parameter values is tagged with the historical information of the plurality of terminal devices to obtain a labelled dataset; See Fig.4 and ¶.65, the DQN training function may provide as output a plurality of Q-values associated with a plurality of actions. A Q-value may indicate a total long-term reward associated with an action, whereas r may indicate an immediate reward associated with an action. A deterministic function may be used to select the action with the highest Q-value from the output of the DQN training function. The goal of the software agent may be to maximize the total reward; See ¶.59, KPI (key performance indicator) is considered as score; Examiner’s Note: applicant specification defines that “the output of the machine-learning model may comprise a Key Performance Indicator (KPI). The score may be a KPI”, See ¶.88); and
- selecting at least one handover parameter value for a handover procedure involving the communication device based on the output from the machine-learning model (See ¶.4, using a first machine learning model to select a subset of handover parameter values from the plurality of handover parameter values, obtaining historical information of a plurality of terminal devices; See ¶.49, the handover process may rely on different handover parameters, for example hysteresis margin, denoted herein as M, and/or time-to-trigger, denoted herein as TTT, which may impact handover performance. Thus, the handover performance may be improved by optimizing the handover parameter values; See ¶.51, Hysteresis margin may be applied to avoid triggering unnecessary events caused by rapid fluctuations of the cell's measured quality. The hysteresis margin may define the entry condition to initiate the handover, when the RSRP measure of a neighbor cell is above the RSRP of the serving cell plus a threshold represented by A3 offset and hysteresis margin; See ¶.56, a subset of handover parameter values is selected from the plurality of candidate handover parameter values in order to reduce the number of handover parameter values. The subset of handover parameter values may represent a set of handover parameter values that are relevant in the considered context, for example corresponding to a given profile of terminal devices in the considered cell or group of cells. For example, TTT values may be preselected for terminal devices moving at high speed. A first machine learning model based on reinforcement learning, for example a deep Q-learning network, DQN, may be used to adapt to the environment and select the subset of handover parameter values from the plurality of candidate handover parameter values.), wherein the selected at least one handover parameter value is specific to the communication device (See ¶.59, the optimal handover parameter values are tagged with the plurality of terminal devices represented by vectors of historical information, for example cell ID, beam ID and/or beam RSRP per terminal device; See ¶.90, the subset of handover parameter values selected by the DQN may then be provided to a data labelling function in order to identify which handover parameter values from the subset are optimal for which individual terminal device, and to obtain the historical information per terminal device in order to form the labelled dataset for training the RNN model; See ¶.91, the historical information may comprise a cell ID, a beam ID, and/or one or more measured RSRP values during a time interval per terminal device),
- wherein the at least one candidate handover parameter value comprises candidate handover parameter values corresponding to different types of handover parameter (Feki, See ¶.49, the handover process may rely on different handover parameters, for example hysteresis margin, denoted herein as M, and/or time-to-trigger, denoted herein as TTT, which may impact handover performance. Thus, the handover performance may be improved by optimizing the handover parameter values; See ¶.50-51, FIG. 2 illustrates an example of a handover event, in particular an A3 handover event. For example, when the reference signal received power, RSRP, of the serving cell decreases below an acceptable level, and the RSRP of the neighbor cell becomes higher than the RSRP of the serving cell by a threshold value indicated by the hysteresis margin, a handover may be initiated by the base station of the serving cell after a time interval indicated by the TTT. [0051] Hysteresis margin may be applied to avoid triggering unnecessary events caused by rapid fluctuations of the cell's measured quality. The hysteresis margin may define the entry condition to initiate the handover, when the RSRP measure of a neighbor cell is above the RSRP of the serving cell plus a threshold represented by A3 offset and hysteresis margin: where RSRPN is the RSRP measure of the neighbor cell, RSRPS is the RSRP measure of the serving cell, A3offset is the A3 offset, and M is the hysteresis margin value).
Feki discloses the method of reporting the measurements associated with the handover parameters (Feki, See ¶.49, the terminal device may continuously measure the signal quality of the serving base station and neighboring base stations, and report these measurements to the base stations. The handover process may rely on different handover parameters, for example hysteresis margin, denoted herein as M, and/or time-to-trigger, denoted herein as TTT, which may impact handover performance. Thus, the handover performance may be improved by optimizing the handover parameter values), but does not explicitly disclose what Futaki discloses “wherein the at least one handover parameter value is usable to determine whether handover related measurements are to be reported by the communication device in the handover procedure (Futaki, See ¶.125-133, hysteresis, one of handover parameters, used to decide whether or not a measurement report is to be performed, and the like may be used).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to apply “the at least one handover parameter value is usable to determine whether handover related measurements are to be reported by the communication device in the handover procedure” as taught by Futaki into the system of Feki, so that it provides a way of deciding whether or not a measurement report to be performed after triggering performance of measurement report by using trigger quality parameter (Futaki, See ¶.133).
Regarding claim 2, Feki discloses “inputting at least one candidate handover parameter value to the machine-learning model (See Fig.7).”
Regarding claim 3, Feki discloses “the score indicates an impact of using the at least one candidate handover parameter value during the handover procedure (See ¶.50, for example, when the reference signal received power, RSRP, of the serving cell decreases below an acceptable level, and the RSRP of the neighbor cell becomes higher than the RSRP of the serving cell by a threshold value indicated by the hysteresis margin, a handover may be initiated by the base station of the serving cell after a time interval indicated by the TTT; See ¶.51, Hysteresis margin may be applied to avoid triggering unnecessary events caused by rapid fluctuations of the cell's measured quality. The hysteresis margin may define the entry condition to initiate the handover, when the RSRP measure of a neighbor cell is above the RSRP of the serving cell plus a threshold represented by A3 offset and hysteresis margin: RSRPN>RSRPS+A3offset+M, where RSRPN is the RSRP measure of the neighbor cell, RSRPS is the RSRP measure of the serving cell, A3offset is the A3 offset, and M is the hysteresis margin value; See ¶.58, the historical information may comprise for example a cell ID of a cell that the terminal device has been served by, a beam ID of a beam that the terminal device has been served by, and/or one or more measured RSRP values of the beam reported during a predefined time period; See ¶.59, the set of optimal handover parameter values may be handover parameter values that are determined to maximize a key performance indicator of the plurality of terminal devices, and the optimal handover parameter values are then tagged with the historical information of the corresponding terminal device that they are optimal for. For example, MRO counters may be used as the key performance indicator. MRO counters may indicate the number of different MRO events, for example too early handovers, too late handovers, and/or handovers to incorrect cells).”
Regarding claim 5, Feki discloses “the selecting comprises at least one of: sampling from a probability mass function of the scores; selecting the at least one handover parameter value corresponding to a maximum value of the scores; and selecting the at least one handover parameter value at random from the handover parameter value corresponding to a predetermined number of the top scores (See ¶.59, the set of optimal handover parameter values may be handover parameter values that are determined to maximize a key performance indicator of the plurality of terminal devices, and the optimal handover parameter values are then tagged with the historical information of the corresponding terminal device that they are optimal for. For example, MRO counters may be used as the key performance indicator. MRO counters may indicate the number of different MRO events, for example too early handovers, too late handovers, and/or handovers to incorrect cells).”
Regarding claim 6, Feki discloses “output from the machine-learning model comprises a key performance indicator, KPI (See ¶.59, KPI).”
Regarding claim 8, Feki discloses “a plurality of candidate handover parameter values are input to the machine-learning model, wherein the plurality of candidate handover parameter values comprise sets of candidate handover parameter values, and wherein candidate handover parameter values within the same set each correspond to a different type of handover parameter; and wherein the selecting comprises selecting a set of handover parameter values based on the output from the machine-learning model (See ¶.4, obtaining a plurality of handover parameter values, using a first machine learning model to select a subset of handover parameter values from the plurality of handover parameter values, obtaining historical information of a plurality of terminal devices, determining a first set of optimal handover parameter values for the plurality of terminal devices from the subset of handover parameter values, tagging the first set of optimal handover parameter values with the historical information of the plurality of terminal devices to obtain a labelled dataset, and training a second machine learning model with the labelled dataset, wherein the trained second machine learning model is capable of predicting a second set of optimal handover parameter values for a first terminal device based on historical information of the first terminal device; See further Fig.7 & 9).”
Regarding claim 10, Feki discloses “the at least one candidate handover parameter value is chosen for input to the machine-learning model from a predefined set of possible candidate handover parameters (See 905 Fig.9, tag the first set of optimal handover parameters values).”
Regarding claim 12, Feki discloses “the at least one handover parameter value comprises a threshold value or offset value (See ¶.50, the RSRP of the neighbor cell becomes higher than the RSRP of the serving cell by a threshold value indicated by the hysteresis margin, a handover may be initiated by the base station of the serving cell after a time interval indicated by the TTT; See ¶.51, off set value; See ¶.49, the terminal device may continuously measure the signal quality of the serving base station and neighboring base stations, and report these measurements to the base stations).”
Regarding claim 13, Feki discloses “one of the at least one candidate handover parameter value corresponds to a handover parameter type comprising one of: time to trigger, TTT; a handover hysteresis margin, HM; a hysteresis parameter, Hys; a measurement result of a cell; a threshold parameter, Thresh; a filter coefficient, K; an offset parameter; a cell individual offset, CIO; and a frequency offset (See ¶.49, TTI and hysteresis margin; See Fig.7, TTT & Hys; See ¶.51, A3 offset).”
Regarding claim 15, Feki discloses “the communication device context information comprises signal timing measurements (See ¶.93, measured RSRP values during a time interval per terminal device ).”
Regarding claim 17, Feki discloses “the communication device context information comprises signal power measurements (See ¶.50-51, measuring RSRP).”
Regarding claim 20, Feki discloses “the communication device context information comprises signal quality measurements (See ¶.49, measuring signal quality).”
Regarding claim 23, Feki discloses “the network context information comprises network usage measurements (See ¶.102, efficient use of the resources of the network).”
Regarding claim 25, Feki discloses “the network context information comprises signal propagation measurements (See ¶.52, delay in handover).”
Regarding claim 32, Feki discloses “the steps of the method are repeated for each of a plurality of communication devices in the communication network (See ¶.61, the same trajectory of a given terminal device may be repeated with the subset of handover parameter values in a simulation in order to determine the optimal handover parameter values that maximize the performance of that individual terminal device based on the simulation. The performance may be measured for example with MRO counters).”
Regarding claim 38, it is a network node claim corresponding to the method claim 1 and is therefore rejected for the similar reasons set forth in the rejection of the claim.
Regarding claim 40, it is a system claim corresponding to the claim 38 and is therefore rejected for the similar reasons set forth in the rejection of the claim.
Claims 27 and 31 are rejected under 35 U.S.C. 103 as being unpatentable over Feki in view of Futaki and further in view of Huangfu et al. (US 2023/0179490, “Huangfu”).
Regarding claim 27, Feki and Futaki do not explicitly disclose what Huangfu discloses “the network context information comprises signal interference measurements (Huangfu, See ¶.35, a measurement report of interference power and SINR).”
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to apply “the network context information comprises signal interference measurements” as taught by Huangfu into the system of Feki and Futaki, so that it provides a way for AI/ML model to use interference power as learning parameter (Huangfu, See ¶.396).”
Regarding claim 31, Feki and Futaki do not explicitly discloses what Huangfu discloses “sending the selected at least one handover parameter value to the communication device (Huangfu, See 7 Fig.2, after AI/ML model training, ‘return the output result’ to initiating network element, i.e. terminal device).”
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to apply the method of “sending the selected at least one handover parameter value to the communication device” as taught by Huangfu into the system of Feki and Futaki, so that it provides a way for the terminal device to perform corresponding control based on the output result (Huangfu, See ¶.193).
Response to Arguments
Applicant's arguments filed have been considered. But, in view of the applicant’s amendment to the claims, examiner has clarified and totally remapped the rejection to the argued claim limitations, using the prior art of record in the current prosecution of the claims.
At page 9, with respect to claim 1, applicant argues that any combination of Feki and Futaki fails discloses the newly added limitations by asserting that;
“More particularly, Fcki discloses performing handover by a base station through an algorithm which uses the signal quality measurements along with the help of certain handover parameters such as hysteresis margin and/or Time-to-Trigger (TTT) to avoid triggering unnecessary events caused by rapid fluctuations of the cell's measured quality. Though Feki discloses usage of handover parameters (hysteresis margin/TTT) to perform better handover, but Feki failed to disclose the selection of one handover parameter value that comprises candidate handover parameter values corresponding to different types of handover parameter. Moreover, the cited portion of Feki seems to disclose usage of hysteresis parameter while taking a decision whether to perform handover or not, whereas the present invention discloses selection of one handover parameter value that comprises handover parameter values corresponding to different type of handover parameter. Accordingly, Applicant submits that Feki fails to disclose or teach or suggest at least, for example, the feature of "the at least one candidate handover parameter value comprises candidate handover parameter values corresponding to different types of handover parameter" as recited in amended independent Claim 1. Accordingly, the allowance of independent Claim 1 is respectfully requested.” [applicant’s emphasis added].
In reply, the limitations “the selection of one handover parameter value that comprises candidate handover parameter values corresponding to different types of handover parameter” explicitly read on:
¶.[0004] of Feki discloses “obtaining a plurality of handover parameter values, using a first machine learning model to select a subset of handover parameter values from the plurality of handover parameter values, obtaining historical information of a plurality of terminal devices, determining a first set of optimal handover parameter values for the plurality of terminal devices from the subset of handover parameter values.” [emphasis added].
¶.[0056] of Feki discloses “In step 302, a subset of handover parameter values is selected from the plurality of candidate handover parameter values in order to reduce the number of handover parameter values. The subset of handover parameter values may represent a set of handover parameter values that are relevant in the considered context, for example corresponding to a given profile of terminal devices in the considered cell or group of cells. For example, TTT values may be preselected for terminal devices moving at high speed. A first machine learning model based on reinforcement learning, for example a deep Q-learning network, DQN, may be used to adapt to the environment and select the subset of handover parameter values from the plurality of candidate handover parameter values.” [emphasis added].
¶.[0060] of Feki discloses “the optimal handover parameter values may be determined by testing the subset of handover parameter values with at least a subset of the plurality of terminal devices and selecting a set of handover parameter values that maximize a performance indicator of the at least subset of the plurality of terminal devices. For example, the optimal handover parameter values for a given terminal device may be determined by testing the subset of handover parameter values for a part of the terminal device trajectory. The optimal handover parameter values, for example a pair of a TTT value and a hysteresis margin value, that maximize the performance of the terminal device may then be tagged with the historical information of that individual terminal device.”
In other words, Feki discloses a plurality of handover parameter values such as a pair of a TTT value and a hysteresis margin value, i.e. different types of handover parameter, and the method of selecting a subset of handover parameter values in order to maximize a performance indicator of the at least subset of the plurality of terminal devices and therefore, the examiner respectfully disagrees.
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 date of this final action.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jung H Park whose telephone number is 571-272-8565. The examiner can normally be reached M-F: 7:00 AM-3:00 PM.
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, Derrick Ferris can be reached on 571-272-3123. 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.
/JUNG H PARK/
Primary Examiner, Art Unit 2411
Prosecution Insights