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
The Action is responsive to the Request for Continued Examination comprising Amendments and Remarks filed on 12/9/2025. Claims 1, 3, 7, 8, 13, 14, 19, and 20 are pending claims. Claims 1, 8, and 14 are written in independent form. Claims 2, 4-6, 9-12, and 15-18 have previously been cancelled.
Claim Objections
Claims 1, 8, and 14 are objected to because of the following informalities:
Claims 1, 8 and 14 appear to recite a typographical error by reciting “based on the uplink transmissions…” and then reciting “based on the detected uplink transmissions…”, both after the step of “detect uplink transmissions”. For the purpose of consistency, the claim limitations are being understood as both reciting “based on the detected uplink transmissions…”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 3, 7, 8, 13, 14, 19, and 20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. Independent Claims 1, 8, and 14 contain subject matter “input, to a large language model, the first natural language query,…, and the detected uplink transmissions from the mobile device that represent contextual information of the mobile device;” and “input, to the large language model, the second natural language query,…, and the detected uplink transmissions from the mobile device that represent contextual information of the mobile device;” which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
It is not clearly stated in the written description any input of uplink transmissions into the large language model. It is noted that Applicant does not appear to state in the Remarks dated 12/9/2025 where support for the amendments is drawn from.For purposes of compact prosecution, the claim limitation is being interpreted as being similar to the previous language of “input, to a large language model, the first natural language query,…, and the
Dependent Claims 3, 7, 13, 19, and 20 inherit the deficiencies of their parent claims and are therefore being rejected based upon the same reason(s) stated for their parent claims.
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.
Claims 1, 3, 7, 8, 13, 14, 19, and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claims 1, 8, and 14, the limitation “detect uplink transmissions from the mobile device that include at least an indication of a cell tower connected to the mobile device, a technical capability of the mobile device, performance information associated with the mobile device, and site deployment information associated with the wireless telecommunication network, and that represent contextual information of the mobile device;” renders the claims indefinite because it is unclear whether the “indication of a cell tower connected to the mobile device, a technical capability of the mobile device, performance information associated with the mobile device, and site deployment information associated with the wireless telecommunication network” and the “contextual information of the mobile device” included in the detected uplink transmissions are the same, overlapping, or different sets of data. It is noted that the previous language, before the amendments filed on 12/9/2025, recited a scope of “detect contextual information associated with the mobile device including a cell tower connected to the mobile device, a technical capability of the mobile device, performance information associated with the mobile device, and site deployment information associated with the wireless telecommunication network”. However, the current amended scope is not clear if the contextual information is its own separate set of information included in the detected uplink transmissions.For the purpose of compact prosecution and based on the scope previously recited prior to the current amendments, the limitation is being understood as reciting “detect uplink transmissions from the mobile device, wherein the uplink transmissions contextual information of the mobile device represented by at least an indication of a cell tower connected to the mobile device, a technical capability of the mobile device, performance information associated with the mobile device, and site deployment information associated with the wireless telecommunication network
Dependent Claims 3, 7, 13, 19, and 20 inherit the deficiencies of their parent claims and are therefore being rejected based upon the same reason(s) stated for their parent claims.
Regarding claims 1, 8, and 14, the two limitations “based on the uplink transmissions from the mobile device that represent contextual information of the mobile device, determine whether a user associated with the mobile device is technologically savvy or not technologically savvy:” and “based on the detected uplink transmissions from the mobile device that represent contextual information of the mobile device, determine whether the user associated with the mobile device is technologically savvy or not technologically savvy;” render the claims indefinite because the determination of whether the user associated with the mobile device is technologically savvy or not technologically savvy is performed “based on” the same detected “uplink transmissions from the mobile device that represent contextual information of the mobile device” and it is unclear whether these are the same determinations or different determinations made at two separate times but still based on the same detected “uplink transmissions from the mobile device that represent contextual information of the mobile device”.
Dependent Claims 3, 7, 13, 19, and 20 inherit the deficiencies of their parent claims and are therefore being rejected based upon the same reason(s) stated for their parent claims.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1, 3, 7, 8, 13, 14, 19, and 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-patentable subject matter. The claimed invention is directed to one or more abstract ideas without significantly more. The judicial exception is not integrated into a practical application. The claims do not include additional elements that are sufficient to amount to significantly more than judicial exception. The eligibility analysis in support of these findings is provided below.
As per Claims 1, 8, and 14
STEP 1:In accordance with Step 1 of the eligibility inquiry (as explained in MPEP 2106), the claimed non-transitory, computer-readable storage medium (claims 1, 3, and 7), method (claims 8 and 13), and system (claims 14, 19, and 20) are directed to one of the eligible categories of subject matter and therefore satisfies Step 1.
STEP 2A Prong One:The independent claims 1, 8, and 14 recite the following limitations directed to an abstract idea:
generate an index of multiple websites associated with the wireless telecommunication network,
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by observing and evaluating websites associated with the wireless telecommunication network, and making a judgement and/or opinion of organizing the multiple websites into an index based on the observation and evaluation.
Wherein the multiple websites are obtained via a website crawl;
The limitation recites a mathematical concept of executing a mathematical formula or function in the form of executing a website crawl that obtains information about multiple websites.
based on the detected uplink transmissions from the mobile device that represent contextual information of the mobile device, determine whether a user associated with the mobile device is technologically savvy or not technologically savvy;
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by observing and evaluating contextual information associated with the mobile device, and making a judgement and/or opinion whether a user associated with the mobile device is technologically savvy or not based on the observation and evaluation.
upon determining that the user is technologically savvy, present the first answer to the first natural language query and a link to the first relevant website among the multiple websites associated with the wireless telecommunication network;
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by making a judgement and/or opinion that a user is technologically savvy and based on the judgement and/or opinion, making another judgement and/or opinion to display/present an answer and a link to a relevant website.
upon determining that the user is not technologically savvy, offer to connect the user to an operator of the wireless telecommunication network.
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by making a judgement and/or opinion that a user is not technologically savvy and based on the judgement and/or opinion, making another judgement and/or opinion to offer to connect the user to an operator.
based on the detected uplink transmissions from the mobile device that represent contextual information of the mobile device, determine whether the user associated with the mobile device is technologically savvy or not technologically savvy;
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by observing and evaluating contextual information associated with the mobile device, and making a judgement and/or opinion whether a user associated with the mobile device is technologically savvy or not based on the observation and evaluation.
upon determining that the user is technologically savvy, present the second answer to the second natural language query and a link to the second relevant website among the multiple websites associated with the wireless telecommunication network; and
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by making a judgement and/or opinion that a user is technologically savvy and based on the judgement and/or opinion, making another judgement and/or opinion to display/present an answer and a link to a relevant website.
upon determining that the user is not technologically savvy, offer to connect the user to the operator of the wireless telecommunication network.
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by making a judgement and/or opinion that a user is not technologically savvy and based on the judgement and/or opinion, making another judgement and/or opinion to offer to connect the user to an operator.
STEP 2A Prong Two:Claim 1 recites that the steps are performed using “a non-transitory, computer-readable storage medium”, “a mobile device”, “a wireless telecommunication network”, and “at least one data processor of a system”, which is a high-level recitation of generic computer components and represents mere instructions to apply on a computer as in MPEP 2106.05(f), which does not provide integration into a practical application.
Claim 8 recites that the steps are performed using “a UE” as user equipment and “a wireless telecommunication network”, which is a high-level recitation of generic computer components and represents mere instructions to apply on a computer as in MPEP 2106.05(f), which does not provide integration into a practical application.
Claim 14 recites that the steps are performed using “a non-transitory memory”, “a UE” as user equipment, “a wireless telecommunication network”, and “at least one hardware processor”, which is a high-level recitation of generic computer components and represents mere instructions to apply on a computer as in MPEP 2106.05(f), which does not provide integration into a practical application.
The claims recite the following additional elements:
wherein the multiple websites include information associated with the wireless telecommunication network;
The limitation recites an insignificant extra-solution activity as selecting a particular type of data being used to represent the multiple websites as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Detect uplink transmissions from the mobile device
The limitation recites a high-level recitation of generic computer components and represents mere instructions to apply on a computer as in MPEP 2106.05(f), which does not provide integration into a practical application.
that include at least an indication of a cell tower connected to the mobile device, a technical capability of the mobile device, performance information associated with the mobile device, and site deployment information associated with the wireless telecommunication network, and that represent contextual information of the mobile device;
The limitation recites an insignificant extra-solution activity as selecting a particular type of data included in the uplink transmission from a mobile device as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Obtain a first natural language query from the mobile device;
The limitation recites an insignificant extra solution activity as retrieval of data (ie. Mere data gathering) such as ‘obtaining information’ as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Wherein the first natural language query is obtained when the cell tower connected to the mobile device is a first cell tower connected to the mobile device;
The limitation recites an insignificant extra-solution activity as selecting a particular type of data and context corresponding to or associated with a mobile device and natural language query as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Input, to a large language model, the first natural langue query, the index of multiple websites associated with the wireless telecommunication network, and the contextual information of the mobile device;
The limitation recites an insignificant extra solution activity as sending/receiving of data (ie. Mere data gathering) such as ‘obtaining information’ as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
obtain from the large language model a first answer to the first natural language query,
The limitation recites an insignificant extra solution activity as sending/receiving of data (ie. Mere data gathering) such as ‘obtaining information’ as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
wherein the first answer is a first summary of a first relevant website among the multiple websites associated with the wireless telecommunication network;
The limitation recites an insignificant extra-solution activity as selecting a particular type of data being used to represent the answer obtained/received from the LLM as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Obtain a second natural language query from the mobile device;
The limitation recites an insignificant extra solution activity as retrieval of data (ie. Mere data gathering) such as ‘obtaining information’ as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Wherein the second natural language query is obtained when the cell tower connected to the mobile device is a second cell tower connected to the mobile device;
The limitation recites an insignificant extra-solution activity as selecting a particular type of data and context corresponding to or associated with a mobile device and natural language query as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Input, to the large language model, the second natural langue query, the index of multiple websites associated with the wireless telecommunication network, and the contextual information of the mobile device;
The limitation recites an insignificant extra solution activity as sending/receiving of data (ie. Mere data gathering) such as ‘obtaining information’ as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
obtain from the large language model a second answer to the second natural language query,
The limitation recites an insignificant extra solution activity as sending/receiving of data (ie. Mere data gathering) such as ‘obtaining information’ as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
wherein the second answer is a second summary of a second relevant website among the multiple websites associated with the wireless telecommunication network;
The limitation recites an insignificant extra-solution activity as selecting a particular type of data being used to represent the answer obtained/received from the LLM as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Viewing the additional limitations together and the claim as a whole, nothing provides integration into a practical application.
STEP 2B:
The conclusions for the mere implementation using a computer are carried over and does not provide significantly more.
With respect to “wherein the multiple websites include information associated with the wireless telecommunication network;” identified as insignificant extra-solution activity above this is also considered to be WURC as court-identified see MPEP 2106.05(d)(II)(iv).
With respect to “uplink transmissions that include at least an indication of a cell tower connected to the mobile device, a technical capability of the mobile device, performance information associated with the mobile device, and site deployment information associated with the wireless telecommunication network, and that represent contextual information of the mobile device;” identified as insignificant extra-solution activity above this is also considered to be WURC as court-identified see MPEP 2106.05(d)(II)(iv).
With respect to “Obtain a first natural language query from the mobile device;” identified as insignificant extra-solution activity above this is also WURC as court-identified see MPEP 2106.05(d)(II)(i).
With respect to “Wherein the first natural language query is obtained when the cell tower connected to the mobile device is a first cell tower connected to the mobile device;” identified as insignificant extra-solution activity above this is also considered to be WURC as court-identified see MPEP 2106.05(d)(II)(iv).
With respect to “Input, to a large language model, the first natural langue query, the index of multiple websites associated with the wireless telecommunication network, and the detected contextual information associated with the mobile device;” identified as insignificant extra-solution activity above this is also WURC as court-identified see MPEP 2106.05(d)(II)(i).
With respect to “obtain from the large language model a first answer to the first natural language query,” identified as insignificant extra-solution activity above this is also WURC as court-identified see MPEP 2106.05(d)(II)(i).
With respect to “wherein the first answer is a first summary of a first relevant website among the multiple websites associated with the wireless telecommunication network;” identified as insignificant extra-solution activity above this is also considered to be WURC as court-identified see MPEP 2106.05(d)(II)(iv).
With respect to “Obtain a second natural language query from the mobile device;” identified as insignificant extra-solution activity above this is also WURC as court-identified see MPEP 2106.05(d)(II)(i).
With respect to “Wherein the second natural language query is obtained when the cell tower connected to the mobile device is a second cell tower connected to the mobile device;” identified as insignificant extra-solution activity above this is also considered to be WURC as court-identified see MPEP 2106.05(d)(II)(iv).
With respect to “Input, to a large language model, the second natural langue query, the index of multiple websites associated with the wireless telecommunication network, and the detected contextual information associated with the mobile device;” identified as insignificant extra-solution activity above this is also WURC as court-identified see MPEP 2106.05(d)(II)(i).
With respect to “obtain from the large language model a second answer to the second natural language query,” identified as insignificant extra-solution activity above this is also WURC as court-identified see MPEP 2106.05(d)(II)(i).
With respect to “wherein the second answer is a second summary of a second relevant website among the multiple websites associated with the wireless telecommunication network;” identified as insignificant extra-solution activity above this is also considered to be WURC as court-identified see MPEP 2106.05(d)(II)(iv).
Looking at the claim as a whole does not change this conclusion and the claim is ineligible.
As per Dependent Claims 3, 7, 13, 19, and 20,
STEP 1:In accordance with Step 1 of the eligibility inquiry (as explained in MPEP 2106), the claimed non-transitory, computer-readable storage medium (claims 1, 3, and 7), method (claims 8 and 13), and system (claims 14, 19, and 20) are directed to one of the eligible categories of subject matter and therefore satisfies Step 1.
STEP 2A Prong One:The dependent claims 3, 7, 13, 19, and 20 recite the following limitations directed to an abstract idea:
The limitation(s) of Dependent Claims 3, 13, and 19 includes the step(s) of:
upon determining that the user is not technologically savvy, determine a wait time associated with calling the operator of the wireless telecommunication network and a wait time associated with chatting via text with the operator;
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by making a judgement and/or opinion that a user is not technologically savvy and based on the judgement and/or opinion, making another judgement and/or opinion of a wait time associated with calling the operator and a wait time associated with chatting via text with the operator.
determine whether the wait time associated with calling the operator is less than the wait time associated with chatting via text with the operator;
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by observing and evaluating the wait time associated with calling the operator and the wait time associated with chatting via text with the operator, and based on the observation and evaluating, making a judgement and/or opinion as to which wait time is less than the other.
upon determining that the wait time associated with calling the operator is less than the wait time associated with chatting via text with the operator, call the operator; and
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by making judgement and/or opinion that the wait time associated with calling the operator is less than the wait time associated with chatting via text with the operator, and based on the judgement and/or opinion, making another judgement and/or opinion to call the operator.
upon determining that the wait time associated with calling the operator is greater than the wait time associated with chatting via text with the operator, initiate a text chat with the operator.
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by making judgement and/or opinion that the wait time associated with calling the operator is greater than the wait time associated with chatting via text with the operator, and based on the judgement and/or opinion, making another judgement and/or opinion to initiate a text chat with the operator.
The limitation(s) of Dependent Claims 7 and 20 includes the step(s) of:
wherein the instructions to determine whether the user associated with the mobile device is technologically savvy comprise instructions to:
determine a portion of the multiple webpages that contains technical content;
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by observing and evaluating multiple webpages and based on the observation and evaluation, making a judgement and/or opinion of portions that contain technical content.
determine whether the portion of the multiple webpages that contains the technical content exceeds a predetermined threshold; and
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by observing and evaluating portions of multiple webpages that contain technical content and a predetermined threshold, and making a judgement and/or opinion based on the observation and evaluating that the technical content exceeds a predetermined threshold.
upon determining that the portion of the multiple webpages that contains technical content exceeds the predetermined threshold, determine that the user is technologically savvy.
The limitation recites a mental process of observation, evaluation, judgement, and/or opinion capable of being performed by the human mind by making a judgement and/or opinion that the technical content exceeds a predetermined threshold, and based on the judgement and/or opinion, making another judgement and/or opinion that the user is determined to be technologically savvy.
STEP 2A Prong Two:The claim(s) recite the following additional elements:
The limitation(s) of Dependent Claims 7 and 20 includes the step(s) of:
wherein the instructions to determine whether the user associated with the mobile device is technologically savvy comprise instructions to:
obtain a browsing history associated with the mobile device indicating multiple webpages the mobile device visited;
The limitation recites an insignificant extra solution activity as retrieval of data (ie. Mere data gathering) such as ‘obtaining information’ as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Viewing the additional limitations together and the claim as a whole, nothing provides integration into a practical application.
STEP 2B:
The conclusions for the mere implementation using a computer are carried over and does not provide significantly more.
With respect to “obtain a browsing history associated with the mobile device indicating multiple webpages the mobile device visited;” identified as insignificant extra-solution activity above this is also WURC as court-identified see MPEP 2106.05(d)(II)(i).
Looking at the claim as a whole does not change this conclusion and the claim is ineligible.
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, 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(s) 1, 3, 8, 13, 14, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Pirat et al. (U.S. Pre-Grant Publication No. 2018/0084111, hereinafter referred to as Pirat) and further in view of Hasan et al. (U.S. Pre-Grant Publication No. 2023/0350929, hereinafter referred to as Hasan) and Rappaport (U.S. Pre-Grant Publication No. 2009/0070379).
Regarding Claim 1:
Pirat teaches:
A non-transitory, computer-readable storage medium comprising instructions recorded thereon (Pirat - Para. [0238]),
wherein the instructions provide an answer to a natural language query from a mobile device operating on a wireless telecommunications,
Pirat teaches “The IMR server 122 may also ask an open ended question such as, for example, ‘How can I help you?’ and the customer may speak or otherwise enter a reason for contacting the contact center. The customer's response may then be used by a routing server 124 to route the call or communication to an appropriate contact center resource.” (Para. [0066]) thereby teaching instructions to provide an answer via the appropriate contact center resource to a natural language query from a customer responding to the natural language question “how can I help you?”.
Pirat further teaches a wireless telecommunications network by teaching “The computing device 1500 may include a network interface 1518 to interface to the network 1504 through a variety of connections including, but not limited to, standard telephone lines, local-area network (LAN), or wide area network (WAN) links, broadband connections, wireless connections, or a combination of any or all of the above. (Para. [0254]) and “the contact center system manages resources (e.g. personnel, computers, software programs, data management, and telecommunication equipment) to enable delivery of services via telephone or other communication mechanisms.” (Para. [0060]).
wherein the instructions, when executed by at least one data processor of a system, cause the system to (Para. [0238]):
wherein the multiple websites include information associated with the wireless telecommunication network;
Pirat teaches “an interaction at a website associated with the contact center” (Para. [0094]) and “when the user is browsing the website, the system may identify the user's phone number via the cookie, and when the user calls into the call center with the phone number, the system may match the cookie with the phone number to determine that the user is browsing the website to link the two modalities together” (Para. [0132]) where “the contact center system manages resources (e.g. personnel, computers, software programs, data management, and telecommunication equipment) to enable delivery of services via telephone or other communication mechanisms” (Para. [0060]). Therefore, Pirat teaches associations between website information and the wireless telecommunication network.
Detect uplink transmissions from the mobile device that include at least an indication of [the following content] that represent contextual information of the mobile device:
Pirat teaches “the orchestration module 230 may further be coupled to the multimodal server 125 for receiving context (e.g. user inputs) on one or more modalities, and may forward the context information to the conversation manager 240.” (Para. [0081]).
a technical capability of the mobile device,
Pirat teaches “the predictive analytics module 260 filters the selected subset of channels based on other criteria, such as, for example, a customer's channel preferences, current context of the interaction, customer's device capabilities, and the like.” (Para. [0199])
performance information associated with the mobile device,
Pirat teaches “the system may recognize that the customer is in a public place and cannot enter credit card information via voice, and based on this data, may have rules to send an SMS to continue the interaction via SMS” (Para. [0223]) thereby teaching tracking performance information such as ability to perform a voice input.
obtain a first natural language query from the mobile device,
Pirat teaches “The IMR server 122 may also ask an open ended question such as, for example, “How can I help you?” and the customer may speak or otherwise enter a reason for contacting the contact center. The customer's response may then be used by a routing server 124 to route the call or communication to an appropriate contact center resource.” (Para. [0066]) thereby teaching obtaining a first natural language query from the mobile device in the form of a customer’s response, “either spoken or otherwise entered”.
based on the detected uplink transmissions from the mobile device that represent contextual information of the mobile device, determine whether the user associated with the mobile device is technologically savvy or not technologically savvy;
Pirat teaches “the contact center system may identify that the user is interacting with a website associated with the contact center through the desktop web 225, and based on the user's activities at the website, the user may be offered an opportunity to interact with a contact center resource (e.g., an agent or a self-help system) via a text, receive a callback from the contact center at a time convenient for the customer and/or the contact center, initiate a voice IVR by calling (e.g., click to call) into the contact center, etc.” (Para. [0126])
Pirat further teaches determining a level of technological savviness of the user by teaching “the selection of a modality may be based on various considerations, for example, such as customer segmentation preferences, logical preferences exhibited by the customer in social interactions, historical best hit rate, customer conversion rate, customer mood or personality, statistics collected over time, customer profile, customer capabilities, best or optimal business outcome, call center capabilities, call center load, and/or any other data (e.g., unstructured rich data) collected by the contact center system.” (Para. [0077]). Customer capabilities, and thus technological savviness, is taught by Pirat through examples such as “determine the capabilities of the user's device, and may automatically switch the user to the other media type to receive the faster service when it is determined that the user is capable of communicating via the other media type” (Para. [0136]) and “the customer is incapable of interacting via SMS” (Para. [0223]).
upon determining that the user is technologically savvy, present the first answer to the first natural language query and a link to the first relevant website among the multiple websites associated with the wireless telecommunication network; and
Pirat teaches “the system may identify preferences of the user, user's channel capabilities, contact center capabilities, and/or the like, and provide the opportunity to interact based on the user's preferences, user's capabilities, and/or contact center capabilities.” (Para. [0127]).
Pirat further teaches presenting the answer to the natural language query with relevant links to associated websites by teaching “On the mobile application, contextually relevant options are forwarded to the mobile application to ensure that the user is aware of pertinent resources available to them related to recent actions” where the “contextually relevant options” are presented as relevant “links” in response to a search for the contextually relevant information. (Paras. [0229]-[0230]).
upon determining that the user is not technologically savvy, offer to connect the user to the operator of the wireless telecommunication network.
Pirat teaches “the system may identify preferences of the user, user's channel capabilities, contact center capabilities, and/or the like, and provide the opportunity to interact based on the user's preferences, user's capabilities, and/or contact center capabilities.” (Para. [0127]) and “the contact center system may identify that the user is interacting with a website associated with the contact center through the desktop web 225, and based on the user's activities at the website, the user may be offered an opportunity to interact with a contact center resource (e.g., an agent or a self-help system) via a text, receive a callback from the contact center at a time convenient for the customer and/or the contact center, initiate a voice IVR by calling (e.g., click to call) into the contact center, etc.” (Para. [0126]).
obtain a second natural language query from the mobile device,
Pirat teaches “The IMR server 122 may also ask an open ended question such as, for example, “How can I help you?” and the customer may speak or otherwise enter a reason for contacting the contact center. The customer's response may then be used by a routing server 124 to route the call or communication to an appropriate contact center resource.” (Para. [0066]).
Pirat further teaches “a new orchestration session may be created, and the first modality may be related to the new orchestration session” (Para. [0131]) and “The UCS 127 may also be configured to facilitate maintaining a history of customers' preferences and interaction history, and to capture and store data regarding comments from agents, customer communication history, and the like” (Para. [0074]). thereby teaching obtaining a second natural language query from the mobile device in the form of a customer’s response, “either spoken or otherwise entered” but from the same customer.
based on the detected uplink transmissions from the mobile device that represent contextual information of the mobile device, determine whether the user associated with the mobile device is technologically savvy or not technologically savvy;
Pirat teaches “the contact center system may identify that the user is interacting with a website associated with the contact center through the desktop web 225, and based on the user's activities at the website, the user may be offered an opportunity to interact with a contact center resource (e.g., an agent or a self-help system) via a text, receive a callback from the contact center at a time convenient for the customer and/or the contact center, initiate a voice IVR by calling (e.g., click to call) into the contact center, etc.” (Para. [0126])
Pirat further teaches determining a level of technological savviness of the user by teaching “the selection of a modality may be based on various considerations, for example, such as customer segmentation preferences, logical preferences exhibited by the customer in social interactions, historical best hit rate, customer conversion rate, customer mood or personality, statistics collected over time, customer profile, customer capabilities, best or optimal business outcome, call center capabilities, call center load, and/or any other data (e.g., unstructured rich data) collected by the contact center system.” (Para. [0077]). Customer capabilities, and thus technological savviness, is taught by Pirat through examples such as “determine the capabilities of the user's device, and may automatically switch the user to the other media type to receive the faster service when it is determined that the user is capable of communicating via the other media type” (Para. [0136]) and “the customer is incapable of interacting via SMS” (Para. [0223]).
upon determining that the user is technologically savvy, present the second answer to the second natural language query and a link to the second relevant website among the multiple websites associated with the wireless telecommunication network; and
Pirat teaches “the system may identify preferences of the user, user's channel capabilities, contact center capabilities, and/or the like, and provide the opportunity to interact based on the user's preferences, user's capabilities, and/or contact center capabilities.” (Para. [0127]).
Pirat further teaches presenting the answer to the natural language query with relevant links to associated websites by teaching “On the mobile application, contextually relevant options are forwarded to the mobile application to ensure that the user is aware of pertinent resources available to them related to recent actions” where the “contextually relevant options” are presented as relevant “links” in response to a search for the contextually relevant information. (Paras. [0229]-[0230]).
Pirat further teaches that the answer is the second answer to the second natural language query by teaching
Pirat further teaches “a new orchestration session may be created, and the first modality may be related to the new orchestration session” (Para. [0131]) and “The UCS 127 may also be configured to facilitate maintaining a history of customers' preferences and interaction history, and to capture and store data regarding comments from agents, customer communication history, and the like” (Para. [0074]). thereby teaching obtaining a second natural language query from the mobile device in the form of a customer’s response, “either spoken or otherwise entered” but from the same customer to be answered as a second answer.
upon determining that the user is not technologically savvy, offer to connect the user to the operator of the wireless telecommunication network.
Pirat teaches “the system may identify preferences of the user, user's channel capabilities, contact center capabilities, and/or the like, and provide the opportunity to interact based on the user's preferences, user's capabilities, and/or contact center capabilities.” (Para. [0127]) and “the contact center system may identify that the user is interacting with a website associated with the contact center through the desktop web 225, and based on the user's activities at the website, the user may be offered an opportunity to interact with a contact center resource (e.g., an agent or a self-help system) via a text, receive a callback from the contact center at a time convenient for the customer and/or the contact center, initiate a voice IVR by calling (e.g., click to call) into the contact center, etc.” (Para. [0126]).
Pirat explicitly teaches all of the elements of the claimed invention as recited above except:
generate an index of multiple websites associated with the wireless telecommunication network;
wherein the multiple websites are obtained via a website crawl;
contextual information of the mobile device including
a cell tower connected to the mobile device,
site deployment information associated with the wireless telecommunication network;
wherein the first natural language query corresponds to a first cell tower connected to the mobile device;
wherein the second natural language query corresponds to a second cell tower connected to the mobile device;
input, to a large language model, the first natural language query, the index of multiple websites associated with the wireless telecommunication network, and the contextual information associated with the mobile device;
obtain from the large language model a first answer to the first natural language query,
wherein the first answer is a first summary of a first relevant website among the multiple websites associated with the wireless telecommunication network;
input, to the large language model, the second natural language query, the index of multiple websites associated with the wireless telecommunication network, and the contextual information associated with the mobile device;
obtain from the large language model a second answer to the second natural language query,
wherein the second answer is a second summary of a second relevant website among the multiple websites associated with the wireless telecommunication network;
However, in the related field of endeavor of generating intent responses to user questions, Hasan teaches:
generate an index of multiple websites associated with the wireless telecommunication network;
Hasan teaches “acquire a collection of various documents that contain relevant information. These documents may be obtained from various sources such as research papers, articles, books, manuals, websites, or any other textual resources that cover a wide range of topics” (Para. [0117]).
Hasan further teaches “Knowledge Representation: Each document in the collection may then represented in a format that allows for efficient storage and retrieval. This representation may vary depending on the specific requirements and design of the knowledgebase. It may involve techniques like document indexing, database structures, or other forms of data organization.” (Para. [0119]) and “Indexing and Categorization: To facilitate quick and accurate retrieval of information, the documents in the knowledgebase may be indexed and categorized based on their content. This may involve assigning keywords, tags, or metadata to each document to represent its main themes or topics. It allows for efficient querying and retrieval of relevant documents based on user intents.” (Para. [0120]).
wherein the multiple websites are obtained via a website crawl;
Hasan teaches “acquire a collection of various documents that contain relevant information. These documents may be obtained from various sources such as research papers, articles, books, manuals, websites, or any other textual resources that cover a wide range of topics” (Para. [0117]).
Hasan further teaches “Knowledge Representation: Each document in the collection may then represented in a format that allows for efficient storage and retrieval. This representation may vary depending on the specific requirements and design of the knowledgebase. It may involve techniques like document indexing, database structures, or other forms of data organization.” (Para. [0119]) and “Indexing and Categorization: To facilitate quick and accurate retrieval of information, the documents in the knowledgebase may be indexed and categorized based on their content. This may involve assigning keywords, tags, or metadata to each document to represent its main themes or topics. It allows for efficient querying and retrieval of relevant documents based on user intents.” (Para. [0120]).
Therefore, Hassan teaches obtaining documents from websites via a website crawl that acquires a collection of documents from various sources such as websites.
Input, to a large language model, the first natural langue query, the index of multiple websites associated with the wireless telecommunication network, and the contextual information of the mobile device;
Hasan teaches “if the input query is in the form of a question, the LLM can identify question patterns and provide an appropriate response.” (Para. [0193]), thereby teaching providing at least the query to an LLM. Hasan further teaches “employ[ing] user profiling techniques to tailor responses based on individual preferences, past interactions, or demographic information” (Para. [0009]), and “to generate accurate and contextually appropriate response, the knowledge bank may be analyzed, at block 406. In particular, a Large Language Model (LLM) is utilized to analyze a collection of documents in the knowledge bank. The purpose of this analysis is to identify and understand newly identified intents expressed by users. The LLM analyze the contents of the documents and extracts relevant information, patterns, and relationships within the text” (Para. [0095]). Hasan further teaches “documents may be obtained from various sources such as research papers, articles, books, manuals, websites, or any other textual resources that cover a wide range of topics” (Para. [0117]) and “knowledge representation…may involve techniques like document indexing, database structures, or other forms of data organization” (Para. [0119]) thereby also teaching providing information associated with the knowledgebase(s) such as indexes of documents from websites covering a wide range of topics and contextual information for use by the LLM.
obtain from the large language model a first answer to the first natural language query,
Hasan teaches “if the input query is in the form theof a question, the LLM can identify question patterns and provide an appropriate response.” (Para. [0193]), thereby teaching the LLM providing an answer to a natural language question/query.
wherein the first answer is a first summary of a first relevant website among the multiple websites associated with the wireless telecommunication network;
Hasan teaches “After the LLM is trained, it analyzes the knowledge bank of documents to leverages its understanding of language and context to provide recommendations for optimal responses that are in line with the identified intents, at block 410. These recommended optimal responses may then be used by the virtual agent to generate an accurate and relevant response for the user's query, at block 412.” (Para. [0104]) and “The sentence tokenization includes splitting text into individual sentences. It separates the text based on punctuation marks or specific sentence delimiters. This method is commonly used in tasks that require analyzing text at the sentence level, such as machine translation or text summarization.” (Para. [0184]).
Hasan further teaches “the response generation may be of the following types: Template-based responses…[with] placeholders for dynamic information extracted from the query or knowledgebase…by populating the placeholders with relevant information” (Paras. [0164]-[0165]) thereby teaching summarizing a relevant website with extracted relevant information.
input, to the large language model, the second natural language query, the index of multiple websites associated with the wireless telecommunication network, and the contextual information associated with the mobile device;
Hasan teaches “if the input query is in the form of a question, the LLM can identify question patterns and provide an appropriate response.” (Para. [0193]), thereby teaching providing at least the query to an LLM. Hasan further teaches “employ[ing] user profiling techniques to tailor responses based on individual preferences, past interactions, or demographic information” (Para. [0009]), and “to generate accurate and contextually appropriate response, the knowledge bank may be analyzed, at block 406. In particular, a Large Language Model (LLM) is utilized to analyze a collection of documents in the knowledge bank. The purpose of this analysis is to identify and understand newly identified intents expressed by users. The LLM analyze the contents of the documents and extracts relevant information, patterns, and relationships within the text” (Para. [0095]). Hasan further teaches “documents may be obtained from various sources such as research papers, articles, books, manuals, websites, or any other textual resources that cover a wide range of topics” (Para. [0117]) and “knowledge representation…may involve techniques like document indexing, database structures, or other forms of data organization” (Para. [0119]) thereby also teaching providing information associated with the knowledgebase(s) such as indexes of documents from websites covering a wide range of topics and contextual information for use by the LLM.
obtain from the large language model a second answer to the second natural language query,
Hasan teaches “if the input query is in the form of a question, the LLM can identify question patterns and provide an appropriate response.” (Para. [0193]), thereby teaching the LLM providing an answer to a natural language question/query.
wherein the second answer is a second summary of a second relevant website among the multiple websites associated with the wireless telecommunication network;
Hasan teaches “After the LLM is trained, it analyzes the knowledge bank of documents to leverages its understanding of language and context to provide recommendations for optimal responses that are in line with the identified intents, at block 410. These recommended optimal responses may then be used by the virtual agent to generate an accurate and relevant response for the user's query, at block 412.” (Para. [0104]) and “The sentence tokenization includes splitting text into individual sentences. It separates the text based on punctuation marks or specific sentence delimiters. This method is commonly used in tasks that require analyzing text at the sentence level, such as machine translation or text summarization.” (Para. [0184]).
Hasan further teaches “the response generation may be of the following types: Template-based responses…[with] placeholders for dynamic information extracted from the query or knowledgebase…by populating the placeholders with relevant information” (Paras. [0164]-[0165]) thereby teaching summarizing a relevant website with extracted relevant information.
Thus, it would have been obvious to one of ordinary skill in the art, having the teachings of Hasan and Pirat at the time that the claimed invention was effectively filed, to have combined the Large Language Model for organizing documents and providing relevant responses, as taught by Hasan, with the systems and methods for managing multi-channel engagements to answer user questions, as taught by Pirat.
One would have been motivated to make such combination because while Pirat teaches presenting the answer to the natural language query with relevant links to associated websites by teaching “On the mobile application, contextually relevant options are forwarded to the mobile application to ensure that the user is aware of pertinent resources available to them related to recent actions”, Hasan teaches “By combining the machine learning techniques with context-based content retrieval, the proposed system achieves improved response generation, ensuring better adaptability, and flexibility in identifying intents and delivering accurate and contextually appropriate responses.” (Para. [0056]) and “These techniques may expand the capability of the system by utilizing the LLM for better understanding. By incorporating the LLM into the NLU process, the system benefits from the LLM's unique capabilities to capture intricate language patterns, relationships, and representations. This integration of the LLM enhances the analysis of user queries, leading to more comprehensive intent extraction.” (Para. [0057]) and it would have been obvious to a person having ordinary skill in the art that expanding the channels taught by Pirat to include at least a channel based on the teachings of Hasan, that uses an LLM to analyze and respond to user questions, would improve the user experience by offering the user an additional choice in channel for receiving assistance.
Hasan and Pirat explicitly teach all of the elements of the claimed invention as recited above except:
contextual information of the mobile device including
a cell tower connected to the mobile device,
site deployment information associated with the wireless telecommunication network;
wherein the first natural language query corresponds to a first cell tower connected to the mobile device;
wherein the second natural language query corresponds to a second cell tower connected to the mobile device;
However, in the related field of endeavor of using a clearinghouse to determine answers to questions, Rappaport teaches:
contextual information of the mobile device including
a cell tower connected to the mobile device,
Rappaport teaches “carriers may view the records of all end users 210 to help the carrier see what opportunities exist for it to locate its equipment, and the carriers could also use the clearinghouse to indicate its own desires, needs, interests, and problem areas where they have need to find locations for equipment in the carrier records 212 “ (Para. [0083]) where the end user records include “tower” as an associated asset (Fig. 2).
site deployment information associated with the wireless telecommunication network;
Rappaport teaches site deployment information of the wireless telecom network by teaching “permits carriers or an independent clearinghouse, or a third party intermediary, to communicate with end user customers, or the wireless devices of end-user customers, in order to aid the end-user in determining how and where new or existing telecommunications assets may be deployed or where service and which service is best or more preferred to the end user, while allowing performance or quality of service knowledge or rank ordering of available telecommunication services to be provided to a wireless end-user. The invention furthermore allows for the control of the operation of a wireless device for enhanced operation, in a particular location based on a ranking of performance or specific requests (made either automatically or as preset) by an end-user, or carrier, or a clearinghouse that provides knowledge on multiple carriers.” (Para. [0035]).
wherein the first natural language query is obtained when the cell tower connected to the mobile device is a first cell tower connected to the mobile device;
Rappaport teaches a phone or wireless device 810 connected to a particular tower or access point 825 used for accessing the internet 830 (Fig. 8 & Para. [0099]). Therefore, any query accessing the internet is necessarily associated with a particular cell tower at the time of the query accessing the internet. Rappaport teaches multiple towers by teaching “determine coverage regions, obstacles due to terrain or buildings, and viable locations for towers, antennas, repeaters, nodes, and end user premise equipment.” (Para. [0043]) and “Access to carriers and end-users as described herein allows the Clearinghouse to be private labeled or OEMed by particular carriers, or by particular intermediaries in the infrastructure industry, or entities, such as the American Radio Relay League or JARL, which has many constituents who own towers or have interest in advancing telecom in general” (Para. [0089]).
Rappaport also teaches multiple towers by teaching “by using the Clearinghouse and database for radio quality and service for wireless devices, and by maintaining an on-going list of performance records of users and infrastructure locations, it becomes possible to build a listing of towers, frequencies, types of service, users who have permission/access abilities to the network, coverage regions of a particular tower or transmitting signal, etc. as well as the physical location and proximity of users on one or more wireless services.” (Para. [0118]).
wherein the second natural language query is obtained when the cell tower connected to the mobile device is a second cell tower connected to the mobile device;
Rappaport teaches a phone or wireless device 810 connected to a particular tower or access point 825 used for accessing the internet 830 (Fig. 8 & Para. [0099]). Therefore, any query accessing the internet is necessarily associated with a particular cell tower at the time of the query accessing the internet. Rappaport teaches multiple towers by teaching “determine coverage regions, obstacles due to terrain or buildings, and viable locations for towers, antennas, repeaters, nodes, and end user premise equipment.” (Para. [0043]) and “Access to carriers and end-users as described herein allows the Clearinghouse to be private labeled or OEMed by particular carriers, or by particular intermediaries in the infrastructure industry, or entities, such as the American Radio Relay League or JARL, which has many constituents who own towers or have interest in advancing telecom in general” (Para. [0089]).
Rappaport also teaches multiple towers by teaching “by using the Clearinghouse and database for radio quality and service for wireless devices, and by maintaining an on-going list of performance records of users and infrastructure locations, it becomes possible to build a listing of towers, frequencies, types of service, users who have permission/access abilities to the network, coverage regions of a particular tower or transmitting signal, etc. as well as the physical location and proximity of users on one or more wireless services.” (Para. [0118]).
Thus, it would have been obvious to one of ordinary skill in the art, having the teachings of Rappaport, Hasan, and Pirat at the time that the claimed invention was effectively filed, to have modified the Large Language Model for organizing documents and providing relevant responses, as taught by Hasan, and the systems and methods for managing multi-channel engagements to answer user questions, as taught by Pirat, with the providing of localized content over wireless networks using a clearinghouse, as taught by Rappaport.
One would have been motivated to make such modification because Pirat teaches “the contact center system manages resources (e.g. personnel, computers, software programs, data management, and telecommunication equipment) to enable delivery of services via telephone or other communication mechanisms” (Para. [0060]) and Rappaport teaches improving the delivery of services in a telecom environment by teaching a system that “allows the customers of a carrier to benefit from better service, lower price for service, as well as receive benefits from the carrier for being a ‘helping’ or ‘value added’ customer, etc. while the carrier is able to use the ‘helping’ customer to improve its service or better utilize its resources, better locate its infrastructure, and improve its capital expenditures. In the specific case of a telecom carrier, more effective, reliable and cost effective provisioning and placement of network gear, antennas, bandwidth allocation over its geographic region, more effective equipment or tower locations, etc. results from awareness and access to end users who are in a position to help the carrier.” (Para. [0018]). It would have been obvious to a person having ordinary skill in the art that the methods and system taught by Rappaport would improve the managed resources by the contact center system taught by Pirat.
Regarding Claim 3:
Rappaport, Hasan, and Pirat further teach instructions to:
upon determining that the user is not technologically savvy, determine a wait time associated with calling the operator of the wireless telecommunication network and a wait time associated with chatting via text with the operator;
Pirat teaches “determine a wait time for interacting with a resource associated with the first media channel, and the instructions that cause the processor to identify the second media channel may be in response to identifying that the wait time for the resource at the first media channel exceeds a threshold wait time, and identifying that the second media channel has a wait time satisfying the threshold wait time” (Para. [0015]) thereby teaching determining a wait time for the different media channels. Pirat further teaches the various channels by teaching “interactions between contact center resources (e.g., live agents and self-service systems) and outside entities (e.g., customers) may be conducted over communication channels such as voice/telephony (e.g., telephone calls, voice over IP or VoIP calls, etc.), video (e.g., video chat, video conferencing, etc.), text (e.g., emails, text chat, etc.), and/or other suitable mediums (e.g., social media, etc.)” (Para. [0055]).
determine whether the wait time associated with calling the operator is less than the wait time associated with chatting via text with the operator;
Pirat teaches “determine a wait time for interacting with a resource associated with the first media channel, and the instructions that cause the processor to identify the second media channel may be in response to identifying that the wait time for the resource at the first media channel exceeds a threshold wait time, and identifying that the second media channel has a wait time satisfying the threshold wait time” (Para. [0015]) thereby teaching comparing the wait times between the first and second media channel and determining whether one is less than the other.
upon determining that the wait time associated with calling the operator is less than the wait time associated with chatting via text with the operator, call the operator; and
Pirat teaches “determine a wait time for interacting with a resource associated with the first media channel, and the instructions that cause the processor to identify the second media channel may be in response to identifying that the wait time for the resource at the first media channel exceeds a threshold wait time, and identifying that the second media channel has a wait time satisfying the threshold wait time” (Para. [0015]) and “the user may be offered an opportunity to interact with a contact center resource (e.g., an agent or a self-help system) via a text, receive a callback from the contact center at a time convenient for the customer and/or the contact center, initiate a voice IVR by calling (e.g., click to call) into the contact center, etc.” (Para. [0126]) thereby teaching “call the operator” when that is the media channel as having the lesser wait time.
upon determining that the wait time associated with calling the operator is greater than the wait time associated with chatting via text with the operator, initiate a text chat with the operator.
Pirat teaches “determine a wait time for interacting with a resource associated with the first media channel, and the instructions that cause the processor to identify the second media channel may be in response to identifying that the wait time for the resource at the first media channel exceeds a threshold wait time, and identifying that the second media channel has a wait time satisfying the threshold wait time” (Para. [0015]) and “the user may be offered an opportunity to interact with a contact center resource (e.g., an agent or a self-help system) via a text, receive a callback from the contact center at a time convenient for the customer and/or the contact center, initiate a voice IVR by calling (e.g., click to call) into the contact center, etc.” (Para. [0126]) thereby teaching “interact with…an agent…via a text” when that is the media channel as having the lesser wait time.
Regarding Claim 8:
All of the limitations herein are similar to some or all of the limitations of Claim 1.
Regarding Claim 13:
All of the limitations herein are similar to some or all of the limitations of Claim 3.
Regarding Claim 14:
Some of the limitations herein are similar to some or all of the limitations of Claim 1.
Rappaport, Hasan, and Pirat further teach a system comprising:
at least one hardware processor (Pirat - Para. [0238]); and
at least one non-transitory memory storing instructions, which, when executed by the at least one hardware processor, cause the system to perform steps (Pirat - Para. [0238]).
Regarding Claim 19:
All of the limitations herein are similar to some or all of the limitations of Claim 3.
Claim(s) 7 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Rappaport, Hasan, and Pirat, and further in view of Bronstein et al. (U.S. Patent No. 10,877,980, hereinafter referred to as Bronstein).
Regarding Claim 7:
Rappaport, Hasan, and Pirat further teach:
wherein the instructions to determine whether the user associated with the mobile device is technologically savvy comprise instructions to:
obtain a browsing history associated with the mobile device indicating multiple webpages the mobile device visited;
Pirat teaches “The UCS 127 may also be configured to facilitate maintaining a history of customers' preferences and interaction history, and to capture and store data regarding comments from agents, customer communication history, and the like.” (Para. [0074]) and “the conversation manager 240 may utilize machine learning to determine the next actions or media type that the user may prefer to engage with according to the context of the received events and historical customer data, profile, and other relevant data elements.” (Para. [0090]) where “End users may browse the web pages and get information about the enterprise's products and services.” (Para. [0071]).
Rappaport, Hasan, and Pirat explicitly teach all of the elements of the claimed invention as recited above except:
determine a portion of the multiple webpages that contains technical content;
determine whether the portion of the multiple webpages that contains the technical content exceeds a predetermined threshold; and
upon determining that the portion of the multiple webpages that contains technical content exceeds the predetermined threshold, determine that the user is technologically savvy.
However, in the related field of endeavor of connecting users to helpful resources, Bronstein teaches:
determine a portion of the multiple webpages that contains technical content;
Bronstein teaches analyzing a data set of content related to a user where “a generative statistical model is constructed from the data set. Based on the content data set 220, one or more generative statistical models 230 may be constructed. The generative statistical models 230 identify a list of topics from the data set and also identify a topic percentage based on the probability or likelihood that a word in the data set is associated with a given topic in the identified list of topics.” (41) thereby determining portions of the content that contains technical content or topical content.
determine whether the portion of the multiple webpages that contains the technical content exceeds a predetermined threshold; and
Bronstein teaches using the topic percentage to calculate a topic strength and “a user knowledge score is determined for each user associated with each identified topic” where “user knowledge scores may represent an indication of how knowledgeable a particular user is in regard to a particular topic” (43-44)
upon determining that the portion of the multiple webpages that contains technical content exceeds the predetermined threshold, determine that the user is technologically savvy.
Bronstein teaches “determining that the user is an expert on the topic based on the knowledge score” and (Column 24 Lines 27-29) where “the identified user data may include topics for which the identified user holds the highest user knowledge score” (Col. 16 Lines 5-7), thereby teaching the user is an expert/savvy in the particular topic and maintaining this information as “identified user data” when the score is at least higher than the 2nd highest score (the threshold for being the highest).
Thus, it would have been obvious to one of ordinary skill in the art, having the teachings of Bronstein, Rappaport, Hasan, and Pirat at the time that the claimed invention was effectively filed, to have combined the inclusion of determining a user’s knowledge on a topic as part of the identified user data, as taught by Bronstein, with the providing of localized content over wireless networks using a clearinghouse, as taught by Rappaport, the Large Language Model for organizing documents and providing relevant responses, as taught by Hasan, and the systems and methods for managing multi-channel engagements to answer user questions, as taught by Pirat.
One would have been motivated to make such combination because Bronstein teaches “the identified user data may include topics for which the identified user holds the highest user knowledge score” (Col. 16 Lines 5-7) and “determining that the user is an expert on the topic based on the knowledge score” and (Column 24 Lines 27-29) and it would have been obvious to a person having ordinary skill in the art that tracking the user’s knowledge score and a determination of the user being an expert on a particular topic would provide further insights for the “customer profile” and “customer capabilities” in Pirat’s teachings of performing “the selection of a modality…based on various considerations, for example…customer profile [and] customer capabilities” (Para. [0077]).
Regarding Claim 20:
All of the limitations herein are similar to some or all of the limitations of Claim 7.
Response to Amendment
Applicant’s Amendments, filed on 12/9/2025, are acknowledged and accepted.
In light of the Amendments filed on 12/9/2025, the 112(a) rejection of Claims 1, 3, 7, 8, 13, 14, 19, and 20 has been withdrawn.
In light of the Amendments filed on 12/9/2025, the claim objections of Claims 1, 3, 7, 8, 13, 14, 19, and 20 have been withdrawn.
Response to Arguments
On page 12 of the Remarks filed on 12/9/2025, Applicant argues, with respect to the 101 rejection, that the amended language related to “detected uplink transmissions are used to generate unique queries for the Al systems of the present technology based on the contextual information gleaned from the detected uplink transmissions (i.e., that a user device is connected to a particular cell tower).” and “Under Step 2A Prong One, the present claims do not recite a process performable in the human mind. A human mind cannot detect an uplink transmission from a mobile device that indicates a cell tower connected to the mobile device and determine, based on that detection, an answer to a natural language query of the user. For example, in the case that the uplink transmission is a time division duplex (TDD) transmission, a human mind does not have the requisite receiver component and control logic to receive such a radio signal and interpret contextual information of the mobile device therefrom to generate a response to the natural language query”.Applicant’s argument is moot, because sending and receiving transmissions are generic computer functions and was never stated in the past office actions as something capable of being performed by the human mind. The amended limitations are further addressed in the rejection above.
On pages 12-13 of the Remarks filed on 12/9/2025, Applicant argues, with respect to the 101 rejection, that “under Step 2A Prong Two, the present claims integrate the alleged abstract idea (mental process) into a practical application by automatically detecting uplink transmissions from the mobile device that represent contextual information of the mobile device (e.g., a cell tower connection).”Applicant’s argument is not convincing because sending and receiving transmissions are generic computer functions, and the type of information included in the uplink transmission is not understood as integrating the claimed into a practical application.
On pages 12-13 of the Remarks filed on 12/9/2025, Applicant argues, with respect to the 103 rejection, that Rappaport does not teach the amended language of ‘detect[ing] uplink transmissions from the mobile device that include at least an indication of a cell tower connected to the mobile device, a technical capability of the mobile device, performance information associated with the mobile device, and site deployment information associated with the wireless telecommunication network and that represent contextual information of the mobile device.’… Rather, Rappaport teaches a computerized system that allows telecommunications network carries to find, evaluate, and select locations for their equipment through direct access to end users. See Rappaport Abstract. To this end, in Rappaport, "carriers may view the records of all end users..." to help the carriers identify locations for their equipment. See Rappaport para. [0083]. These records are maintained by a "clearinghouse" (e.g., an intermediary database or entity). See Rappaport para. [0083]. Accordingly, Rappaport does not teach a telecommunications network that detects particular uplink transmissions from a mobile device to identify contextual information.”.Applicant’s argument is not convincing because the Rappaport reference was used to teach that cell towers corresponding to mobile devices could be used as contextual information, but the other references (Pirat and Hasan) were relied upon as teaching receiving other contextual information (Pirat – Para. [0081]) and the actual use of the contextual information as input into an LLM (Hasan – Paras. [0095], [0117], [0119], and [0193]) in the manner in which the claims describe.
On pages 12-13 of the Remarks filed on 12/9/2025, Applicant argues, with respect to the 103 rejection, that “Further, with regard to the connected cell tower. Rappaport does not describe detecting a cell tower connected to a particular mobile device to use as contextual information for said mobile device. Instead, Rappaport merely describes that a "tower" can be included in the clearinghouse record (e.g., a record can be maintained that a certain tower is on land owned by an individual). Thus, Rappaport fails to disclose a technology that identifies a particular cell tower that is connected to (e.g., in wireless communication with) the mobile device. The site deployment contextual information of the present technology fails to be covered by Rappaport for similar reasons.”Applicant’s argument is not convincing because Rappaport teaches “carriers may view the records of all end users 210 to help the carrier see what opportunities exist for it to locate its equipment, and the carriers could also use the clearinghouse to indicate its own desires, needs, interests, and problem areas where they have need to find locations for equipment in the carrier records 212” (Para. [0083]) where the end user records include “tower” as an associated asset (Fig. 2) and “permits carriers or an independent clearinghouse, or a third party intermediary, to communicate with end user customers, or the wireless devices of end-user customers, in order to aid the end-user in determining how and where new or existing telecommunications assets may be deployed or where service and which service is best or more preferred to the end user” (Para. [0035]). Rappaport is collecting cell tower information and using it as contextual information to help and aid the end-user. It is further noted that the claims do not recite using the cell tower information to affect the answers to the natural language queries, just that “the first natural language query is obtained when the cell tower connected to the device is a first cell tower connected to the mobile device.”
On pages 12-13 of the Remarks filed on 12/9/2025, Applicant argues, with respect to the 103 rejection, that “the first independent claim now recites "obtain[ing] a first natural language query from the mobile device, wherein the first natural language query is obtained when the cell tower connected to the mobile device is a first cell tower connected to the mobile device" and "obtain[ing] a second natural language query from the mobile device, wherein the second natural language query is obtained when the cell tower connected to the mobile device is a second cell tower connected to the mobile device." As further clarified with these amendments, the first natural language query is obtained when the mobile device is connected to the first cell tower and the second natural language query is obtained when the mobile device is connected to the second cell tower. Accordingly, the contextual information that the technology uses to build the first and second natural language query differs at least by which cell tower (the first or second) is connected to the mobile device when the first or second natural language query is generated by the user.”Applicant’s argument is moot because it appears to be arguing a scope that is not understood as being reflected in the claims. The amended claims do not recite using the cell tower information to affect the answers to the natural language queries, just that detecting uplink transmissions from the mobile device that “include at least an indication of a cell tower connected to the mobile device” and followed by “the first natural language query is obtained when the cell tower connected to the device is a first cell tower connected to the mobile device.” and the contextual information, including cell tower information, is input into the LLM with the natural language query and an index of multiple websites, the LLM generating an answer to the natural language query summarizing a relevant website.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Mishra (U.S. Pre-Grant Publication No. 2023/0410801) teaches systems, methods, instructions, and other aspects describing automated transcription and associated script generation. In one aspect, a method includes facilitating a voice bot segment of a two-way communication session, where the voice bot segment is between a customer device and a non-human bot agent, and transfer of the session to a human agent device as part of a human voice segment of the two-way communication session, wherein the transfer occurs following a failure of the non-human bot agent to resolve a customer issue. Accessing survey data describing the two-way communication session, wherein the survey data is associated with successful resolution of the customer issue and automatically processing transcript data from the two-way communication with the survey data to identify language data from the transcript associated with resolution of the customer issue. The non-human bot agent is then dynamically updated using the language data.
Dahan et al. (U.S. Pre-Grant Publication No. 2022/0210274) teaches a telephone subnet crawler is used to access automated telephone response systems and index the information, contents and structure contained therein. A database of the information, contents and structure of a plurality of automated telephone response systems is created by the telephone subnet crawler. A user interface provides a waiting party with direct access to the information, contents and structure of the automated telephone response systems contained in the database. Where an automated telephone response system requires user input, the user interface calls the automated telephone response system and navigates to the node requiring user input, provides the user input and displays the results to the user. Where an automated telephone response system connects to an operator, the user interface calls the automated telephone response system, navigates to the node for an operator, and when an operator is detected, calls the user at a user provided callback number.
Al-Alami (U.S. Pre-Grant Publication No. 2012/0130910) teaches a customer support flow system and method is described. In one example, a method includes, receiving an inquiry from a user, forwarding the inquiry to a public user group. Forwarding the inquiry to a customer support agent, applying the inquiry to previously received comments, receiving a comment to the inquiry from at least one of the public user group, the customer support agent, and the applying of the inquiry, and displaying the received comments to the user on a single display.
Sharpe et al. (U.S. Pre-Grant Publication No. 2018/0027118) teaches a request is received for connecting a user with an agent, the request identifying a user interaction with content. A second server is accessed to determine a first score of the user representing a benefit the user has generated for a client that provides the content. A third server is accessed to determine a second score of the user representing overall burden to provide services to the user by the client based on an interaction history of the user with the client. A user value is dynamically determined based on the first score and the second score using a user value determination algorithm that is specifically configured for the client. A list of agent candidates is identified from a pool of agents based on the user value and the collection of real-time data. A first communication session is established between the user and one of the agent candidates.
Mullane et al. (U.S. Pre-Grant Publication No. 2020/0162612) teaches monitoring activities of a mobile device user, predicting (e.g., based on the monitored activities, information stored in memory, or information received from another device, etc.) a reason that the mobile device user has commenced calling the customer service center or will commence calling the customer service center in the near future, selecting a media element based on the predicted reason that the mobile device user has commenced calling the customer service center or will commence calling the customer service center in the near future, and rendering the selected media element on a screen of a mobile device of the mobile device user prior to completing a call to the customer service center associated with the enterprise and until the mobile device user interacts with the mobile device or the rendered media element.
Awasthi et al. (U.S. Pre-Grant Publication No. 2020/014772) teaches establishing communication channel between a user and a resource. A data capturing module captures data corresponding to the user of the web service. A resource identification module identifies the resource based on comparison of one or more attribute of the resource with the data. A determination module determines at least one mode of a communication channel between the User and the resource by comparing a bandwidth of the communication channel available with one of the user and the resource. Examples of the communication channel comprises a video call, an audio call, an automated chat, and an email. A connection module connects the resource to the user via the at least one mode of the communication channel.
Le et al. (U.S. Pre-Grant Publication No. 2022/0414684) teaches using multi-modal regression to predict customer intent to contact a merchant. Multi-modal data including numerical data and unstructured data are extracted from customer interactions with the merchant. Features of the numerical data and the unstructured data are separately extracted and classified using techniques specific to the data types. The features for each type are then separately used to predict probabilities of customer intent. A neural network is used to combine the predictions into a single set of estimates of customer intent. This set of estimates of customer intents is used to estimate a probability that the customer will contact the merchant. The customer is then contacted based on the estimate.
Rizk et al. (U.S. Pre-Grant Publication No. 2019/0034975) teaches a “knowledge score” is a score associated with a user or group of users indicating the knowledge of the user or group of users with respect to a particular topic (or topics). Knowledge scores can be positive or negative or zero, and may exist or not exist. A “neutral” knowledge score may indicate no score, a score indicating awareness but without a strong opinion, or a score indicating awareness but no depth of knowledge. Where no knowledge score exists, user knowledge has not been tested, or records indicate no confirmed knowledge, of the topic. (Para. [0018]).
Fish et al. (U.S. Pre-Grant Publication No. 2005/0080786) teaches customizing search results based on the searcher's actual geographic location when the search query was sent out via a wireless device. The searcher's geographic location information is extracted from, for example, the signals carrying the search query. The search engine compares the searcher's actual geographic location information against the geographic location information contained in the searchable resources to determine one or more parameters and then filters and ranks the search objects based on the determined parameters.
Gaos (U.S. Pre-Grant Publication No. 2003/0046689) teaches a virtual environment created through the combination of technologies. The invention employs the knowledge and experience of a Personal Assistant or Host, created through Artificial Intelligence applications, which assists and guides the user of the environment to products and/or services that they will most likely be interested in purchasing or requiring. The intelligent assistant's choices are based on its experiences with the specific user. The intelligent assistant communicates with the user by means of a speech recognition and speech synthesis device. This invention is an easy to use virtual reality environment that takes advantage of existing technologies and global communications networks such as the Internet without requiring any given degree of computer literacy. This invention includes a virtual intelligent assistant for each user which adapts to its user as it provides individualized guidance. The intelligent assistant or avatar projects human-like features and behaviors appropriate to the preferences of its user and appears as a virtual person to the user.
Harris et al. (U.S. Pre-Grant Publication NO. 2013/0290234) teaches the ICST transforms user service request inputs via ICST components into a service solution executable by an intelligent terminal. In one embodiment, a method is disclosed, comprising: receiving a service request inquiry from a remote terminal; parsing the service request inquiry to obtain service identifying information; querying in a solution cloud based on the obtained service identifying information; retrieving a solution from the solution cloud from the query; generating a downloadable instruction package including the retrieved solution based on source information of the remote terminal; and providing the downloadable instruction package to the remote terminal.
Nguyen et al. (U.S. Pre-Grant Publication No. 2022/0078282) teaches a method to determine a user intent when a user device initiates an interactive voice response (IVR) call with a wireless telecommunication network. A processor can detect the IVR call initiated with the network and determine whether the user device is a member of the network. Upon determining that the user device is a member of the network, the processor can obtain user history including interaction history between the user and the network. Based on the user history, the processor can predict the user intent when the user initiates the IVR call. The processor can detect whether user device is a 5G capable device. Upon the determining that the device is 5G capable and based on the predicted user intent, the processor can suggest to the user an application configured to execute on the user device and configured to address the predicted user intent.
Carlson et al. (U.S. Patent No. 10,417,345) teaches a customer service agent (CSA) is able to assist a customer with obtaining a desired response from a speech-controlled appliance while protecting customer data. The customer service agent submits queries to a natural language understanding (NLU) processor that performs entity resolution using personalized library information stored in an entity library based on the customer identity information and/or an device identifier. The CSA is shielded from the entity library itself, as well as data stored on the speech-controlled appliance. The CSA can instruct the NLU processor to deliver results to multiple endpoints, including both the customer's appliance and the CSA agent's console.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROBERT F MAY whose telephone number is (571)272-3195. The examiner can normally be reached Monday-Friday 9:30am to 6pm.
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, Boris Gorney can be reached on 571-270-5626. 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.
/ROBERT F MAY/Examiner, Art Unit 2154 1/8/2026
/SYED H HASAN/Primary Examiner, Art Unit 2154